撰寫 研究論文履歷學位論文研究計畫書研究論文 少些繁瑣雜務。
Oleafly 是一款免費的桌面工作區,可用 LaTeX、Typst 與 Markdown 撰寫論文。在同一處尋找文獻、管理引用,看著論文逐步成形。請 AI 助理修改某個章節、製作圖表或修復失敗的建置,所有變更都能先審閱。你的專案以你自己擁有的一般檔案保存,編輯器可以搭配 AI 使用,也可以完全不用。
\[ E = h\nu \]\[ E = h\nu \]\[ \int_{-\infty}^{\infty} e^{-x^2}\,dx = \sqrt{\pi} \]\[ \Delta G = \Delta H - T\Delta S \]\[ \Delta G = \Delta H - T\Delta S \]\[ a^2 + b^2 = c^2 \]



+2
重新編譯
results.tex 裡有 3 位共同作者


+2
編譯
in mammary epithelial cells
Figure 1: Growth factors reach ERK through one cascade but leave different temporal signatures. (a) Receptor tyrosine kinases converge on the RAS–RAF–MEK–ERK module. (b) Single-cell ERK activity from the kinase translocation reporter after stimulation at t = 0.
Cells read growth factors through a small number of shared kinases, yet they respond to EGF, HGF and IGF-1 with different fates. We imaged ERK activity in 2,184 MCF10A cells with a kinase translocation reporter and found that each ligand produces pulses at a characteristic frequency rather than a characteristic amplitude. Frequency alone identifies the ligand in 91 percent of cells.
Epidermal growth factor, hepatocyte growth factor and insulin-like growth factor all reach the nucleus through the same RAS–RAF–MEK–ERK module [1], yet epithelial cells answer them with migration, scattering or growth. How a single kinase carries that distinction has been a long-standing question. Early work in PC-12 cells tied fate to whether ERK activity was transient or sustained [2, 3].
Live-cell reporters changed the picture. In single cells ERK does not rise and settle; it fires in discrete pulses, and the pulse frequency tracks the growth factor dose [4, 5]. Here we ask whether frequency also encodes which growth factor a cell has seen.
We find that it does. Each ligand sets its own pulse rate, the rate survives changes in dose, and cells that keep pulsing are the ones that go on to divide. The same code is rescaled, not erased, in cells carrying an activating RAS mutation. Blocking the pulses with a MEK inhibitor at 60 minutes stopped division under all three ligands. Section 2 sets out these results, Section 3 discusses what they mean for signalling by timing, and Section 4 gives the imaging and decoding methods.
We stimulated MCF10A cells expressing the ERK kinase translocation reporter [6] with saturating doses of EGF, HGF or IGF-1 and tracked nuclear and cytoplasmic signal every two minutes in 2,184 cells for four hours. All three ligands produced the same first spike within ten minutes (Figure 1b). After that the responses diverged: EGF drove pulses about every 19 minutes, HGF about every 41, and IGF-1 rarely more than once an hour (Table 1).
Table 1: Pulse statistics between 15 and 120 minutes after stimulation. Medians across cells.
| Ligand | Dose | Pulses/h | Width | Cells |
| EGF | 20 | 3.1 | 7.8 | 812 |
| HGF | 50 | 1.5 | 8.4 | 694 |
| IGF-1 | 100 | 0.8 | 9.6 | 521 |
| Vehicle | – | 0.2 | 11.2 | 157 |
Pulse amplitude overlapped almost completely between ligands, so we trained a decoder on inter-pulse intervalsthe gaps between pulses alone. Given the first two hours of a single cell's trace, it named the ligand correctly in 91 percent of held-out cells, compared with 47 percent for a decoder that saw only amplitudes. Shuffling the intervals within each cell removed the signal, and so did pooling cells across doses.
A decoder trained on amplitudes alone did no better than chance for HGF against IGF-1, while interval-based decoding separated all three ligands after the first hour of imaging.
Cells that kept pulsing past the second hour entered S phase within 18 hours in 74 percent of cases, against 21 percent for cells whose pulses stopped early (Figure 2). Pulse count over the first four hours predicted entry better than mean ERK activity over the same window.
Frequency coding lets one kinase carry several messages without crosstalk at the level of amplitude.
Mutant RAS rescales this code rather than erasing it [7], which suggests the frequency channel survives oncogenic signalling and could be read by downstream targets that integrate over time.
MCF10A cells were imaged every two minutes for four hours on a widefield microscope with environmental control. Nuclear and cytoplasmic reporter signal was segmented automatically and checked by hand for a random subset of cells.
Lucas Moreau
編輯者
正在編輯 sections/methods.tex
Daniel Hart
編輯者
正在編輯 sections/results.tex
- 語言分析已分析目前的專案修訂版本
- 正在編譯正在產生並驗證 PDF 輸出
- 正在算繪 PDF正在等待已驗證的編譯輸出
Single-Fault LATEX Compilation Repair
Independent Researcher
San Jose, CA, USA
Abstract—Compilation repair for LaTeX is easy to score badly. A candidate may compile after deleting or hiding content, while exact source equality rejects valid alternative repairs. We present TeXFix-Bench, a controlled benchmark for repairing complete, broken LaTeX sources under a pinned engine. The generator applies 12 deterministic single-fault operators to 13 hand-authored seed documents. It retains 627 engine-validated rows, comprising 300 unique hard-track inputs and 67 unique warning-only inputs after hash deduplication.
Index Terms—automated program repair, LaTeX, benchmark, compilation, large language models, reproducibility
LaTeX compilation failures are a practical target for automated repair. A missing delimiter or misspelled control sequence can prevent a complete document from building, and the first reported diagnostic may be distant from the underlying fault. LLM-assisted writing systems now operate inside LaTeX editors , but their publications do not provide a public, engine-pinned evaluation of compilation-failure repair.
Program repair benchmarks pair a defect with an executable oracle and a fixed harness . TeXFix-Bench studies a narrower contract: a broken source document in, a repaired full source out, under a specified engine.
TexOCR-Bench evaluates page-image-to-LaTeX reconstruction , and EqFix repairs errors in individual equations by synthesizing rules from examples . Overfitting to a weak oracle is a known hazard .
A system receives one broken source file and returns one repaired source file. The engine, its version, and the build command are fixed for every attempt.
Every generated row passes an engine gate before it is retained, and duplicate broken sources are removed by SHA-256 so that no input is scored twice .
Compile Recovery requires a successful Tectonic 0.17.0 run and at least 0.80 token-level LCS similarity between text extracted from the candidate and reference PDFs. Normalized exact match sits beside it, because compilation alone cannot separate a faithful repair from a deletion .
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
| System | CR | CR % | NEM | Fail |
| Identity | 0/86 | 0.0 | 0/86 | 0 |
| Rule | 34/86 | 39.5 | 28/86 | 0 |
| Qwen-7B + fb | 57/86 | 66.3 | 17/86 | 0 |
| MiniMax M3 | 75/86 | 87.2 | 50/86 | 2 |
| DeepSeek V4 | 81/86 | 94.2 | 38/86 | 2 |
| Gemini 3.5 | 82/86 | 95.3 | 26/86 | 0 |
| Claude S5 | 85/86 | 98.8 | 52/86 | 0 |
| GPT-5.6 Sol | 85/86 | 98.8 | 66/86 | 1 |
| Grok 4.5 | 85/86 | 98.8 | 59/86 | 0 |
Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs, yet their normalized exact-match counts are 52, 66, and 59 . Compilation and edit precision must be reported together.
The contribution is an auditable task definition, an executable oracle, a fixed cohort, and a replayable candidate ledger.
[1]R. Just, D. Jalali, and M. D. Ernst, “Defects4J: A database of existing faults to enable controlled testing studies for Java programs,” in Proc. ISSTA, 2014, pp. 437–440.
[2]C. Le Goues, N. Holtschulte, E. K. Smith, Y. Brun, P. Devanbu, S. Forrest, and W. Weimer, “The ManyBugs and IntroClass benchmarks for automated repair of C programs,” IEEE Trans. Softw. Eng., vol. 41, no. 12, pp. 1236–1256, 2015.
[3]C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and K. Narasimhan, “SWE-bench: Can language models resolve real-world GitHub issues?” in Proc. ICLR, 2024.
[4]M. Chen et al., “Evaluating large language models trained on code,” arXiv:2107.03374, 2021.
[5]E. K. Smith, E. T. Barr, C. Le Goues, and Y. Brun, “Is the cure worse than the disease? Overfitting in automated program repair,” in Proc. ESEC/FSE, 2015, pp. 532–543.
[6]R. A. DeMillo, R. J. Lipton, and F. G. Sayward, “Hints on test data selection: Help for the practicing programmer,” Computer, vol. 11, no. 4, pp. 34–41, 1978.
[7]Y. Jia and M. Harman, “An analysis and survey of the development of mutation testing,” IEEE Trans. Softw. Eng., vol. 37, no. 5, pp. 649–678, 2011.
[8]R. Gupta, S. Pal, A. Kanade, and S. Shevade, “DeepFix: Fixing common C language errors by deep learning,” in Proc. AAAI, vol. 31, no. 1, pp. 1345–1351, 2017.
[9]M. Yasunaga and P. Liang, “Graph-based, self-supervised program repair from diagnostic feedback,” in Proc. ICML, PMLR, vol. 119, pp. 10799–10808, 2020.
[10]F. Zhu, Z. Liu, G. Yang, J. Li, and S. Cheung, “EqFix: Fixing LaTeX equation errors by examples,” in SETTA 2022, LNCS 13649, pp. 89–109.
[11]K. Wang et al., “TexOCR-Bench: Benchmarking page-image-to-LaTeX reconstruction,” in Proc. 64th ACL, Vol. 1, 2026.
[12]H. Wen, Z. Zhang, and Y. Li, “OverleafCopilot: Empowering academic writing in Overleaf with large language models,” arXiv:2403.09733, 2024.
[13]S. Hou et al., “PaperDebugger: Assisting scientific writing, review, and editing,” in Companion Proc. ACM Web Conf., 2026.
[14]J. Tan, K. Zhang, and X. Chen, “Inconsistencies in TeX-produced documents,” in Proc. ISSTA, 2024.
[15]L. Zheng et al., “Judging LLM-as-a-judge with MT-Bench and Chatbot Arena,” Adv. Neural Inf. Process. Syst., vol. 36, pp. 46595–46623, 2023.
[16]A. Panickssery, S. R. Bowman, and S. Feng, “LLM evaluators recognize and favor their own generations,” Adv. Neural Inf. Process. Syst., vol. 37, 2024.
[17]B. Hui et al., “Qwen2.5-Coder technical report,” arXiv:2409.12186, 2024.
[18]Meta AI, “Llama 3.2 model card,” 2024.
[19]E. Kassis et al., “Agent skills for reproducible research agents,” arXiv:2609.00065, 2026.
ibitem{legoues2015manybugs}
main.tex:956
- 步數
- 1
- 輸入
- 5,144
- 輸出
- 467
- 執行次數
- 1
- 步數
- 3
- token 數
- 39,035
費用是依公開的模型價格估算,並非實際帳單金額。
使用你自己的 API 金鑰(OpenAI、Anthropic、Groq 等),或用 Ollama 在本機執行模型。助理可以讀取與編輯檔案、編譯專案,並驗證 PDF。
連接供應商用 Ollama 執行本機模型
你今天想做什麼?正在處理「TeXFix-Bench: LaTeX Repair Bench...」
Comprehensive citation management for academic research. Search OpenAlex, PubMed, and Google Scholar for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain formats are reference-only and unknown formats fail closed.
Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Use when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts.
正在處理「TeXFix-Bench: LaTeX Repair Bench...」
Claude Code
能耗比較需要一個佐證來源。我在引言中找到了這項論點,但它引用的文獻談的是偵測準確度。你的檔案沒有變動。
- 衛星火災偵測
- 低功耗感測網路
- TinyML 與量化推論
我只會保留具有可驗證 DOI 中繼資料的結果。
write_filereferences.bib第 1 行
references.bib第一處變更 · L1@article{open_science2015, title = {Estimating the Reproducibility of Psychological Science},@article{giglio2003, author = {Giglio, Louis and Descloitres, Jacques and Justice, Christopher O.}, title = {An Enhanced Contextual Fire Detection Algorithm for {MODIS}}, journal = {Remote Sensing of Environment}, year = {2003}, doi = {10.1016/S0034-4257(03)00184-6}}replace_in_filemain.tex第 21 行
main.tex第一處變更 · L21Program repair benchmarks pair a defect with an executable oracle and afixed harness~\cite{just2014defects4j,legoues2015manybug}. SWE-bench extendsfixed harness~\cite{just2014defects4j,legoues2015manybugs}. SWE-bench extendsthe contract to repository-scale issues~\cite{jimenez2024swebench}.TeXFix-Bench studies a narrower contract: a system receives an existingTeXFix-Bench studies a narrower contract~\cite{zhu2022eqfix}: a system receivesSingle-Fault LATEX Compilation Repair
Independent Researcher
San Jose, CA, USA
Abstract—Compilation repair for LaTeX is easy to score badly. A candidate may compile after deleting or hiding content, while exact source equality rejects valid alternative repairs. We present TeXFix-Bench, a controlled benchmark for repairing complete, broken LaTeX sources under a pinned engine. The generator applies 12 deterministic single-fault operators to 13 hand-authored seed documents. It retains 627 engine-validated rows, comprising 300 unique hard-track inputs and 67 unique warning-only inputs after hash deduplication.
Index Terms—automated program repair, LaTeX, benchmark, compilation, large language models, reproducibility
LaTeX compilation failures are a practical target for automated repair. A missing delimiter or misspelled control sequence can prevent a complete document from building, and the first reported diagnostic may be distant from the underlying fault. LLM-assisted writing systems now operate inside LaTeX editors , but their publications do not provide a public, engine-pinned evaluation of compilation-failure repair.
Program repair benchmarks pair a defect with an executable oracle and a fixed harness . TeXFix-Bench studies a narrower contract: a broken source document in, a repaired full source out, under a specified engine.
TexOCR-Bench evaluates page-image-to-LaTeX reconstruction , and EqFix repairs errors in individual equations by synthesizing rules from examples . Overfitting to a weak oracle is a known hazard .
A system receives one broken source file and returns one repaired source file. The engine, its version, and the build command are fixed for every attempt.
Every generated row passes an engine gate before it is retained, and duplicate broken sources are removed by SHA-256 so that no input is scored twice .
Compile Recovery requires a successful Tectonic 0.17.0 run and at least 0.80 token-level LCS similarity between text extracted from the candidate and reference PDFs. Normalized exact match sits beside it, because compilation alone cannot separate a faithful repair from a deletion .
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
| System | CR | CR % | NEM | Fail |
| Identity | 0/86 | 0.0 | 0/86 | 0 |
| Rule | 34/86 | 39.5 | 28/86 | 0 |
| Qwen-7B + fb | 57/86 | 66.3 | 17/86 | 0 |
| MiniMax M3 | 75/86 | 87.2 | 50/86 | 2 |
| DeepSeek V4 | 81/86 | 94.2 | 38/86 | 2 |
| Gemini 3.5 | 82/86 | 95.3 | 26/86 | 0 |
| Claude S5 | 85/86 | 98.8 | 52/86 | 0 |
| GPT-5.6 Sol | 85/86 | 98.8 | 66/86 | 1 |
| Grok 4.5 | 85/86 | 98.8 | 59/86 | 0 |
Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs, yet their normalized exact-match counts are 52, 66, and 59 . Compilation and edit precision must be reported together.
The contribution is an auditable task definition, an executable oracle, a fixed cohort, and a replayable candidate ledger.
[1]R. Just, D. Jalali, and M. D. Ernst, “Defects4J: A database of existing faults to enable controlled testing studies for Java programs,” in Proc. ISSTA, 2014, pp. 437–440.
[2]C. Le Goues, N. Holtschulte, E. K. Smith, Y. Brun, P. Devanbu, S. Forrest, and W. Weimer, “The ManyBugs and IntroClass benchmarks for automated repair of C programs,” IEEE Trans. Softw. Eng., vol. 41, no. 12, pp. 1236–1256, 2015.
[3]C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and K. Narasimhan, “SWE-bench: Can language models resolve real-world GitHub issues?” in Proc. ICLR, 2024.
[4]M. Chen et al., “Evaluating large language models trained on code,” arXiv:2107.03374, 2021.
[5]E. K. Smith, E. T. Barr, C. Le Goues, and Y. Brun, “Is the cure worse than the disease? Overfitting in automated program repair,” in Proc. ESEC/FSE, 2015, pp. 532–543.
[6]R. A. DeMillo, R. J. Lipton, and F. G. Sayward, “Hints on test data selection: Help for the practicing programmer,” Computer, vol. 11, no. 4, pp. 34–41, 1978.
[7]Y. Jia and M. Harman, “An analysis and survey of the development of mutation testing,” IEEE Trans. Softw. Eng., vol. 37, no. 5, pp. 649–678, 2011.
[8]R. Gupta, S. Pal, A. Kanade, and S. Shevade, “DeepFix: Fixing common C language errors by deep learning,” in Proc. AAAI, vol. 31, no. 1, pp. 1345–1351, 2017.
[9]M. Yasunaga and P. Liang, “Graph-based, self-supervised program repair from diagnostic feedback,” in Proc. ICML, PMLR, vol. 119, pp. 10799–10808, 2020.
[10]F. Zhu, Z. Liu, G. Yang, J. Li, and S. Cheung, “EqFix: Fixing LaTeX equation errors by examples,” in SETTA 2022, LNCS 13649, pp. 89–109.
[11]K. Wang et al., “TexOCR-Bench: Benchmarking page-image-to-LaTeX reconstruction,” in Proc. 64th ACL, Vol. 1, 2026.
[12]H. Wen, Z. Zhang, and Y. Li, “OverleafCopilot: Empowering academic writing in Overleaf with large language models,” arXiv:2403.09733, 2024.
[13]S. Hou et al., “PaperDebugger: Assisting scientific writing, review, and editing,” in Companion Proc. ACM Web Conf., 2026.
[14]J. Tan, K. Zhang, and X. Chen, “Inconsistencies in TeX-produced documents,” in Proc. ISSTA, 2024.
[15]L. Zheng et al., “Judging LLM-as-a-judge with MT-Bench and Chatbot Arena,” Adv. Neural Inf. Process. Syst., vol. 36, pp. 46595–46623, 2023.
[16]A. Panickssery, S. R. Bowman, and S. Feng, “LLM evaluators recognize and favor their own generations,” Adv. Neural Inf. Process. Syst., vol. 37, 2024.
[17]B. Hui et al., “Qwen2.5-Coder technical report,” arXiv:2409.12186, 2024.
[18]Meta AI, “Llama 3.2 model card,” 2024.
[19]E. Kassis et al., “Agent skills for reproducible research agents,” arXiv:2609.00065, 2026.
@article{giglio2003, title = {An Enhanced Contextual Fire Detection Algorithm for MODIS}, year = {2003},}@article{schroeder2014, title = {The New VIIRS 375 m Active Fire Detection Data Product}, year = {2014},}@article{dampage2022, title = {Forest Fire Detection System Using Wireless Sensor Networks}, year = {2022},}@article{adumanu2018, title = {Energy-Harvesting Wireless Sensor Networks: A Review}, year = {2018},}@article{adelantado2017, title = {Understanding the Limits of LoRaWAN}, year = {2017},}@article{bai2018, title = {An Empirical Evaluation of Generic Convolutional Networks}, year = {2018},}@article{jacob2018, title = {Quantization and Training of Neural Networks}, year = {2018},}@article{ray2022, title = {A Review on TinyML}, year = {2022},}@article{geifman2017, title = {Selective Classification for Deep Neural Networks}, year = {2017},}在下方連接你使用的供應商。金鑰只會存放在本機。儲存其中一組就會設為預設。
你可以在對話面板的下拉選單中,切換已設定的供應商與模型。
每次開始新對話時都會使用。你仍可在對話面板為個別對話切換模型。
會以你的個人風格與偏好加入每一次 AI 請求。助理會在內建行為之上遵循這些內容,但無法覆寫它的工具或安全規則。
允許 AI 擷取 PDF 頁面允許代理程式將編譯後的頁面轉成點陣圖,以進行視覺版面檢查。若不想把頁面影像傳給供應商,請停用。
- 語言分析已分析目前的專案修訂版本
- 正在編譯正在產生並驗證 PDF 輸出
- 正在算繪 PDF正在等待已驗證的編譯輸出
Single-Fault LATEX Compilation Repair
Independent Researcher
San Jose, CA, USA
Abstract—Compilation repair for LaTeX is easy to score badly. A candidate may compile after deleting or hiding content, while exact source equality rejects valid alternative repairs. We present TeXFix-Bench, a controlled benchmark for repairing complete, broken LaTeX sources under a pinned engine. The generator applies 12 deterministic single-fault operators to 13 hand-authored seed documents. It retains 627 engine-validated rows, comprising 300 unique hard-track inputs and 67 unique warning-only inputs after hash deduplication.
Index Terms—automated program repair, LaTeX, benchmark, compilation, large language models, reproducibility
LaTeX compilation failures are a practical target for automated repair. A missing delimiter or misspelled control sequence can prevent a complete document from building, and the first reported diagnostic may be distant from the underlying fault. LLM-assisted writing systems now operate inside LaTeX editors , but their publications do not provide a public, engine-pinned evaluation of compilation-failure repair.
Program repair benchmarks pair a defect with an executable oracle and a fixed harness . TeXFix-Bench studies a narrower contract: a broken source document in, a repaired full source out, under a specified engine.
TexOCR-Bench evaluates page-image-to-LaTeX reconstruction , and EqFix repairs errors in individual equations by synthesizing rules from examples . Overfitting to a weak oracle is a known hazard .
A system receives one broken source file and returns one repaired source file. The engine, its version, and the build command are fixed for every attempt.
Every generated row passes an engine gate before it is retained, and duplicate broken sources are removed by SHA-256 so that no input is scored twice .
Compile Recovery requires a successful Tectonic 0.17.0 run and at least 0.80 token-level LCS similarity between text extracted from the candidate and reference PDFs. Normalized exact match sits beside it, because compilation alone cannot separate a faithful repair from a deletion .
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
| System | CR | CR % | NEM | Fail |
| Identity | 0/86 | 0.0 | 0/86 | 0 |
| Rule | 34/86 | 39.5 | 28/86 | 0 |
| Qwen-7B + fb | 57/86 | 66.3 | 17/86 | 0 |
| MiniMax M3 | 75/86 | 87.2 | 50/86 | 2 |
| DeepSeek V4 | 81/86 | 94.2 | 38/86 | 2 |
| Gemini 3.5 | 82/86 | 95.3 | 26/86 | 0 |
| Claude S5 | 85/86 | 98.8 | 52/86 | 0 |
| GPT-5.6 Sol | 85/86 | 98.8 | 66/86 | 1 |
| Grok 4.5 | 85/86 | 98.8 | 59/86 | 0 |
Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs, yet their normalized exact-match counts are 52, 66, and 59 . Compilation and edit precision must be reported together.
The contribution is an auditable task definition, an executable oracle, a fixed cohort, and a replayable candidate ledger.
[1]R. Just, D. Jalali, and M. D. Ernst, “Defects4J: A database of existing faults to enable controlled testing studies for Java programs,” in Proc. ISSTA, 2014, pp. 437–440.
[2]C. Le Goues, N. Holtschulte, E. K. Smith, Y. Brun, P. Devanbu, S. Forrest, and W. Weimer, “The ManyBugs and IntroClass benchmarks for automated repair of C programs,” IEEE Trans. Softw. Eng., vol. 41, no. 12, pp. 1236–1256, 2015.
[3]C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and K. Narasimhan, “SWE-bench: Can language models resolve real-world GitHub issues?” in Proc. ICLR, 2024.
[4]M. Chen et al., “Evaluating large language models trained on code,” arXiv:2107.03374, 2021.
[5]E. K. Smith, E. T. Barr, C. Le Goues, and Y. Brun, “Is the cure worse than the disease? Overfitting in automated program repair,” in Proc. ESEC/FSE, 2015, pp. 532–543.
[6]R. A. DeMillo, R. J. Lipton, and F. G. Sayward, “Hints on test data selection: Help for the practicing programmer,” Computer, vol. 11, no. 4, pp. 34–41, 1978.
[7]Y. Jia and M. Harman, “An analysis and survey of the development of mutation testing,” IEEE Trans. Softw. Eng., vol. 37, no. 5, pp. 649–678, 2011.
[8]R. Gupta, S. Pal, A. Kanade, and S. Shevade, “DeepFix: Fixing common C language errors by deep learning,” in Proc. AAAI, vol. 31, no. 1, pp. 1345–1351, 2017.
[9]M. Yasunaga and P. Liang, “Graph-based, self-supervised program repair from diagnostic feedback,” in Proc. ICML, PMLR, vol. 119, pp. 10799–10808, 2020.
[10]F. Zhu, Z. Liu, G. Yang, J. Li, and S. Cheung, “EqFix: Fixing LaTeX equation errors by examples,” in SETTA 2022, LNCS 13649, pp. 89–109.
[11]K. Wang et al., “TexOCR-Bench: Benchmarking page-image-to-LaTeX reconstruction,” in Proc. 64th ACL, Vol. 1, 2026.
[12]H. Wen, Z. Zhang, and Y. Li, “OverleafCopilot: Empowering academic writing in Overleaf with large language models,” arXiv:2403.09733, 2024.
[13]S. Hou et al., “PaperDebugger: Assisting scientific writing, review, and editing,” in Companion Proc. ACM Web Conf., 2026.
[14]J. Tan, K. Zhang, and X. Chen, “Inconsistencies in TeX-produced documents,” in Proc. ISSTA, 2024.
[15]L. Zheng et al., “Judging LLM-as-a-judge with MT-Bench and Chatbot Arena,” Adv. Neural Inf. Process. Syst., vol. 36, pp. 46595–46623, 2023.
[16]A. Panickssery, S. R. Bowman, and S. Feng, “LLM evaluators recognize and favor their own generations,” Adv. Neural Inf. Process. Syst., vol. 37, 2024.
[17]B. Hui et al., “Qwen2.5-Coder technical report,” arXiv:2409.12186, 2024.
[18]Meta AI, “Llama 3.2 model card,” 2024.
[19]E. Kassis et al., “Agent skills for reproducible research agents,” arXiv:2609.00065, 2026.
成果會先留在另一個獨立工作區,直到你審閱並套用為止。
尋找低功耗野火感測的論文。儲存一份附有已驗證 DOI 的閱讀清單。
在你套用審閱過的檔案之前,原始專案維持不變。
套用前,先預覽每個選取的檔案。
research/reading-list.md新增預覽+ # Wildfire sensing: reading list + + ## Satellite fire detection + Giglio et al. (2003). An Enhanced Contextual Fire + Detection Algorithm for MODIS. + DOI: 10.1016/S0034-4257(03)00184-6 + + Use: background on satellite detection methods. + Check separately: claims about ground-sensor energy use.
Attention
\definecolor{c0F172A}{HTML}{0F172A}\definecolor{c1E293B}{HTML}{1E293B}\definecolor{cC7C7CC}{HTML}{C7C7CC}\definecolor{cCDEDD0}{HTML}{CDEDD0}\definecolor{cCFE8F8}{HTML}{CFE8F8}\definecolor{cDAD2F0}{HTML}{DAD2F0}\definecolor{cE9E9EC}{HTML}{E9E9EC}\definecolor{cEEF2C3}{HTML}{EEF2C3}\definecolor{cF9D7D9}{HTML}{F9D7D9}\definecolor{cFDE3C7}{HTML}{FDE3C7}\definecolor{cFFFFFF}{HTML}{FFFFFF}\begin{tikzpicture}[>={Triangle[length=0.313cm,width=0.313cm]}] \node (n1_mds37) at (6.25,-21.75) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1cm] {Inputs}; \node (n2_hnw3j) at (6.25,-20.075) [draw=c1E293B, line width=0.025cm, fill=cF9D7D9, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Input Embedding}; \node (n3_x9vjf) at (4.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {}; \node (n4_aa0b6) at (6.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {+}; \node (n5_lbeum) at (2.625,-19.375) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=3.5cm, minimum height=1cm] {Positional Encoding}; \node (n6_gr85r) at (6.25,-16.325) [draw=c1E293B, line width=0.025cm, fill=cFDE3C7, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Multi-Head Attention}; \node (n7_it3d0) at (6.25,-14.575) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm}; \node (n8_0ae9p) at (6.25,-12.575) [draw=c1E293B, line width=0.025cm, fill=cCFE8F8, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Feed Forward}; \node (n9_31jhg) at (6.25,-10.825) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm}; \node (n11_3mv5b) at (1.875,-13.575) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=1.25cm, minimum height=0.75cm] {N×}; \node (n12_y6hil) at (16.25,-21.75) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1cm] {Outputs (shifted right)}; \node (n13_oukbf) at (16.25,-20.075) [draw=c1E293B, line width=0.025cm, fill=cF9D7D9, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Output Embedding}; \node (n14_e6m10) at (16.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {+}; \node (n15_te7fn) at (18.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {}; \node (n16_otz7n) at (19.875,-19.375) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=3.5cm, minimum height=1cm] {Positional Encoding}; \node (n17_nw4kz) at (16.25,-16.325) [draw=c1E293B, line width=0.025cm, fill=cFDE3C7, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Masked Multi-Head Attention}; \node (n18_feep8) at (16.25,-14.575) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm}; \node (n19_9lw0g) at (16.25,-12.575) [draw=c1E293B, line width=0.025cm, fill=cFDE3C7, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Multi-Head Attention}; \node (n20_lz6h6) at (16.25,-10.825) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm}; \node (n21_iyi8d) at (16.25,-8.825) [draw=c1E293B, line width=0.025cm, fill=cCFE8F8, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Feed Forward}; \node (n22_hapki) at (16.25,-7.075) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm}; \node (n24_qwbl3) at (19.375,-11.825) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=1.25cm, minimum height=0.75cm] {N×}; \node (n25_isnp1) at (16.25,-4.8) [draw=c1E293B, line width=0.025cm, fill=cDAD2F0, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.1cm] {Linear}; \node (n26_ggail) at (16.25,-2.8) [draw=c1E293B, line width=0.025cm, fill=cCDEDD0, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.1cm] {Softmax}; \node (n27_76g5v) at (16.25,-0.875) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.5cm, minimum height=1.25cm] {Output Probabilities}; \begin{scope}[on background layer] \node (n10_ma9el) at (6.25,-13.575) [draw=cC7C7CC, line width=0.025cm, fill=cE9E9EC, rounded corners=0.4cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=5.5cm, minimum height=7.65cm] {}; \node (n23_egiii) at (16.25,-11.7) [draw=cC7C7CC, line width=0.025cm, fill=cE9E9EC, rounded corners=0.4cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=5.5cm, minimum height=11.4cm] {}; \draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-21.25) -- (6.25,-20.75) -- (6.25,-21.15) -- (6.25,-20.65); \draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-19.5) -- (6.25,-19) -- (6.25,-19.1) -- (6.25,-18.6); \draw[->, line width=0.05cm] (n3_x9vjf.east) to[out=0, in=180] (n4_aa0b6.west); \draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-17.75) -- (6.25,-17.25) -- (6.25,-17.4) -- (6.25,-16.9); \draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-15.75) -- (6.25,-15.25) -- (6.25,-15.65) -- (6.25,-15.15); \draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-14) -- (6.25,-13.5) -- (6.25,-13.65) -- (6.25,-13.15); \draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-12) -- (6.25,-11.5) -- (6.25,-11.9) -- (6.25,-11.4); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-21.25) -- (16.25,-20.75) -- (16.25,-21.15) -- (16.25,-20.65); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-19.5) -- (16.25,-19) -- (16.25,-19.1) -- (16.25,-18.6); \draw[->, line width=0.05cm] (n15_te7fn.west) to[out=180, in=0] (n14_e6m10.east); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-17.75) -- (16.25,-17.25) -- (16.25,-17.4) -- (16.25,-16.9); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-15.75) -- (16.25,-15.25) -- (16.25,-15.65) -- (16.25,-15.15); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-14) -- (16.25,-13.5) -- (16.25,-13.65) -- (16.25,-13.15); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-12) -- (16.25,-11.5) -- (16.25,-11.9) -- (16.25,-11.4); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-10.25) -- (16.25,-9.75) -- (16.25,-9.9) -- (16.25,-9.4); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-8.25) -- (16.25,-7.75) -- (16.25,-8.15) -- (16.25,-7.65); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-6.5) -- (16.25,-6) -- (16.25,-5.925) -- (16.25,-5.85) -- (16.25,-5.35); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-4.25) -- (16.25,-3.75) -- (16.25,-3.85) -- (16.25,-3.35); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-2.25) -- (16.25,-1.75) -- (16.25,-2) -- (16.25,-1.5); \draw[->, line width=0.05cm, rounded corners=0.125cm] (8.375,-10.825) -- (8.875,-10.825) -- (11.25,-10.825) -- (11.25,-12.575) -- (13.625,-12.575) -- (14.125,-12.575); \draw[->, line width=0.05cm, rounded corners=0.125cm] (5.825,-18.175) -- (5.325,-18.175) -- (3.625,-18.175) -- (3.625,-14.575) -- (4.125,-14.575); \draw[->, line width=0.05cm, rounded corners=0.125cm] (4.125,-14.575) -- (4.1,-14.575) -- (3.625,-14.575) -- (3.625,-10.825) -- (4.125,-10.825); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.675,-18.175) -- (17.175,-18.175) -- (18.875,-18.175) -- (18.875,-14.575) -- (18.375,-14.575); \draw[->, line width=0.05cm, rounded corners=0.125cm] (18.375,-14.575) -- (18.875,-14.575) -- (18.875,-10.825) -- (18.4,-10.825) -- (18.375,-10.825); \draw[->, line width=0.05cm, rounded corners=0.125cm] (18.375,-10.825) -- (18.875,-10.825) -- (18.875,-7.075) -- (18.4,-7.075) -- (18.375,-7.075); \end{scope}\end{tikzpicture}Attention
\definecolor{c0F172A}{HTML}{0F172A}\definecolor{c1E293B}{HTML}{1E293B}\definecolor{cC7C7CC}{HTML}{C7C7CC}\definecolor{cCDEDD0}{HTML}{CDEDD0}\definecolor{cCFE8F8}{HTML}{CFE8F8}\definecolor{cDAD2F0}{HTML}{DAD2F0}\definecolor{cE9E9EC}{HTML}{E9E9EC}\definecolor{cEEF2C3}{HTML}{EEF2C3}\definecolor{cF9D7D9}{HTML}{F9D7D9}\definecolor{cFDE3C7}{HTML}{FDE3C7}\definecolor{cFFFFFF}{HTML}{FFFFFF}\begin{tikzpicture}[>={Triangle[length=0.313cm,width=0.313cm]}] \node (n1_mds37) at (6.25,-21.75) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1cm] {Inputs}; \node (n2_hnw3j) at (6.25,-20.075) [draw=c1E293B, line width=0.025cm, fill=cF9D7D9, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Input Embedding}; \node (n3_x9vjf) at (4.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {}; \node (n4_aa0b6) at (6.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {+}; \node (n5_lbeum) at (2.625,-19.375) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=3.5cm, minimum height=1cm] {Positional Encoding}; \node (n6_gr85r) at (6.25,-16.325) [draw=c1E293B, line width=0.025cm, fill=cFDE3C7, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Multi-Head Attention}; \node (n7_it3d0) at (6.25,-14.575) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm}; \node (n8_0ae9p) at (6.25,-12.575) [draw=c1E293B, line width=0.025cm, fill=cCFE8F8, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Feed Forward}; \node (n9_31jhg) at (6.25,-10.825) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm}; \node (n11_3mv5b) at (1.875,-13.575) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=1.25cm, minimum height=0.75cm] {N×}; \node (n12_y6hil) at (16.25,-21.75) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1cm] {Outputs (shifted right)}; \node (n13_oukbf) at (16.25,-20.075) [draw=c1E293B, line width=0.025cm, fill=cF9D7D9, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Output Embedding}; \node (n14_e6m10) at (16.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {+}; \node (n15_te7fn) at (18.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {}; \node (n16_otz7n) at (19.875,-19.375) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=3.5cm, minimum height=1cm] {Positional Encoding}; \node (n17_nw4kz) at (16.25,-16.325) [draw=c1E293B, line width=0.025cm, fill=cFDE3C7, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Masked Multi-Head Attention}; \node (n18_feep8) at (16.25,-14.575) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm}; \node (n19_9lw0g) at (16.25,-12.575) [draw=c1E293B, line width=0.025cm, fill=cFDE3C7, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Multi-Head Attention}; \node (n20_lz6h6) at (16.25,-10.825) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm}; \node (n21_iyi8d) at (16.25,-8.825) [draw=c1E293B, line width=0.025cm, fill=cCFE8F8, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Feed Forward}; \node (n22_hapki) at (16.25,-7.075) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm}; \node (n24_qwbl3) at (19.375,-11.825) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=1.25cm, minimum height=0.75cm] {N×}; \node (n25_isnp1) at (16.25,-4.8) [draw=c1E293B, line width=0.025cm, fill=cDAD2F0, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.1cm] {Linear}; \node (n26_ggail) at (16.25,-2.8) [draw=c1E293B, line width=0.025cm, fill=cCDEDD0, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.1cm] {Softmax}; \node (n27_76g5v) at (16.25,-0.875) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.5cm, minimum height=1.25cm] {Output Probabilities}; \begin{scope}[on background layer] \node (n10_ma9el) at (6.25,-13.575) [draw=cC7C7CC, line width=0.025cm, fill=cE9E9EC, rounded corners=0.4cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=5.5cm, minimum height=7.65cm] {}; \node (n23_egiii) at (16.25,-11.7) [draw=cC7C7CC, line width=0.025cm, fill=cE9E9EC, rounded corners=0.4cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=5.5cm, minimum height=11.4cm] {}; \draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-21.25) -- (6.25,-20.75) -- (6.25,-21.15) -- (6.25,-20.65); \draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-19.5) -- (6.25,-19) -- (6.25,-19.1) -- (6.25,-18.6); \draw[->, line width=0.05cm] (n3_x9vjf.east) to[out=0, in=180] (n4_aa0b6.west); \draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-17.75) -- (6.25,-17.25) -- (6.25,-17.4) -- (6.25,-16.9); \draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-15.75) -- (6.25,-15.25) -- (6.25,-15.65) -- (6.25,-15.15); \draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-14) -- (6.25,-13.5) -- (6.25,-13.65) -- (6.25,-13.15); \draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-12) -- (6.25,-11.5) -- (6.25,-11.9) -- (6.25,-11.4); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-21.25) -- (16.25,-20.75) -- (16.25,-21.15) -- (16.25,-20.65); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-19.5) -- (16.25,-19) -- (16.25,-19.1) -- (16.25,-18.6); \draw[->, line width=0.05cm] (n15_te7fn.west) to[out=180, in=0] (n14_e6m10.east); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-17.75) -- (16.25,-17.25) -- (16.25,-17.4) -- (16.25,-16.9); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-15.75) -- (16.25,-15.25) -- (16.25,-15.65) -- (16.25,-15.15); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-14) -- (16.25,-13.5) -- (16.25,-13.65) -- (16.25,-13.15); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-12) -- (16.25,-11.5) -- (16.25,-11.9) -- (16.25,-11.4); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-10.25) -- (16.25,-9.75) -- (16.25,-9.9) -- (16.25,-9.4); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-8.25) -- (16.25,-7.75) -- (16.25,-8.15) -- (16.25,-7.65); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-6.5) -- (16.25,-6) -- (16.25,-5.925) -- (16.25,-5.85) -- (16.25,-5.35); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-4.25) -- (16.25,-3.75) -- (16.25,-3.85) -- (16.25,-3.35); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-2.25) -- (16.25,-1.75) -- (16.25,-2) -- (16.25,-1.5); \draw[->, line width=0.05cm, rounded corners=0.125cm] (8.375,-10.825) -- (8.875,-10.825) -- (11.25,-10.825) -- (11.25,-12.575) -- (13.625,-12.575) -- (14.125,-12.575); \draw[->, line width=0.05cm, rounded corners=0.125cm] (5.825,-18.175) -- (5.325,-18.175) -- (3.625,-18.175) -- (3.625,-14.575) -- (4.125,-14.575); \draw[->, line width=0.05cm, rounded corners=0.125cm] (4.125,-14.575) -- (4.1,-14.575) -- (3.625,-14.575) -- (3.625,-10.825) -- (4.125,-10.825); \draw[->, line width=0.05cm, rounded corners=0.125cm] (16.675,-18.175) -- (17.175,-18.175) -- (18.875,-18.175) -- (18.875,-14.575) -- (18.375,-14.575); \draw[->, line width=0.05cm, rounded corners=0.125cm] (18.375,-14.575) -- (18.875,-14.575) -- (18.875,-10.825) -- (18.4,-10.825) -- (18.375,-10.825); \draw[->, line width=0.05cm, rounded corners=0.125cm] (18.375,-10.825) -- (18.875,-10.825) -- (18.875,-7.075) -- (18.4,-7.075) -- (18.375,-7.075); \end{scope}\end{tikzpicture}Attention
Attention
@article{venkateshmurthy2026etb, author = {Venkateshmurthy, Prajwal S.}, title = {Engine-Transfer-Bench: An Evidence-Based Benchmark for Document Compilation Engine Selection}, journal = {arXiv preprint}, year = 2026, eprint = {2608.18329}, }
LaTeX (latexmk) · main.tex
9/13/2026, 4:57:36 PM
7 個檔案 · 183.8 KB · ded1c2ae
LaTeX (latexmk) · main.tex
9/13/2026, 3:52:03 PM
7 個檔案 · 183.8 KB · 157c1ffb
LaTeX (latexmk) · main.tex
9/6/2026, 4:22:40 PM
7 個檔案 · 183.7 KB · 891b7ee7
篩選條件會立即套用到專案書架
Senior Software Engineer (L5) with 9+ years designing and operating large-scale distributed systems. Deep experience in backend infrastructure, performance, and reliability.
- Tech lead for a Search serving component handling 2M+ queries/second; cut p99 latency 38%.
- Designed a globally replicated feature store on Spanner backing 40+ ML models.
- Led migration of a 300-service fleet to a new RPC framework; reduced on-call pages 45%.
- Mentored six engineers and ran the team’s design-review program.
- Built a real-time aggregation pipeline processing 8B events/day.
- Cut batch-job cost 30% with sharding and incremental computation.
- Shipped ledger and reconciliation services processing $60B+/year.
- Reduced a reconciliation run from six hours to 25 minutes.
Go, Raft, gRPC — distributed rate limiter doing 4M+ decisions/sec/node.
Rust — typed query builder for Postgres with compile-time-checked SQL.
Languages: C++, Go, Rust, Python, Java, SQL
Systems: Spanner, Bigtable, Kubernetes, Kafka, gRPC / Protobuf, Redis
選擇這份手稿的起點,而每一個部分,都保留給你修改。

一個研究資料夾,包含章節、文獻來源與審閱筆記,並附上一項界定研究問題的起始任務。

接手你既有的手稿:封存檔、Word 或 Markdown 草稿,或 GitHub 儲存庫。

從為期刊論文、學位論文、報告、海報或演講準備好的版面配置開始。
Data scientist focused on trustworthy machine learning, experimentation, and decision systems used by product and research teams.
- Built evaluation systems for large language models across safety and product quality.
- Designed experiments used to guide high-impact model launches.
- Developed ranking models and reliable offline evaluation pipelines.
- Partnered with product teams to improve marketplace search quality.
- Created retention models and executive experimentation dashboards.
Open evaluation templates for production ML systems.
Python package for reproducible causal inference workflows.
Languages: Python, R, SQL, PyTorch, JAX
Systems: Spark, dbt, BigQuery, Airflow, MLflow, Kubernetes
Data scientist focused on trustworthy machine learning, experimentation, and decision systems used by product and research teams.
- Built evaluation systems for large language models across safety and product quality.
- Designed experiments used to guide high-impact model launches.
- Developed ranking models and reliable offline evaluation pipelines.
- Partnered with product teams to improve marketplace search quality.
- Created retention models and executive experimentation dashboards.
Open evaluation templates for production ML systems.
Python package for reproducible causal inference workflows.
Languages: Python, R, SQL, PyTorch, JAX
Systems: Spark, dbt, BigQuery, Airflow, MLflow, Kubernetes
Senior Software Engineer (L5) with 9+ years designing and operating large-scale distributed systems. Deep experience in backend infrastructure, performance, and reliability.
- Tech lead for a Search serving component handling 2M+ queries/second; cut p99 latency 38%.
- Designed a globally replicated feature store on Spanner backing 40+ ML models.
- Led migration of a 300-service fleet to a new RPC framework; reduced on-call pages 45%.
- Mentored six engineers and ran the team’s design-review program.
- Built a real-time aggregation pipeline processing 8B events/day.
- Cut batch-job cost 30% with sharding and incremental computation.
- Shipped ledger and reconciliation services processing $60B+/year.
- Reduced a reconciliation run from six hours to 25 minutes.
Go, Raft, gRPC — distributed rate limiter doing 4M+ decisions/sec/node.
Rust — typed query builder for Postgres with compile-time-checked SQL.
Languages: C++, Go, Rust, Python, Java, SQL
Systems: Spanner, Bigtable, Kubernetes, Kafka, gRPC / Protobuf, Redis
Product engineer bridging design systems and frontend infrastructure to build accessible, high-craft tools for creative teams.
- Led architecture for collaborative prototyping workflows used by millions.
- Created an accessible component platform shared across six product teams.
- Shipped core editor interactions and improved canvas rendering performance 42%.
- Partnered with design to establish product-wide interaction standards.
- Prototyped service experiences for health and education clients.
Open-source accessible color and typography toolkit.
Patterns for resilient collaborative interfaces.
Languages: TypeScript, React, Rust, Swift, Figma
Systems: WebGL, Canvas, design systems, accessibility, prototyping
Product engineer bridging design systems and frontend infrastructure to build accessible, high-craft tools for creative teams.
- Led architecture for collaborative prototyping workflows used by millions.
- Created an accessible component platform shared across six product teams.
- Shipped core editor interactions and improved canvas rendering performance 42%.
- Partnered with design to establish product-wide interaction standards.
- Prototyped service experiences for health and education clients.
Open-source accessible color and typography toolkit.
Patterns for resilient collaborative interfaces.
Languages: TypeScript, React, Rust, Swift, Figma
Systems: WebGL, Canvas, design systems, accessibility, prototyping
Research engineer building fast, expressive systems for scientific communication and reproducible technical publishing.
- Built incremental layout and diagnostics for a modern typesetting engine.
- Improved large-document render latency and editor feedback loops.
- Worked on text shaping, browser layout, and developer tooling.
- Published work on interactive document systems.
A small language server for technical documents.
Experiments in high-performance text layout.
Languages: Rust, C++, TypeScript, Python
Systems: Compilers, text layout, language servers, WebAssembly
\documentclass[11pt,letterpaper]{article}\usepackage[T1]{fontenc}\usepackage[margin=0.5in]{geometry}\usepackage{titlesec}\usepackage{enumitem}\usepackage{hyperref}% ATS-friendly: single column, real selectable text, no tables-for-layout,% embedded subset fonts. Linear reading order so parsers extract cleanly.\setlength{\parindent}{0pt}\pagenumbering{gobble}\hypersetup{colorlinks=true, urlcolor=black, linkcolor=black}\titleformat{\section}{\large\bfseries\uppercase}{}{0em}{}[\vspace{2pt}\titlerule]\titlespacing*{\section}{0pt}{8pt}{4pt}\setlist[itemize]{leftmargin=14pt, itemsep=1pt, topsep=2pt, parsep=0pt}% role{Title}{Company}{Location}{Dates}\newcommand{\role}[4]{% \textbf{#1} \hfill #2 \\ \textit{#3} \hfill \textit{#4}%}\begin{document}\begin{center} {\Huge \textbf{Alex Chen}}\\[3pt] \small Senior Software Engineer\\[2pt] \href{mailto:alex.chen@gmail.com}{alex.chen@gmail.com}\,$\cdot$\, (650) 555-0142\,$\cdot$\, Mountain View, CA\,$\cdot$\, \href{https://alexchen.dev}{alexchen.dev}\,$\cdot$\, \href{https://github.com/alexchen}{github.com/alexchen}\,$\cdot$\, \href{https://linkedin.com/in/alexchen}{linkedin.com/in/alexchen}\end{center}\vspace{2pt}\section*{Summary}Senior Software Engineer (L5) with 9+ years designing and operating large-scaledistributed systems. Deep experience in backend infrastructure, performance, andreliability, with a track record of shipping products used by hundreds ofmillions of users and mentoring engineers toward senior roles.\section*{Experience}\role{Senior Software Engineer (L5)}{Google}{Mountain View, CA}{Mar 2020 -- Present}\begin{itemize} \item Tech lead for a Search serving component handling 2M+ queries/second; drove a redesign that cut p99 latency 38\% and saved an estimated \$14M/year in compute. \item Designed and launched a globally-replicated feature store on Spanner backing 40+ ML models, adopted by 12 teams across Search and Ads. \item Led migration of a 300-service fleet to a new RPC framework, improving tail latency and reducing on-call pages by 45\%. \item Mentored 6 engineers (2 promoted to senior); ran the team's design-review and readability programs.\end{itemize}\vspace{3pt}\role{Software Engineer (L4)}{Google}{Mountain View, CA}{Jul 2017 -- Mar 2020}\begin{itemize} \item Built a real-time aggregation pipeline (C++, Flume) processing 8B events/day for a Search-quality dashboard used org-wide. \item Cut batch-job cost 30\% by reworking sharding and introducing incremental recomputation.\end{itemize}\vspace{3pt}\role{Software Engineer}{Stripe}{San Francisco, CA}{Aug 2015 -- Jun 2017}\begin{itemize} \item Shipped core ledger and reconciliation services for a payments platform processing \$60B+/year. \item Reduced a reconciliation run from 6 hours to 25 minutes via parallelization and a columnar store.\end{itemize}\section*{Selected Projects}\textbf{Ratel} \hfill \href{https://github.com/alexchen/ratel}{github.com/alexchen/ratel} \\\textit{Go, Raft, gRPC} --- open-source distributed rate limiter doing 4M+ decisions/sec/node; 1.5k GitHub stars.\par\vspace{4pt}\textbf{tql} \hfill \href{https://github.com/alexchen/tql}{github.com/alexchen/tql} \\\textit{Rust} --- a typed query builder for Postgres with compile-time-checked SQL.\section*{Education}\textbf{M.S. Computer Science} \hfill Stanford University \\\textit{2013 -- 2015} \hfill \textit{Focus: Distributed Systems}\par\vspace{4pt}\textbf{B.S. Computer Science} \hfill University of Illinois Urbana-Champaign \\\textit{2009 -- 2013} \hfill \textit{GPA: 3.9 / 4.0}\section*{Skills}\textbf{Languages:} C++, Go, Rust, Python, Java, SQL \\\textbf{Systems:} Spanner, Bigtable, Kubernetes, Kafka, gRPC / Protobuf, Redis \\\textbf{Focus:} Distributed systems, performance, reliability (SLOs), system design, mentoring\end{document}Senior Software Engineer (L5) with 9+ years designing and operating large-scale distributed systems. Deep experience in backend infrastructure, performance, and reliability.
- Tech lead for a Search serving component handling 2M+ queries/second; cut p99 latency 38%.
- Designed a globally replicated feature store on Spanner backing 40+ ML models.
- Led migration of a 300-service fleet to a new RPC framework; reduced on-call pages 45%.
- Mentored six engineers and ran the team’s design-review program.
- Built a real-time aggregation pipeline processing 8B events/day.
- Cut batch-job cost 30% with sharding and incremental computation.
- Shipped ledger and reconciliation services processing $60B+/year.
- Reduced a reconciliation run from six hours to 25 minutes.
Go, Raft, gRPC — distributed rate limiter doing 4M+ decisions/sec/node.
Rust — typed query builder for Postgres with compile-time-checked SQL.
Languages: C++, Go, Rust, Python, Java, SQL
Systems: Spanner, Bigtable, Kubernetes, Kafka, gRPC / Protobuf, Redis
Results
Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs, yet their normalized exact-match counts are 52, 66, and 59 just2014defects4j.
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
| System | CR | CR % | NEM | Fail |
| Identity | 0/86 | 0.0 | 0/86 | 0 |
| Rule | 34/86 | 39.5 | 28/86 | 0 |
| Qwen-7B + fb | 57/86 | 66.3 | 17/86 | 0 |
| MiniMax M3 | 75/86 | 87.2 | 50/86 | 2 |
| DeepSeek V4 | 81/86 | 94.2 | 38/86 | 2 |
| Gemini 3.5 | 82/86 | 95.3 | 26/86 | 0 |
| Claude S5 | 85/86 | 98.8 | 52/86 | 0 |
| GPT-5.6 Sol | 85/86 | 98.8 | 66/86 | 1 |
| Grok 4.5 | 85/86 | 98.8 | 59/86 | 0 |
Evaluation method
Compile Recovery requires a successful Tectonic 0.17.0 run and at least 0.80 token-level LCS similarity between text extracted from the candidate and reference PDFs. Normalized exact match sits beside it, because compilation alone cannot separate a faithful repair from a deletion.
Discussion and limitations
These results show why compilation and edit precision should be reported together, but they do not establish a universal model ranking jimenez2024swebench.
Every generated row passes an engine gate before it is retained, and duplicate broken sources are removed by SHA-256 so that no input is scored twice.
Conclusion
The contribution is an auditable task definition, an executable oracle, a fixed cohort, and a replayable candidate ledger.
- 語言分析已分析目前的專案修訂版本
- 正在編譯正在產生並驗證 PDF 輸出
- 正在算繪 PDF正在等待已驗證的編譯輸出
Single-Fault LATEX Compilation Repair
Independent Researcher
San Jose, CA, USA
Abstract—Compilation repair for LaTeX is easy to score badly. A candidate may compile after deleting or hiding content, while exact source equality rejects valid alternative repairs. We present TeXFix-Bench, a controlled benchmark for repairing complete, broken LaTeX sources under a pinned engine. The generator applies 12 deterministic single-fault operators to 13 hand-authored seed documents. It retains 627 engine-validated rows, comprising 300 unique hard-track inputs and 67 unique warning-only inputs after hash deduplication.
Index Terms—automated program repair, LaTeX, benchmark, compilation, large language models, reproducibility
LaTeX compilation failures are a practical target for automated repair. A missing delimiter or misspelled control sequence can prevent a complete document from building, and the first reported diagnostic may be distant from the underlying fault. LLM-assisted writing systems now operate inside LaTeX editors , but their publications do not provide a public, engine-pinned evaluation of compilation-failure repair.
Program repair benchmarks pair a defect with an executable oracle and a fixed harness . TeXFix-Bench studies a narrower contract: a broken source document in, a repaired full source out, under a specified engine.
TexOCR-Bench evaluates page-image-to-LaTeX reconstruction , and EqFix repairs errors in individual equations by synthesizing rules from examples . Overfitting to a weak oracle is a known hazard .
A system receives one broken source file and returns one repaired source file. The engine, its version, and the build command are fixed for every attempt.
Every generated row passes an engine gate before it is retained, and duplicate broken sources are removed by SHA-256 so that no input is scored twice .
Compile Recovery requires a successful Tectonic 0.17.0 run and at least 0.80 token-level LCS similarity between text extracted from the candidate and reference PDFs. Normalized exact match sits beside it, because compilation alone cannot separate a faithful repair from a deletion .
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
| System | CR | CR % | NEM | Fail |
| Identity | 0/86 | 0.0 | 0/86 | 0 |
| Rule | 34/86 | 39.5 | 28/86 | 0 |
| Qwen-7B + fb | 57/86 | 66.3 | 17/86 | 0 |
| MiniMax M3 | 75/86 | 87.2 | 50/86 | 2 |
| DeepSeek V4 | 81/86 | 94.2 | 38/86 | 2 |
| Gemini 3.5 | 82/86 | 95.3 | 26/86 | 0 |
| Claude S5 | 85/86 | 98.8 | 52/86 | 0 |
| GPT-5.6 Sol | 85/86 | 98.8 | 66/86 | 1 |
| Grok 4.5 | 85/86 | 98.8 | 59/86 | 0 |
Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs, yet their normalized exact-match counts are 52, 66, and 59 . Compilation and edit precision must be reported together.
The contribution is an auditable task definition, an executable oracle, a fixed cohort, and a replayable candidate ledger.
[1]R. Just, D. Jalali, and M. D. Ernst, “Defects4J: A database of existing faults to enable controlled testing studies for Java programs,” in Proc. ISSTA, 2014, pp. 437–440.
[2]C. Le Goues, N. Holtschulte, E. K. Smith, Y. Brun, P. Devanbu, S. Forrest, and W. Weimer, “The ManyBugs and IntroClass benchmarks for automated repair of C programs,” IEEE Trans. Softw. Eng., vol. 41, no. 12, pp. 1236–1256, 2015.
[3]C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and K. Narasimhan, “SWE-bench: Can language models resolve real-world GitHub issues?” in Proc. ICLR, 2024.
[4]M. Chen et al., “Evaluating large language models trained on code,” arXiv:2107.03374, 2021.
[5]E. K. Smith, E. T. Barr, C. Le Goues, and Y. Brun, “Is the cure worse than the disease? Overfitting in automated program repair,” in Proc. ESEC/FSE, 2015, pp. 532–543.
[6]R. A. DeMillo, R. J. Lipton, and F. G. Sayward, “Hints on test data selection: Help for the practicing programmer,” Computer, vol. 11, no. 4, pp. 34–41, 1978.
[7]Y. Jia and M. Harman, “An analysis and survey of the development of mutation testing,” IEEE Trans. Softw. Eng., vol. 37, no. 5, pp. 649–678, 2011.
[8]R. Gupta, S. Pal, A. Kanade, and S. Shevade, “DeepFix: Fixing common C language errors by deep learning,” in Proc. AAAI, vol. 31, no. 1, pp. 1345–1351, 2017.
[9]M. Yasunaga and P. Liang, “Graph-based, self-supervised program repair from diagnostic feedback,” in Proc. ICML, PMLR, vol. 119, pp. 10799–10808, 2020.
[10]F. Zhu, Z. Liu, G. Yang, J. Li, and S. Cheung, “EqFix: Fixing LaTeX equation errors by examples,” in SETTA 2022, LNCS 13649, pp. 89–109.
[11]K. Wang et al., “TexOCR-Bench: Benchmarking page-image-to-LaTeX reconstruction,” in Proc. 64th ACL, Vol. 1, 2026.
[12]H. Wen, Z. Zhang, and Y. Li, “OverleafCopilot: Empowering academic writing in Overleaf with large language models,” arXiv:2403.09733, 2024.
[13]S. Hou et al., “PaperDebugger: Assisting scientific writing, review, and editing,” in Companion Proc. ACM Web Conf., 2026.
[14]J. Tan, K. Zhang, and X. Chen, “Inconsistencies in TeX-produced documents,” in Proc. ISSTA, 2024.
[15]L. Zheng et al., “Judging LLM-as-a-judge with MT-Bench and Chatbot Arena,” Adv. Neural Inf. Process. Syst., vol. 36, pp. 46595–46623, 2023.
[16]A. Panickssery, S. R. Bowman, and S. Feng, “LLM evaluators recognize and favor their own generations,” Adv. Neural Inf. Process. Syst., vol. 37, 2024.
[17]B. Hui et al., “Qwen2.5-Coder technical report,” arXiv:2409.12186, 2024.
[18]Meta AI, “Llama 3.2 model card,” 2024.
[19]E. Kassis et al., “Agent skills for reproducible research agents,” arXiv:2609.00065, 2026.
本版新功能
一起寫論文,就在同一個檔案裡。
與共同作者共用專案,就能看到他們打字時游標移動,每個游標都標有名字。留言就放在相關的那一行旁邊。火車上 Wi-Fi 斷了也能繼續寫,重新連線後你的編輯就會送出。
如何架設伺服器


+2
重新編譯
具名游標
一眼就能看出誰在寫研究方法,誰在修表 1。
逐行留言
針對某個句子提問,修好之後標為已解決。
看看誰在線上
頭像會顯示誰在專案中,以及他們正在編輯哪個檔案。
架設自己的伺服器
只要一行指令,就能把 Oleafly Server 安裝在你的團隊掌控的機器上。
研究空間
一個視窗,容納整篇論文。
原始檔、插圖、參考文獻和編譯好的 PDF 都在同一個視窗裡。大綱和結構圖會跟著你開啟的檔案走,點一下標題或標籤,就能直接跳到它所在的那一行。
- 檔案總管、大綱和結構共用同一個側邊欄
- 點選標籤或引用,就能跳到它的定義處
in mammary epithelial cells
Cells read growth factors through a small number of shared kinases, yet they respond to EGF, HGF and IGF-1 with different fates. We imaged ERK activity in 2,184 MCF10A cells with a kinase translocation reporter and found that each ligand produces pulses at a characteristic frequency rather than a characteristic amplitude. Frequency alone identifies the ligand in 91 percent of cells.
1 IntroductionEpidermal growth factor, hepatocyte growth factor and insulin-like growth factor all reach the nucleus through the same RAS–RAF–MEK–ERK module, yet epithelial cells migrate, scatter or grow. How a single kinase carries that distinction has been a long-standing question. Early work in PC-12 cells tied fate to whether ERK activity was transient or sustained.
Live-cell reporters changed the picture. In single cells ERK does not rise and settle; it fires in discrete pulses, and the pulse frequency tracks the dose. Here we ask whether frequency also encodes which growth factor a cell has seen.
We make three contributions. A decoder identifies the ligand from inter-pulse intervals alone. A perturbation screen shows that the code survives mutant RAS. And pulse count, not pulse height, predicts whether a cell enters S phase.
Section 2 describes the reporter and the decoder, and Section 3 discusses what a frequency code means for drugs that target the pathway. Traces, segmentation masks and analysis code are available on request.
We stimulated MCF10A cells with saturating doses of EGF, HGF or IGF-1 and tracked ERK every two minutes (Table 1). After the first spike the responses diverged: EGF drove pulses about every 19 minutes, HGF about every 41, and IGF-1 rarely more than once an hour.
Pulse amplitude overlapped almost completely between ligands, so we trained a decoder on inter-pulse intervals alone. Given the first two hours of a single cell’s trace, it named the ligand correctly in 91 percent of held-out cells.
Mutant RAS rescales this code rather than erasing it, so the frequency channel survives oncogenic signalling.
2.3 Sustained pulsing predicts S-phase entryCells that kept pulsing through hour eight were far more likely to enter S phase. Entry tracked how many pulses a cell fired rather than how tall they were, and blocking the receptor early removed the effect.
The same cells, stimulated with a constant dose, fired fewer pulses and entered S phase less often.
Because identity sits in the timing of pulses and not in their height, one cascade can serve many ligands at once. A cell does not need a separate kinase for each growth factor; it needs a way to read how often ERK fires.
The code is also robust. Mutant RAS shifts the pulse rates but keeps the ligands apart, which suggests that a downstream reader of frequency, rather than of level, decides what the cell does next.
We expect the same logic to hold in other receptor tyrosine kinase pathways, and we have begun to test it in cells that express other reporters.
Two limits are worth stating. We worked in one epithelial cell line, and the decoder was trained on the first two hours of each trace, so longer recordings may separate the ligands even better.
We thank the imaging facility for help with the microscopes and our reviewers for pressing us on the decoder. This work was supported by the Northbridge Institute.
References[1] Regot, S., Hughey, J. J., Bajar, B. T., Carrasco, S. and Covert, M. W. High-sensitivity measurements of multiple kinase activities in live single cells. Cell 157, 1724–1734 (2014).
[2] Gillies, T. E., Pargett, M., Silva, J. M., Teragawa, C. K., McCann, C. and Albeck, J. G. Oncogenic mutant RAS signaling activity is rescaled by the ERK/MAPK pathway. Mol. Syst. Biol. 16, e9518 (2020).
[3] Albeck, J. G., Mills, G. B. and Brugge, J. S. Frequency-modulated pulses of ERK activity transmit quantitative proliferation signals. Mol. Cell 49, 249–261 (2013).
[4] Aoki, K., Kumagai, Y., Sakurai, A., Komatsu, N., Fujita, Y., Shionyu, C. and Matsuda, M. Stochastic ERK activation induced by noise and cell-to-cell propagation regulates cell density-dependent proliferation. Mol. Cell 52, 529–540 (2013).
即時評論
在句子旁邊,直接提問。
選取幾個字詞,選擇「新增評論」。輸入 @ 就能把共同作者拉進來。回覆都留在文字旁邊的同一個討論裡,問題有了答案,按「解決」就能把它收起來。
- 周圍的文字移動時,討論仍然跟著原文走
- 已解決的討論,需要時點一下就能找回來

重新編譯
建議:你的編輯會變成建議,由擁有者或編輯者接受
建議模式
從「編輯」切換到「建議」後,你的修改會以追蹤修訂的插入與刪除呈現。共同作者可以逐一接受或拒絕,助理的編輯也可以用建議的形式送來。

重新編譯
專案聊天
每個共用專案都在論文旁邊附有自己的聊天,不必離開草稿,就能向共同作者問問某張圖。
這個檔案會為本專案中的所有人還原到 2026年11月7日 上午11:20 時的狀態。它目前的文字會保留在歷史記錄中,所以你可以再回到那個版本。
共用歷史記錄
在共用專案中,可以看到誰在何時改了什麼、為重要的版本命名、比較任意兩個版本,並還原單一檔案或整個專案。在你自己的專案中,每次成功編譯後儲存的檢查點也能做到同樣的事。

Epidermal growth factor, hepatocyte growth factor and insulin-like growth factor all reach the nucleus through the same RAS–RAF–MEK–ERK module, yet epithelial cells migrate, scatter or grow. How a single kinase carries that distinction has been a long-standing question [1]. Early work in PC-12 cells tied fate to whether ERK activity was transient or sustained [2].
Live-cell reporters changed the picture. In single cells ERK does not rise and settle; it fires in discrete pulses, and the pulses differ from ligand to ligand [4, 5].
Here we ask whether the timing of those pulses carries the identity of the growth factor. We imaged ERK activity in 2,184 MCF10A cells stimulated with EGF, HGF or IGF-1 and compared the amplitude, width and spacing of every pulse. Each ligand settles into its own rhythm after the first spike and keeps it at every dose we tested, while amplitudes overlap. A decoder that sees only the gaps between pulses names the ligand in most cells.
We stimulated MCF10A cells expressing the ERK kinase translocation reporter [3] with saturating doses of EGF, HGF or IGF-1 and tracked nuclear and cytoplasmic signal every two minutes for four hours. All three ligands produced the same first spike within ten minutes (Figure 1b). After that the responses diverged: EGF drove pulses about every 19 minutes, HGF about every 41, and IGF-1 rarely more than once an hour (Table 1).
2.2 Frequency, not amplitude, identifies the ligandPulse amplitude overlapped almost completely between ligands, so we trained a decoder on the gaps between pulses alone. Given the first two hours of a single cell’s trace, it named the ligand correctly in 91 percent of held-out cells, compared with 47 percent for a decoder that saw only amplitudes.
瀏覽器中的共同作者
只要你的伺服器允許,共同作者就能在瀏覽器中開啟專案,進行編輯、評論、聊天,並閱讀最新的 PDF。他們的角色決定了可以修改什麼。
Oleafly Server
自己架設協作伺服器。
伺服器是一個單一程式,由你的實驗室或系所在自己的機器上執行,專案存放在磁碟或 S3 中。成員可以用 GitHub、你們的 OIDC 供應商或電子郵件登入,管理主控台則涵蓋誰能進入、有哪些專案、電子郵件和安全性記錄。
- 人員、存取規則、伺服器設定和安全性記錄,全在同一個主控台
- 不想自己架設?一鍵加入代管伺服器
專案擁有者將這些人邀請為訪客。訪客只會看到受邀的專案,而且不能分享這些專案。
-
A
編輯者 等待核准已邀請 核准拒絕撤回amara.okafor@riverton.edu訪客Nina Takeda邀請他們加入ERK Pulse Frequency Encodes Growth Factor Identity · 到期日:Nov 21, 2026
所有曾登入這個伺服器的人。
要讓新成員加入,請在允許名單中新增。
-
Daniel Hartdaniel@northbridge.org啟用中 成員 裝置停權移除 -
Elena Petrovaelena@northbridge.org啟用中 成員 裝置停權移除 -
Lucas Moreaulucas@northbridge.org啟用中 成員維護者 裝置停權移除 -
Nina Takedanina@northbridge.org啟用中 成員 裝置停權移除 -
啟用中 管理員 裝置Prajwal你prajwal@northbridge.org
這些設定適用於這個伺服器上的每個人。
這個伺服器上的登入、裝置變更與管理員操作。
- Prajwal → 變更伺服器設定允許透過連結分享:開啟Nov 7, 2026, 10:42 AM ·起始203.0.113.24
- Prajwal → 變更角色從成員改為維護者Nov 7, 2026, 10:41 AM ·開啟Lucas Moreau ·起始203.0.113.24
- Prajwal → 核准訪客邀請專案:ERK Pulse Frequency Encodes Growth Factor Identity ·角色:編輯者Nov 7, 2026, 10:41 AM ·開啟amara.okafor@riverton.edu ·起始203.0.113.24
- Nina Takeda → 邀請訪客專案:ERK Pulse Frequency Encodes Growth Factor Identity ·角色:編輯者Nov 7, 2026, 9:58 AM ·開啟amara.okafor@riverton.edu ·起始198.51.100.7
- Daniel Hart → 已登入透過 GitHub · 裝置:Firefox on LinuxNov 7, 2026, 9:12 AM ·起始198.51.100.31
- Sofia Marín → 已登入透過 GitHub · 裝置:Chrome on WindowsNov 7, 2026, 8:47 AM ·起始198.51.100.58
雲端同步
你寫作用的每一台電腦上,都有你的專案庫。
備份到 Dropbox、Google Drive 或任何 S3 儲存空間,每個專案都會在你自己掌控的地方留一份副本。在另一台電腦上開啟 Oleafly,專案庫就已經在那裡了。API 金鑰與 AI 對話只會留在建立它們的那台電腦上。
- 每台電腦可各自選擇要同步哪些專案
- 從雲端儲存空間刪除內容前,一定會先詢問你
-
ERK pulse frequency encodes growth factor identity尚未在 Dropbox 中剛剛已同步正在上傳第 9 個檔案,共 38 個正在上傳第 24 個檔案,共 38 個正在上傳第 38 個檔案,共 38 個2.4 MB
-
TeXFix-Bench: Engine-Grounded Evaluation of Single-Fault LaTeX Compilation Repair尚未在 Dropbox 中剛剛已同步正在上傳第 18 個檔案,共 61 個正在上傳第 42 個檔案,共 61 個正在上傳第 61 個檔案,共 61 個5.1 MB
-
Larkspur: Block-Sparse Attention for Long-Context Inference尚未在 Dropbox 中剛剛已同步正在上傳第 31 個檔案,共 120 個正在上傳第 77 個檔案,共 120 個正在上傳第 120 個檔案,共 120 個18 MB
-
Grant Proposal 2027仍在從 Lab iMac 上傳只在 Dropbox 中412 KB so far3.2 MB
LaTeX、Typst 與 Markdown
用投稿場域要求的格式寫作。
LaTeX 可用隨附的 Tectonic 或你自己安裝的 TeX 編譯,Typst 有自己隨附的編譯器,Markdown 則透過 Pandoc 處理。大綱、結構圖與即時預覽在三種格式中的操作方式都相同。
- 編譯器隨應用程式附上,不必和 TeX 安裝奮戰
- 在工具庫中轉換 LaTeX、Typst 與 Word
視覺化模式
編輯時,標題、數學式、插圖和引用都會就地呈現,表格則有網格可處理列、欄與合併儲存格。.tex 檔始終是唯一的副本。
Typst 表單
範本的參數會顯示成有標籤的欄位,填寫封面頁或履歷條目時,不必去改程式碼。
Quarto 與 Calepin
在論文裡直接執行分析。
在正文旁邊寫 R、Python 或 Julia,結果會直接放進 PDF:表格、數字與圖表都會隨資料更新。Quarto 能把 .qmd 和 .Rmd 檔建置成 PDF、網頁或投影片。Calepin 則在 Typst 文件中做同樣的事。
- 只有在你為該專案允許後,程式碼才會執行
- 範本庫中有 Quarto 與 Calepin 範本
此專案的程式碼已關閉,因此這份文件中的程式碼沒有執行。只有在你信任專案中的每個檔案時,才允許程式碼。
在此專案中允許程式碼Each ligand settles into its own pulse rate after the first spike.
EGF pulses fastest and IGF-1 slowest.
Pulse amplitude overlapped almost completely between ligands, so we trained a decoder on the gaps between pulses alone. Given two hours of a single cell's trace, it named the ligand in 91 percent of held-out cells.
隨 Oleafly 提供。快速、離線、免設定。涵蓋一般 LaTeX 與大多數常見套件。
僅適用於信任的專案。會執行本機 TeX 發行版,它可以讀取你帳戶能存取的檔案。支援完整套件集與多次編譯流程。主機指令執行仍是各專案獨立的權限。
這台電腦上沒有偵測到 TeX 發行版。
精簡版的 TeX Live,不需要管理員權限。核心下載約 250 MB。期刊範本之後可能再加入套件,總計最多約 1 GB。事先安裝好,就能在你明確選擇時使用系統 LaTeX。
如果 TeX 安裝在 Oleafly 不會尋找的位置,請在這裡選擇它的資料夾。可以選含有 latexmk 的資料夾,也可以選它上層的 TeX Live 年份資料夾,例如 texlive/2026。
隨 Oleafly 提供,無需任何設定。只有在文件首次匯入 @preview 套件時才需要連網。
一鍵安裝 TeX
不需管理員權限就能安裝 TinyTeX,也可以讓 Oleafly 使用你已安裝的 TeX,或為每個專案鎖定一個 Typst 版本,讓舊論文依然以相同方式建置。
匯出與轉換
從同一份 LaTeX 原始碼匯出 Word、含 MathML 的 HTML、Markdown、Typst 與純文字,書籍還能匯出 EPUB,Beamer 投影片還能匯出 PowerPoint。你也可以把 LaTeX 專案轉換成 Typst,並閱讀一份列出變更內容的報告。
校對
拼字和文法都在你的電腦上檢查。LaTeX 指令、數學式和引用鍵會被略過。
引用
同時搜尋 arXiv、Semantic Scholar、Crossref、PubMed 和 OpenAlex,直接從結果清單中引用。
參考文獻
引用、標籤和 bib 項目集中在同一個面板裡。輸入時,未定義和重複的鍵會被標示出來。
- albeck2013frequencyAlbeck et al. 2013 · Frequency-modulated pulses of ERK activity transmit qua…
- aoki2013stochasticAoki et al. 2013 · Stochastic ERK activation induced by noise and cell-to-…
- purvis2013encodingPurvis & Lahav 2013 · Encoding and decoding cellular information through sign…
Git、GitHub 與 Zotero
在側邊欄就能提交與推送,把專案發布到 GitHub,也能從 Zotero、EndNote 或任何 .bib 檔匯入參考文獻。
- albeck2013frequencyAlbeck et al. 2013 · Zotero · Frequency-modulated pulses of ERK activity transmit qua…
- albeck2008modelingAlbeck et al. 2008 · Zotero · Modeling a snap-action, variable-delay switch controlli…
- gillies2020oncogenicGillies et al. 2020 · Zotero · Oncogenic mutant RAS signaling activity is rescaled by…
從 Zotero 引用
寫作時輸入 @ 就能搜尋你的 Zotero 文獻庫。只有你引用的論文才會寫進 .bib,並沿用你的 Better BibTeX 鍵。
Growth Factor Identity
Growth Factor Identity
- Decoder on pulse intervals: 91% of cells
- Decoder on amplitude: 47%
- Same first spike for every ligand
Thank the Hart lab first. Then the question: how does one kinase tell EGF from IGF-1?
Point at the EGF bar. Every ligand gives the same first spike; after that the rates split.
放映你的投影片
直接從 PDF 檢視器開始放映。簡報者檢視會顯示你的備忘稿、下一張投影片和計時器。
畫出來,就有 TikZ
在畫布上放方塊與箭頭,再切換到 TikZ 原始碼繼續編輯。
/image-to-latex
把筆記、方程式或表格的圖片變成可編輯的 LaTeX。
圖片裝置端模型不需要專案
/pdf-to-latex
把 PDF 轉換成 LaTeX,並保留數學式、圖片與結構。
數學式擷取圖片匯出在本機執行
47 款免費工具
PDF 轉 LaTeX、arXiv 轉 Typst、試算表轉表格、BibTeX 檢查等等,不需要建立專案。
你的所有工作,集中一處
論文、學位論文、投影片和研究計畫申請書草稿放在同一個書架上,封面一眼就能分辨。搜尋可以用專案名稱找到專案,也可以用專案裡的某一行找到,書籤則讓本週要用的專案排在最前面。
AAAI Style Paper
XeLaTeXCC0-1.0
ACL Style Paper
XeLaTeXCC0-1.0
arXiv Preprint
XeLaTeXCC0-1.0
CVPR Style Paper
XeLaTeXCC0-1.0
ICLR Style Preprint
XeLaTeXCC0-1.0
ICML Style Preprint
XeLaTeXCC0-1.0
- 引擎
- XeLaTeX
- 授權
- CC0-1.0
- 語言
- 英文
範本包
下載會議、期刊或學位論文的範本包。存到你的電腦後,每個範本都能離線編譯。
匯入你的 Overleaf 專案
在 Oleafly 中登入 Overleaf,匯入你的專案並保持同步。.zip、Word 檔、arXiv 論文或 GitHub 儲存庫也同樣可以匯入。
預檢
投稿前檢查版面、無障礙、參考文獻,以及任何會破壞盲審的內容。
AI 助理
提出需求,看過差異,再做決定。
助理可以讀取你的專案、執行編譯、修正找到的錯誤,或草擬一張 TikZ 圖。每項編輯都以差異呈現,可以審閱也可以復原。使用代管模型或你自己的端點,或是執行 Ollama,讓一切留在你的電腦上。
- 計畫模式會先讀過專案,才開始寫任何內容
- 關閉 AI,應用程式其他部分照常運作
replace_in_fileresults.tex第 31 行results.tex第一處變更 · L31行內編輯
選取一個句子,按下 ⌘L(Windows 與 Linux 上為 Ctrl+L),說明要怎麼改。改寫結果會以差異的形式就地出現,由你接受或拒絕。
依描述生成圖形
描述你需要的圖。助理會撰寫 TikZ、編譯並檢查呈現結果,按一下就能存進你的專案。
任何模型,離線也可以
自備 OpenAI、Anthropic、Gemini、DeepSeek 等服務的金鑰,或使用任何 OpenAI 相容端點,也可以在 Ollama 或 LM Studio 中執行本機模型。
- 91% 的解碼器準確率來自訓練用的場次。請用新的重複實驗來測試。
- 就 HGF 和 IGF-1 而言,頻率與劑量互相混淆。請加入一組匹配的對照。
- 沒有任何結果顯示頻率具有因果作用。請在固定振幅下滴定 MEK 抑制劑。
審閱與研究技能
投稿前可以要求一份友善的審閱,或一份嚴厲的審閱;也可以開啟研究技能,讓助理知道你所在領域的論文通常怎麼寫。
CLI 代理程式
直接用你已經在付費的代理程式。
Claude Code、Codex CLI、Gemini CLI 與其他命令列代理程式透過 ACP 連線,直接在你的專案裡工作。它們做的修改和其他變更一樣,會交給你審閱。
- 每個代理程式都用你自己的帳號登入
- 逐一核准每項編輯,或讓長時間任務自行執行
results.tex顯示變更Claude Desktop、Claude Code、Cursor 與其他 MCP 用戶端可以讀取、編輯並編譯已開啟的專案,每一項變更都需要你核准。
XXXXXX
claude mcp add --transport http oleafly http://127.0.0.1:5323/mcp --header "Authorization: Bearer XXXXXX"
透過 MCP 使用 Oleafly
Claude Code、Codex、Cursor 或 Claude Desktop 可以透過 Oleafly 的 MCP 伺服器讀取你的專案、編譯並檢查 PDF。你可以設為唯讀,或要求修改必須經過你核准。
讓代理程式透過 Cua Driver 使用這台電腦上的應用程式和網站。代理程式只能存取你在這裡列出的應用程式和網站。
Cua Driver 說明文件
已安裝 Cua Driver 0.38.0。
位於 /Applications/CuaDriver.app/Contents/MacOS/cua-driver
為某個網站開啟「使用我已登入的瀏覽器」後,代理程式會在你自己的 Chrome 或 Edge 中操作該網站。關閉時,則使用另一個瀏覽器設定檔。
Cua Driver 正依照你的限制執行。
Computer Use
當任務需要的不只是專案資料夾時,代理程式可以透過 Cua Driver,在你允許的桌面應用程式和網站中工作。
PDF 預覽
為草稿量身打造的 PDF 檢視器。
縮放、雙頁並排、深色閱讀模式和搜尋都在工具列上。點選 PDF 中的某個字詞,就能跳到它在編輯器裡的那一行。建置失敗時,上一份正常的 PDF 會留在畫面上,讓你邊修邊看。
- 從工具列就能全螢幕放映 PDF
- 長文件可以展開大綱抽屜
in mammary epithelial cells
Cells read growth factors through a small number of shared kinases, yet they respond to EGF, HGF and IGF-1 with different fates. We imaged ERK activity in 2,184 MCF10A cells with a kinase translocation reporter and found that each ligand produces pulses at a characteristic frequency rather than a characteristic amplitude. Frequency alone identifies the ligand in 91 percent of cells.
1 IntroductionEpidermal growth factor, hepatocyte growth factor and insulin-like growth factor all reach the nucleus through the same RAS–RAF–MEK–ERK module, yet epithelial cells migrate, scatter or grow. How a single kinase carries that distinction has been a long-standing question. Early work in PC-12 cells tied fate to whether ERK activity was transient or sustained.
We stimulated MCF10A cells expressing the ERK kinase translocation reporter with saturating doses of EGF, HGF or IGF-1 and tracked nuclear and cytoplasmic signal every two minutes for four hours. All three ligands produced the same first spike within ten minutes. After that the responses diverged: EGF drove pulses about every 19 minutes, HGF about every 41, and IGF-1 rarely more than once an hour.
Live-cell reporters changed the picture. In single cells ERK does not rise and settle; it fires in discrete pulses.
Pulse amplitude overlapped almost completely between ligands, so we trained a decoder on inter-pulse intervals alone. Given the first two hours of a single cell’s trace, it named the ligand correctly in 91 percent of held-out cells, compared with 47 percent for a decoder that saw only amplitudes.
Mutant RAS rescales this code rather than erasing it, which suggests the frequency channel survives oncogenic signalling.
Cells that kept pulsing through hour eight were far more likely to enter S phase. Entry tracked how many pulses a cell fired rather than how tall they were, and blocking the receptor early removed the effect.
3 DiscussionBecause identity sits in the timing of pulses and not in their height, one cascade can serve many ligands at once.
專案裡的終端機
在論文旁邊用你慣用的 shell 執行指令碼,最多可開十個分頁。輸出中的路徑與錯誤都可以點選。
變更介面語言不會變更文件語言或校對設定。
隨心自訂
淺色與深色主題、自選的強調色與字型、11 款應用程式圖示,以及 22 種介面語言。
oleaflyc
應用程式能做的一切,在終端機裡也能做。
oleaflyc 使用與應用程式相同的引擎和設定,來建置、檢查及編輯 Oleafly 專案。每個指令都能以 JSON 回傳結果,所以指令碼、CI 工作和寫程式的代理程式都能直接呼叫。
oleaflyc build --watch建置與監看
以與應用程式完全相同的方式編譯 LaTeX、Typst 和 Markdown,或監看一個資料夾,每次儲存就重新建置。
oleaflyc check --jsonCI 裡的預檢
在 GitHub Action 中執行預檢和 lint 檢查,論文尚未準備好投稿時就讓工作失敗。
oleaflyc agent run "Make it compile"無頭代理程式
從命令列把任務交給助理。它使用你自己的服務供應商和金鑰,在你套用變更之前,不會有任何內容寫進專案。
oleaflyc ask "Which sections cite preprints?"針對專案提問
不必開啟論文,也不會動到任何檔案,就能得到關於論文的答案。
oleaflyc daemon status結束後繼續運作
關閉 Oleafly 時,研究任務會移到一個小型背景助手繼續執行,再次開啟時又回到應用程式裡。
oleaflyc cite 10.1038/nature14539從命令列處理引用
搜尋文獻,用 DOI 把一篇論文加進 refs.bib,並在審稿人發現之前找出失效的引用鍵。
oleaflyc mcp給代理程式用的 MCP 伺服器
Claude Code、Codex、Cursor 和 Gemini 透過它處理你的專案,使用的工具與助理相同。
oleaflyc remote sync你的協作伺服器
登入、同步共用專案、執行 Oleafly Server,全都能在命令列完成。
oleaflyc import overleaf直接取得 Overleaf 專案
登入一次 Overleaf,就能把你的任何 Overleaf 專案拉取成本機資料夾,並在命令列中保持同步。
oleaflyc convert main.tex --to docx匯出與轉換
把論文轉成 Word、HTML 或 Markdown,或在 LaTeX 和 Typst 之間轉換,全程不必開啟應用程式。
oleaflyc checkpoint restore v12從命令列管理檢查點
列出 Oleafly 在每次成功建置後儲存的版本,一個指令就能還原其中任何一個。
ssh · slurm · cloud在更強大的機器上跑實驗
把分析與訓練任務透過 SSH 送到伺服器、Slurm 叢集或雲端主機,再把結果拉回論文裡。
強大的研究工作台
從第一筆引用到最終 PDF。
草擬、編譯、校對、搜尋、引用、審閱、發表,不必再拼湊多個工具。Oleafly 把原始碼、預覽、參考文獻、AI 與 Git 歷史,全部收進一個由你掌控的工作區。
匯入既有內容
將許多基於文字的 PDF 重新建構為本地可編輯的 LaTeX,透過託管 Pandoc 轉換 DOCX,或讓視覺模型轉錄頁面的照片。之後可選AI細化。
匯出到目標格式
透過情境選單匯出 PDF、DOCX、HTML、Markdown 等格式。也可以將整個專案下載為原始碼 ZIP。
讓它成為你的
Vim 模式、淺色與深色主題、強調色、七種版面配置預設,以及可編輯的鍵盤快速鍵。編輯器就該用得順手。
用程式碼或視覺方式編寫
將任何 LaTeX 或 Markdown 文件切換到視覺化編輯器:標題、清單、粗體、連結都能直接編輯,兩種模式共用一致的復原紀錄。不支援的指令會以原始區塊保留顯示,而不會被默默捨棄,因此切回原始碼的往返過程不會破壞內容。
SyncTeX,精確到字詞
按住 ⌘ 點選 PDF 中的某個單字,然後定位到原始碼中的該單字。使用 ⌘⇧J 跳回。
程式碼智慧
轉到定義,尋找引用,並在每個檔案中重新命名標籤、引用鍵或巨集。
斜線指令
輸入 / 以獲得 Notion 風格的插入選單:/figure、/table、/section、/cite、/math。
title = {Raft-based KV stores}, …
DOI 引用
貼上 DOI、arXiv ID 或 URL。Oleafly 會取得 BibTeX、去除重複項目,並插入 \cite。
匯入整個文獻庫
批次匯入 BibTeX、RIS、EndNote XML 與 Zotero RDF。在任何條目寫入 .bib 之前,所有內容都會先與你的專案比對並去除重複。
命令面板
⌘K 模糊搜尋應用程式中的每個操作:專案、檔案、設定等等。
不限模型的 AI
連接你偏好的模型供應商、在本機執行 Ollama,或使用以自有帳號運作的已安裝 CLI 代理程式。依手邊的工作設定核准模式。不用 AI,編輯器也照樣能用。
研究,隨取隨用
該代理程式會搜尋 alphaXiv 和 OpenAlex,提取論文內容,並在引用進入您的參考書目之前根據 Crossref 驗證引用。
內建校對
透過 Hunspell 與 Harper 在本機校對拼字與文法。Oleafly 會略過 LaTeX 指令與數學式,讓檢查專注於你的內文。
給研究一個專屬工作區
撰寫任務簡述、選擇代理程式,它在隔離副本中工作時,你可以繼續撰寫。追蹤它的活動、預覽變更的檔案,並套用你想要的結果。
從一頁到六百頁
無論是一頁的履歷還是整本書篇幅的學位論文,編輯器與虛擬化 PDF 檢視器都能保持流暢。
用於真正閱讀的 PDF 檢視器
將預覽分離到第二台顯示器、閱讀兩頁跨頁、在深夜反轉顏色或全螢幕演示。
圖表編輯器
描述一張圖表,AI 就會撰寫 TikZ 或 CeTZ、自行編譯該圖,並檢視算繪結果來修正重疊。也可以在真正的畫布上自己畫:LaTeX 用 TikZ、Typst 用 fletcher、Markdown 用 Mermaid 流程圖,程式碼與圖面會雙向保持同步。完全離線即可匯出透明背景的高解析度 PNG。
三個引擎,一個工作區
將 LaTeX、Typst 與 Markdown 專案放在同一個專案庫中。為每個專案選擇編譯器,並使用相同的預覽、參考文獻、版本管理與 AI 工具。
LaTeX 編輯器
以 LaTeX、Typst 或 Markdown 撰寫,搭配即時 PDF 預覽與字詞級 SyncTeX。編譯器隨附在內,無需設定 TeX,也不必排隊等候編譯。
AI 助理
請助理編輯原始碼、編譯專案、檢查 PDF。連接模型供應商、Ollama,或已安裝的 CLI 代理程式;較費時的工作,就交給專屬的研究任務,你可以繼續寫作。
參考文獻管理工具
匯入 BibTeX、RIS、EndNote 或 Zotero,自動去除重複項目。貼上 DOI 或 arXiv ID,即可建立一筆經 Crossref 驗證的參考文獻。
履歷製作工具
從針對 ATS 設計的履歷範本開始,檢查擷取出來的文字,並為每個申請分叉一份專屬副本,先前的版本也不會遺失。
版本控制
編譯成功後,自動為變更的原始碼保留檢查點。用 Git 主動提交、比較修訂版本,並從同一個工作區推送到 GitHub。
PDF 工具箱
閱讀長篇 PDF、把多種文字型 PDF 重建為 LaTeX,並匯出 PDF、DOCX、HTML 或投稿用的原始碼封存檔。
研究工作區
一項研究任務,從起點到終點。
把一項明確的任務交給代理程式,閱讀它建議的編輯,準備好再編譯。工作成果會留在你的專案裡。
$ theta_(t+1) = theta_t - eta nabla_theta cal(L) $- 01建立研究專案先為你的手稿、文獻來源與研究任務,準備一個專屬位置。
- 02交給代理程式一項任務選擇它需要的檔案,並說明你想修改什麼。
- 03審閱建議的變更閱讀差異內容,判斷哪些編輯該留在你的手稿裡。
- 04編譯並保留成果檢查 PDF,之後隨時回來接手,任務仍留在你的專案裡。
展開新的工作
選擇這份手稿的起點,而每一個部分,都保留給你修改。

研究專案
一個研究資料夾,包含章節、文獻來源與審閱筆記,並附上一項界定研究問題的起始任務。

匯入專案
接手你既有的手稿:封存檔、Word 或 Markdown 草稿,或 GitHub 儲存庫。

使用範本
從為期刊論文、學位論文、報告、海報或演講準備好的版面配置開始。
新研究任務
成果會先留在另一個獨立工作區,直到你審閱並套用為止。
main.tex…\section{方法}我們排除了缺少主要結果的回應。 \end{document}睡眠與記憶
方法
我們排除了缺少主要結果的回應。
研究循環
研究、寫作、驗證、發布。
從文獻搜尋到投稿,全程不失去脈絡。Oleafly 將你的文獻來源、參考文獻、圖表、編譯器輸出與歷史記錄,集中在一個可檢視的工作流程中。
$ bold(tau) = bold(J)^T bold(F) $- doi:10.1145/3576915@article{gatto24} ✓1
研究
搜尋開放的研究資源,將 DOI 與 arXiv ID 轉換為 BibTeX,並在引用寫入參考文獻之前完成驗證。
- \section{Results}2
寫
以 LaTeX、Typst 或 Markdown 撰寫,搭配範本、全專案程式碼智慧,以及具備核准控制的選用 AI 助理。
- compiled · 0 errors ✓3
核實
在本機編譯、閱讀清楚的錯誤訊息,並在原始碼與 PDF 之間跳轉。預檢會顯示解析器與螢幕閱讀器將擷取的內容。
- PDFarXivGitHub ↑4
發布
匯出 PDF、DOCX 或 HTML,打包原始碼以供投稿,並從工作起始的同一個資料夾推送到 GitHub。
產品比較
唯一能取代其他所有工具的研究工作區。
在同一處完成撰寫、編譯、校對、文獻搜尋、引文管理、PDF 審閱、編輯自動化與論文交付。Oleafly 將整套研究工具整合至一款免費、開放原始碼的應用程式。看看下列替代方案還欠缺哪些功能。 文件.
| Oleafly | OpenAI PrismRIP · 2027年1月1日 | Overleaf | Typst Web App | Curvenote | LyX | TeXstudio | Texifier | VS Code + LaTeX | Paperpal | Writefull | 履歷製作工具 | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 擁有權與存取 | 價格 | 免費且開放原始碼。不需訂閱 Oleafly | 使用 ChatGPT 帳號即可免費使用 | 提供免費方案;付費方案可增加功能 | 提供免費方案;Pro 需額外付費 | 提供免費方案;付費方案可建立私人專案 | 免費且開放原始碼 | 免費,採 GPL 授權 | 付費;提供免費試用版 | 免費;AI 有用量限制或付費方案 | 提供免費方案;Prime 需額外付費 | 提供免費方案;Premium 需額外付費 | 視產品而定;多數採訂閱制 |
| 不需帳號 | 是 | 否 | 否 | 否 | 否 | 是 | 是 | 是 | 是 | 否 | 否 | 視產品而定 | |
| 平台 | macOS、Windows 與 Linux 桌面應用程式 | 僅限網頁版 | 網頁版,另有自行託管的 Server Pro | 網頁版,另有地端部署方案 | 網頁編輯器,另有開源 CLI | Windows、macOS 與 Linux | Windows、macOS 與 Linux | macOS 與 iOS,Windows 版即將推出 | Windows、macOS 與 Linux | 網頁版、Word、Google Docs、Overleaf | Word、Overleaf 與網頁版 | 多為網頁版 | |
| 可離線使用 | 離線也能撰寫、編譯、檢查與提交;共用編輯稍後合併 | 否,採雲端工作區 | 否,採雲端服務 | 否;網頁應用程式需要網路連線 | 否;編輯器採雲端服務 | 是 | 是 | 是 | 是 | 否 | 否 | 鮮少支援 | |
| 介面語言 | 21 種介面語言 | 未見文件說明 | 18 種 | 未見文件說明 | 未見文件說明 | 26 種,完整度不一 | 約 30 種社群翻譯 | 8 種 | 15 種 | 未見文件說明 | 未見文件說明 | 視產品而定 | |
| 檔案保留在本機磁碟 | 由你擁有的一般資料夾 | 雲端儲存 | 雲端儲存 | 雲端儲存;編譯器可在本機執行 | 雲端儲存 | 是 | 是 | 本機檔案與檔案服務供應商 | 是 | 雲端服務與編輯器整合 | 檔案保留在 Word 或 Overleaf 中 | 通常採雲端儲存 | |
| 協作與同步 | 即時協作 | 內建。即時共同編輯、具名游標、共同作者人數不限 | 不限協作者人數 | 內建;人數限制依方案而定 | 內建 | 即時編輯與留言 | 不支援即時共同編輯 | 透過 Teamtype 點對點協作 | 透過 Texifier Connect 即時協作 | 透過 Live Share | 使用 Word、Google Docs 或 Overleaf | 使用 Word 或 Overleaf | 視產品而定 |
| 即時留言 | 討論串,支援回覆、@提及與標為已解決 | 是 | 是 | 是,擁有者需 Pro 方案 | 是 | 否 | 否 | 未見文件說明 | 僅能透過擴充功能 | 僅限所嵌入的編輯器內 | 僅限所嵌入的編輯器內 | 鮮少支援 | |
| 自有伺服器 | Oleafly Server:一行指令安裝、管理主控台、SSO | 否 | 是 | 地端部署方案 | 未見文件說明 | 否 | 點對點,由一位使用者主持 | 未見文件說明 | 否。Live Share 由 Microsoft 代管 | 未見文件說明 | 未見文件說明 | 鮮少支援 | |
| 雲端同步 | 以 Dropbox 同步你的專案庫與設定 | 雲端工作區 | 雲端工作區,另提供付費 Git 與 Dropbox 同步 | 雲端工作區,Pro 方案另提供 Git 同步 | 雲端專案與串連式出版 | 使用 Git 或自選同步服務 | 使用 Git 或自選同步服務 | 透過 Texifier Connect 即時同步 | 使用 Git 或自選同步服務 | 雲端工作區 | 在 Word 或 Overleaf 中運作 | 通常採雲端儲存 | |
| 共用專案與角色 | 共用專案,具擁有者、編輯者與檢視者角色 | 共用專案,協作者人數不限 | 群組與機構方案 | 共用專案,另為組織提供地端部署 | 團隊工作區與存取控制 | 未內建團隊空間 | 未內建團隊空間 | 透過 Texifier Connect 共用專案 | GitHub 組織與 Live Share | 機構儀表板與授權管理 | 機構存取 | 視產品而定 | |
| 版本記錄 | 每次成功編譯後建立檢查點,可隨時還原 | 雲端修訂版本 | 付費方案提供完整記錄 | Pro 方案提供 Git 同步 | 內建版本記錄 | Git 與其他版本控制工具 | 手動或 SVN | 使用檔案服務供應商或 Git 工具 | 內建 Git,需自行設定 | 未見文件說明 | 使用宿主應用程式的版本記錄 | 視產品而定 | |
| Git 與 GitHub | 內建 Git 面板。發布到 GitHub,並推送與提取 | 尚未支援,已在規劃中 | 付費方案提供 Git 與 GitHub | Pro 方案提供 GitHub 與 GitLab 同步(實驗性) | GitHub 整合與 CLI | 基本功能,僅限本機 | 內建 Git 面板與 SVN | 未見文件說明 | 內建 | 未見文件說明 | 未見文件說明 | 否 | |
| 寫作與出版 | 文件引擎 | 在同一工作區使用 LaTeX、Typst 與 Markdown | 僅支援 LaTeX | 僅支援 LaTeX | 僅支援 Typst | MyST Markdown 與 Jupyter | LaTeX 與 DocBook | 僅支援 LaTeX | LaTeX 與 Markdown | 透過擴充功能 | Word、Google Docs、網頁與 Overleaf | Word 與 Overleaf LaTeX | 僅支援履歷格式 |
| TeX 設定 | 隨附 Tectonic、Typst 與 Pandoc,不需安裝 TeX | 不需安裝;在雲端編譯 | 不需安裝;在雲端編譯 | 不需安裝 TeX | 不需安裝 TeX | 需安裝 TeX 發行版 | 需安裝 TeX 發行版 | 內建排版引擎與套件管理工具 | 需安裝擴充功能與 TeX | 透過 Overleaf 使用 LaTeX | 透過 Overleaf 使用 LaTeX | 不需設定 TeX | |
| 程式碼與視覺化編輯 | 原始碼與視覺化編輯,雙向轉換不失真 | 原始碼與預覽 | 原始碼與富文字模式 | 原始碼與即時預覽 | 支援 LaTeX 數學式的視覺化編輯器 | 結構化視覺編輯器 | 僅限原始碼 | 原始碼與 PDF 預覽 | 僅限原始碼 | 視覺化寫作助理 | 行內寫作建議 | 僅限視覺化編輯 | |
| 全專案程式碼智慧 | 自動完成、定義與參照查找,以及全專案重新命名 | 編輯器與 AI 輔助 | 自動完成與參照搜尋 | 錯誤提示、自動完成與 Assists | 結構化參照與方程式 | 標籤、參照、大綱與自動完成 | 結構與參照檢查工具 | 自動完成、大綱、參照與搜尋 | LaTeX Workshop IntelliSense | 沒有 LaTeX 程式碼工具 | 以 TeXGPT 輔助 LaTeX 程式碼 | 否 | |
| 原始碼與 PDF 同步 | LaTeX 與 Typst 皆可在原始碼與 PDF 間雙向跳轉 | 即時 PDF 預覽 | 原始碼與 PDF 同步 | 即時預覽 | 不支援原始碼與 PDF 同步 | 原始碼與輸出預覽 | 接近字詞層級 | 原始碼與 PDF 同步 | 正向與反向 SyncTeX | 否 | 使用 Overleaf 預覽 | 否 | |
| PDF 閱讀模式 | 內建檢視器,另有獨立視窗、跨頁、深色與閱讀模式 | 內建預覽 | 內建預覽 | 內建預覽 | 文件預覽 | 使用 PDF 檢視器 | 整合式檢視器 | 整合式 PDF 檢視器 | 擴充功能檢視器,支援反相模式 | 與 PDF 對話 | 無 PDF 閱讀器 | 文件預覽 | |
| 文件範本 | 24 個範本包共 1,800 多個範本,也可使用自己的範本 | 未見文件說明 | 豐富的出版社範本庫 | Typst Universe 與 Pro 私人範本 | 付費方案提供專業範本 | 內建文件類別 | 內建範本與使用者範本 | 未見文件說明 | 程式碼片段與社群範本 | 未見文件說明 | 否 | 核心功能 | |
| 專案與文件匯入 | ZIP、資料夾、GitHub、arXiv、Word、HTML、Typst、Markdown、PDF 與線上 LaTeX 帳號 | 資料夾、ZIP 或拖放 | 檔案、ZIP 與付費整合服務 | 可轉換 LaTeX、Word 與 Markdown | Jupyter 內容與參考文獻匯入 | LaTeX 與其他文字格式 | 開啟本機原始碼檔案 | 本機資料夾與雲端檔案 | 開啟本機原始碼檔案 | 上傳 PDF 與文件 | Word 與 Overleaf 文件 | 通常支援 PDF 或 DOCX | |
| 匯出格式 | PDF、PDF/A、PDF/UA、DOCX、HTML、EPUB、PowerPoint、Markdown、Typst 與 LaTeX | PDF 與專案檔案 | PDF 與原始碼 ZIP | PDF、PNG 與 SVG | PDF、Word、LaTeX、Typst 與 MyST | PDF、HTML、Word、RTF、ePub 等 | PDF 與原始碼檔案 | PDF 與原始碼檔案 | 取決於本機工具 | Word 工作流程 | 具追蹤修訂的 Word 文件 | 通常支援 PDF 與 DOCX | |
| 視覺化與 AI 圖表工具 | 在畫布上繪製,產生 TikZ、Typst 或 Mermaid | 將圖片與語音轉為程式碼 | 手動編寫 TikZ 與 AI 工具 | Typst 套件與原生繪圖 | 互動式圖表與圖形 | 視覺化表格與圖片工具 | 手動編寫 TikZ,搭配編輯器輔助 | 手動編寫 TikZ | 手動編寫或使用擴充功能 | 否 | AI 表格、方程式與圖形 | 否 | |
| 內建工具 | 47 種轉換工具,另有引用與數學工具 | 圖片與語音轉 LaTeX | 無專門的工具庫 | 未見文件說明 | 未見文件說明 | 否 | 表格、圖形與快速入門精靈 | 未見文件說明 | 透過擴充功能 | 改寫、翻譯、引用、PDF 對話 | 改寫、學術化改寫、標題與摘要產生器 | ATS 檢查工具與求職信產生器 | |
| 研究與 AI | AI 助理,任選模型 | +4自備金鑰。10 家代管供應商或任何自訂端點 | 內建 OpenAI 模型 | 內建研究 AI;每日額度依方案而異 | 無 AI 助理 | 未見文件說明 | 無 | Mistral、Claude、OpenRouter、ChatGPT 或本機模型 | 無 | Copilot、自備金鑰或擴充功能 | Paperpal AI | Writefull 模型與 GPT | 內建;模型選擇視產品而定 |
| 編輯器內的 CLI 智慧代理 | +714 種代理程式可在編輯器內執行,另支援任何 ACP 代理程式 | 內建 Codex | 未見文件說明 | 未見文件說明 | 未見文件說明 | 未見文件說明 | 未見文件說明 | 未見文件說明 | Copilot、Claude 和 Codex | 未見文件說明 | 未見文件說明 | 依產品而異 | |
| 本機 AI | Ollama 或任何本機 OpenAI 相容伺服器 | 否 | 否 | 否 | 否 | 否 | Ollama、llama.cpp 與 llamafile | 否 | 自備金鑰或擴充功能 | 否 | 否 | 否 | |
| 套用前檢視 AI 編輯內容 | 每項變更都以差異呈現。四種核准模式,可逐檔復原 | 保留或復原 | 檢視 AI 建議 | 無 AI 助理 | 未見文件說明 | 未內建 AI | 未內建 AI | 未內建 AI | 檢視變更 | 檢視寫作建議 | 追蹤修訂 | 視產品而定 | |
| 由 AI 檢查算繪結果 | 編輯原始碼、編譯,再檢查算繪後的 PDF | 由你重新編譯確認 | 由你重新編譯確認 | 無 AI 助理 | 否 | 未內建 AI | 未內建 AI | 未內建 AI | 檢查建置結果,但不審查 PDF | 不審查算繪後的 PDF | 不審查算繪後的 PDF | 否 | |
| AI 技能 | 內建 36 項研究技能,還可下載更多 | 內建 Paper Review 等技能 | 內建一項論述檢查 | 無 AI 助理 | 未見文件說明 | 無 AI 助理 | 可編輯的提示詞與 AI 巨集 | 無 AI 助理 | 是 | 預設與自訂提示詞 | 未見文件說明 | 頂多支援自訂提示詞 | |
| 文獻與引文搜尋 | 同時搜尋 arXiv、Semantic Scholar、Crossref、PubMed 與 OpenAlex | 內建文獻搜尋 | 參考文獻搜尋與 AI 引文建議 | 未內建搜尋 | DOI 引文查詢 | 未內建搜尋 | 否 | 未內建搜尋 | 透過 AI 或擴充功能 | 搜尋超過 2.5 億篇文章 | Writefull Cite 可找出缺漏的引文 | 否 | |
| 研究工作區與任務 | 研究任務:隔離的工作區、代理程式活動、檔案預覽與選擇性套用 | 未見文件說明 | 未見文件說明 | 否 | 未見文件說明 | 否 | 否 | 否 | 透過 AI 擴充功能 | 否 | 否 | 否 | |
| 參考文獻庫匯入 | Zotero 應用程式與網頁文獻庫、BibTeX、RIS、EndNote 與 Zotero RDF | Zotero 同步 | 付費方案提供參考文獻整合 | Pro 方案提供 Zotero 與 Mendeley 同步 | Zotero、Mendeley 與 EndNote | BibTeX 檔案 | 可搭配 BibTeX 檔案使用 | BibTeX 檔案 | 透過擴充功能 | 引文產生器 | 不支援文獻庫匯入 | 否 | |
| 供外部 AI 代理程式使用的 MCP | 將 MCP 工具連接到助理,或將專案工具提供給外部代理程式使用 | 否 | 否 | 否 | 否 | 否 | 否 | 否 | 是 | 否 | 否 | 否 | |
| 品質與投稿 | 投稿前檢查 | 六項檢查:編譯、投稿、ATS、無障礙、參考文獻、隱私 | 提供 AI 審閱,但無完整投稿檢查套件 | 編譯檢查 | 編譯器錯誤與 Assists | SCMS 合規工具 | 編譯器記錄與選用的 ChkTeX | 錯誤與警告 | 清楚的編譯器錯誤訊息 | 透過擴充功能進行程式碼檢查 | 30 多項投稿檢查 | 語言品質審查 | 僅限履歷檢查 |
| 拼字與文法檢查 | 私密的離線拼字與文法檢查,並能理解 LaTeX 語境檢查內文 | AI 校對 | 內建拼字檢查,以及針對研究寫作設計的 AI 回饋 | 未見文件說明 | 未見文件說明 | Hunspell、Aspell 與同義詞庫 | 互動式拼字與文法檢查 | 拼字檢查 | 透過擴充功能或 AI | 學術文法與文體 | 學術語言回饋 | 基本檢查功能視產品而定 | |
| ATS 履歷檢查 | ATS 評分檢查與擷取文字預覽 | 否 | 否 | 否 | 否 | 否 | 否 | 否 | 未內建檢查 | 否 | 否 | 視產品而定;評分方式通常不透明 | |
| 無障礙預檢 | 106 項 PDF/UA 檢查,以及無障礙匯出準備 | 否 | 否 | 未見文件說明 | 結構化網頁出版 | 結構化文件;無預檢功能 | 否 | 未見文件說明 | 未內建檢查 | 否 | 否 | 視產品而定 | |
| 盲審檢查 | 標出作者姓名、致謝、PDF 中繼資料與註解 | 未見文件說明 | 未見文件說明 | 未見文件說明 | 否 | 未見文件說明 | 未見文件說明 | 未見文件說明 | 未見文件說明 | 未見文件說明 | 未見文件說明 | 否 | |
| 參照與檔案檢查 | 未定義的參照、缺少的檔案、重複的鍵、未引用的條目 | AI 錯誤修正與 Paper Review | AI 檢查 .bib 與論述 | 缺少標籤時顯示編譯器錯誤 | DOI、連結、交互參照與圖片檢查 | 標示失效的交互參照 | 即時參照檢查 | 僅有 LaTeX 錯誤清單 | ChkTeX 與 LaCheck 程式碼檢查 | 30 多項檢查,包括參考文獻與圖表 | 標出未附引用的論述(機構版) | 否 | |
| 字數統計與文件分析 | 字數,以及標題、圖、表、引用與 TODO | 未見文件說明 | 是 | 未見文件說明 | 摘要字數上限檢查 | 是 | 是 | 是 | 是,透過 TeXcount | 未見文件說明 | 未見文件說明 | 履歷分析評分 |
隱私,講清楚
預設在本機。連網由你決定。
你的專案保留在你的電腦上。Oleafly 只在你選用的功能中使用網路,並會在傳送當機報告前先讓你查看。不需要 Oleafly 帳號,也沒有遙測。 隱私.
始終在本機
關掉 Wi-Fi 照樣能用
- 專案檔案、草稿、已儲存的檢查點與 Git 歷史記錄
- 撰寫、編譯、PDF 審閱與預檢
- 離線拼字檢查、文法檢查、圖表,以及選用的 Ollama
僅在你操作時連網
只在你點選時
- 代管的 AI 只會收到你選擇傳送的上下文
- GitHub 同步與研究搜尋僅在你要求時執行
- 套件、範本、字型與應用程式更新會視需要下載
\[ v = \frac{V_{\max}[S]}{K_m + [S]} \]\[ p^2 + 2pq + q^2 = 1 \]哲學
你的研究應當比創作它的工具更長久。你的研究應當比創作它的工具更長久。
\[ v = \frac{V_{\max}[S]}{K_m + [S]} \]\[ p^2 + 2pq + q^2 = 1 \]
開源,認真打造
堅持獨立,為社群打造。
Oleafly 公開開發。可靠性是產品的一部分:從可取消的編譯、安全的檔案路徑,到 Git 復原、PDF 備援,以及涵蓋 macOS、Windows 和 Linux 的測試。
查看程式碼、回報問題、貢獻修正或為 Oleafly 按 Star,歡迎前往 GitHub.
常見問題
轉換之前,你該知道的事。
沒找到答案?提問請到 Discord 或 GitHub Discussions.
01Oleafly 是什麼?+
Oleafly 是一款免費的桌面工作區,適用於論文、學位論文、履歷與其他技術文件。以 LaTeX、Typst 或 Markdown 撰寫、預覽 PDF、管理參考文獻,並可選用 AI 助理。你的專案以一般檔案的形式,保存在你自己的電腦上。
02真的免費嗎?+
是的。Oleafly 免費且開放原始碼,桌面應用程式不額外加收訂閱費用。若連接付費的 AI 供應商,用量費用依該供應商計收;透過 Ollama 使用本機模型,則不需要付費 API。
03支援哪些 AI 模型?+
自備 10 家代管供應商中任一家的金鑰、透過 Ollama 在本機執行模型,或將 Oleafly 指向任何 OpenAI 相容端點。它也能在編輯器內執行 14 種命令列代理程式(包括 Claude Code 與 Codex),沿用你現有的工具與帳號。在助理中選擇執行環境與模型。
04需要帳號嗎?+
不需要。你可以直接安裝 Oleafly 開始寫作,不必註冊任何帳號,專案也保存在你電腦上的一般資料夾中。只有需要登入的功能才要登入:加入你的團隊架設的協作伺服器,或開啟 Dropbox 同步。AI 供應商與 Git 代管服務使用各自的登入憑證。
05可以取代哪些工具?+
在許多工作流程中,Oleafly 可取代各自獨立的寫作、校對、編譯、引用、PDF、履歷、AI 與 Git 用戶端。它持續以一般檔案與 GitHub 運作,因此你可以放心採用,不必把工作鎖進專有格式。
06可以匯入既有的論文或履歷嗎?+
可以。開啟資料夾、匯入 ZIP、從 GitHub 複製,或直接從 arXiv 取得論文。線上 LaTeX 編輯器的匯出檔也能使用,Oleafly 會替你找出主要文件。文字型 PDF 可在本機轉換為 LaTeX,Word 檔透過 Pandoc 處理,視覺模型則能轉錄掃描件或照片。
07PDF 輸出對 ATS 友善嗎?+
ATS 相容程度取決於範本與內容,因此 Oleafly 不保證分數。履歷範本採用可選取的 Unicode 文字、內嵌字體、單欄版面與線性閱讀順序;預檢會在送出 PDF 前,顯示解析器實際擷取到的內容。
08那協作與同步呢?+
多人可即時共同編輯同一個專案,畫面上會顯示每個人的具名游標,留言就放在相關的那幾行旁邊。你的團隊自行架設 Oleafly Server,每個人都在自己的電腦上以一般檔案保存專案,因此可以離線繼續寫作,重新連線後編輯內容就會同步。Dropbox 同步讓你的專案庫與設定在你自己的各台裝置間保持一致。Git 也能一起使用:發布到 GitHub,然後在 Oleafly 中推送與提取。
09可以離線寫作,或完全不用 AI 嗎?+
可以。寫作、本機編譯、PDF 審閱與校對都不需要 AI。離線之前,請先下載專案所需的套件、字體與工具。若要本機 AI,請在 Ollama 下載模型,並連上它的本機伺服器。
10我繼續寫作時,代理程式可以同時工作嗎?+
可以。開啟研究任務,給出任務簡述並選擇代理程式。它會在隔離的副本中工作,你則繼續撰寫論文;隨時查看活動進度、預覽變更的檔案,並套用你選擇的結果。
\[ E = h\nu \]