mirror of
https://github.com/hanzoai/papers.git
synced 2026-10-22 17:20:17 +00:00
zooqueenandHanzo Dev
44ec401a31
`make -k all` returned 0 over any number of broken papers, so CI was green the
whole time it existed. Four things had to be true for that:
- every recipe line ended in `|| true` and the rule printed "FAIL" instead of
exiting, so make never saw a failure;
- nonstopmode emits a PDF for almost any input, so "the PDF exists" is not
the same question as "the paper compiled" — zen-nano_whitepaper produced
one through 23 LaTeX errors;
- pdfs/ was tracked, so a checkout handed the "check every paper came out"
step 100 of the PDFs it was about to look for;
- discovery was three wildcards, so 69 of the repo's 219 papers were
compiled by nothing at all, defense/ by a second copy of the same
swallowing loop written inline in ci.yml.
The rule is now one latexmk per paper and its exit status is the gate:
-halt-on-error (no PDF from a broken paper), -bibtex (a declared bibliography
must resolve rather than being skipped when the .bib is absent), -Werror (an
undefined citation is a defect, not a log note), -cd (each paper compiles from
its own directory, so zen/ finds references.bib and defense/ finds
hanzo-defense.sty). .DELETE_ON_ERROR so a failed run leaves nothing behind,
and pdfs/ is untracked because it is output.
Run against the tree it was guarding, the honest gate fails 24 papers:
6 \begin{itemize} with its backslash-b eaten, leaving a bare `egin{itemize}`
and no \end — artist, designer-instruct, eco, nano, next, omni
3 the same list with the opener deleted outright, so five \item stood in no
environment — artist-edit, designer-thinking, scribe
4 \and in a cover page's raw \@author: it expands to \end{tabular} and closed
a tabular nothing had opened, and \thanks left hyperref pointing at a
footnote anchor that was never created; plus five stray \end{table} at the
end of those documents — director, foley, musician, video
9 \color{gray} under \usepackage{color}, which defines eight names and not
that one — xcolor is the superset the working papers already load
6 \bibliography{references} naming a database that was never written, so
every citation rendered [?] — zen/references.bib now holds all 27 works
9 \bibliographystyle+\bibliography in papers with no \cite at all — dropped
3 characters pdflatex has no glyph for: CO₂ -> CO\textsubscript{2},
↔ -> $\leftrightarrow$, Persian letters -> their code points, the
SentencePiece marker -> \textvisiblespace
1 \IF{...} \COMMENT{...}: algorithmic's \IF opens a list and the comment
landed in it before any \item; the comment slot is \IF[...]{...}
1 \ref{eq:anchor_update} to an equation the paper never writes
All 219 papers now compile from a clean tree: `make -k all` exits 0.
Co-authored-by: Hanzo Dev <[email protected]>
196 lines
9.2 KiB
BibTeX
196 lines
9.2 KiB
BibTeX
% Works cited by the zen papers. Every \cite key in zen/*.tex resolves here;
|
|
% the papers named a database that had never been written, so bibtex produced
|
|
% nothing and every citation rendered as [?].
|
|
|
|
@article{allal2024smollm,
|
|
title = {{SmolLM2}: When Smol Goes Big --- Data-Centric Training of a Small Language Model},
|
|
author = {Allal, Loubna Ben and Lozhkov, Anton and Bakouch, Elie and Blazquez, Gabriel Mart{\'i}n and Penedo, Guilherme and Tunstall, Lewis and Marafioti, Andr{\'e}s and Kydl{\'i}{\v{c}}ek, Hynek and Lajar{\'i}n, Agust{\'i}n Piqueres and Srivastav, Vaibhav and others},
|
|
journal = {arXiv preprint arXiv:2502.02737},
|
|
year = {2024}
|
|
}
|
|
|
|
@article{artetxe2021efficient,
|
|
title = {Efficient Large Scale Language Modeling with Mixtures of Experts},
|
|
author = {Artetxe, Mikel and Bhosale, Shruti and Goyal, Naman and Mihaylov, Todor and Ott, Myle and Shleifer, Sam and Lin, Xi Victoria and Du, Jingfei and Iyer, Srinivasan and Pasunuru, Ramakanth and others},
|
|
journal = {arXiv preprint arXiv:2112.10684},
|
|
year = {2021}
|
|
}
|
|
|
|
@article{beltagy2020longformer,
|
|
title = {Longformer: The Long-Document Transformer},
|
|
author = {Beltagy, Iz and Peters, Matthew E. and Cohan, Arman},
|
|
journal = {arXiv preprint arXiv:2004.05150},
|
|
year = {2020}
|
|
}
|
|
|
|
@article{fedus2022switch,
|
|
title = {Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity},
|
|
author = {Fedus, William and Zoph, Barret and Shazeer, Noam},
|
|
journal = {Journal of Machine Learning Research},
|
|
volume = {23},
|
|
number = {120},
|
|
pages = {1--39},
|
|
year = {2022}
|
|
}
|
|
|
|
@article{glazer2024frontiermath,
|
|
title = {{FrontierMath}: A Benchmark for Evaluating Advanced Mathematical Reasoning in {AI}},
|
|
author = {Glazer, Elliot and Erdil, Ege and Besiroglu, Tamay and Chicharro, Diego and Chen, Evan and Gunning, Alex and Olsson, Caroline Falkman and Denain, Jean-Stanislas and Ho, Anson and Santos, Emily de Oliveira and others},
|
|
journal = {arXiv preprint arXiv:2411.04872},
|
|
year = {2024}
|
|
}
|
|
|
|
@article{gunasekar2023textbooks,
|
|
title = {Textbooks Are All You Need},
|
|
author = {Gunasekar, Suriya and Zhang, Yi and Aneja, Jyoti and Mendes, Caio C{\'e}sar Teodoro and Del Giorno, Allie and Gopi, Sivakanth and Javaheripi, Mojan and Kauffmann, Piero and de Rosa, Gustavo and Saarikivi, Olli and others},
|
|
journal = {arXiv preprint arXiv:2306.11644},
|
|
year = {2023}
|
|
}
|
|
|
|
@article{hinton2015distilling,
|
|
title = {Distilling the Knowledge in a Neural Network},
|
|
author = {Hinton, Geoffrey and Vinyals, Oriol and Dean, Jeff},
|
|
journal = {arXiv preprint arXiv:1503.02531},
|
|
year = {2015}
|
|
}
|
|
|
|
@article{hoffmann2022chinchilla,
|
|
title = {Training Compute-Optimal Large Language Models},
|
|
author = {Hoffmann, Jordan and Borgeaud, Sebastian and Mensch, Arthur and Buchatskaya, Elena and Cai, Trevor and Rutherford, Eliza and de Las Casas, Diego and Hendricks, Lisa Anne and Welbl, Johannes and Clark, Aidan and others},
|
|
journal = {arXiv preprint arXiv:2203.15556},
|
|
year = {2022}
|
|
}
|
|
|
|
@inproceedings{jimenez2024swebench,
|
|
title = {{SWE-bench}: Can Language Models Resolve Real-World {GitHub} Issues?},
|
|
author = {Jimenez, Carlos E. and Yang, John and Wettig, Alexander and Yao, Shunyu and Pei, Kexin and Press, Ofir and Narasimhan, Karthik},
|
|
booktitle = {International Conference on Learning Representations (ICLR)},
|
|
year = {2024}
|
|
}
|
|
|
|
@inproceedings{lepikhin2021gshard,
|
|
title = {{GShard}: Scaling Giant Models with Conditional Computation and Automatic Sharding},
|
|
author = {Lepikhin, Dmitry and Lee, HyoukJoong and Xu, Yuanzhong and Chen, Dehao and Firat, Orhan and Huang, Yanping and Krikun, Maxim and Shazeer, Noam and Chen, Zhifeng},
|
|
booktitle = {International Conference on Learning Representations (ICLR)},
|
|
year = {2021}
|
|
}
|
|
|
|
@article{lightman2023let,
|
|
title = {Let's Verify Step by Step},
|
|
author = {Lightman, Hunter and Kosaraju, Vineet and Burda, Yura and Edwards, Harri and Baker, Bowen and Lee, Teddy and Leike, Jan and Schulman, John and Sutskever, Ilya and Cobbe, Karl},
|
|
journal = {arXiv preprint arXiv:2305.20050},
|
|
year = {2023}
|
|
}
|
|
|
|
@article{liu2023ring,
|
|
title = {Ring Attention with Blockwise Transformers for Near-Infinite Context},
|
|
author = {Liu, Hao and Zaharia, Matei and Abbeel, Pieter},
|
|
journal = {arXiv preprint arXiv:2310.01889},
|
|
year = {2023}
|
|
}
|
|
|
|
@article{nye2021show,
|
|
title = {Show Your Work: Scratchpads for Intermediate Computation with Language Models},
|
|
author = {Nye, Maxwell and Andreassen, Anders Johan and Gur-Ari, Guy and Michalewski, Henryk and Austin, Jacob and Bieber, David and Dohan, David and Lewkowycz, Aitor and Bosma, Maarten and Luan, David and others},
|
|
journal = {arXiv preprint arXiv:2112.00114},
|
|
year = {2021}
|
|
}
|
|
|
|
@article{patil2023gorilla,
|
|
title = {Gorilla: Large Language Model Connected with Massive {APIs}},
|
|
author = {Patil, Shishir G. and Zhang, Tianjun and Wang, Xin and Gonzalez, Joseph E.},
|
|
journal = {arXiv preprint arXiv:2305.15334},
|
|
year = {2023}
|
|
}
|
|
|
|
@article{polu2022formal,
|
|
title = {Formal Mathematics Statement Curriculum Learning},
|
|
author = {Polu, Stanislas and Han, Jesse Michael and Zheng, Kunhao and Baksys, Mantas and Babuschkin, Igor and Sutskever, Ilya},
|
|
journal = {arXiv preprint arXiv:2202.01344},
|
|
year = {2022}
|
|
}
|
|
|
|
@inproceedings{romero2014fitnets,
|
|
title = {{FitNets}: Hints for Thin Deep Nets},
|
|
author = {Romero, Adriana and Ballas, Nicolas and Kahou, Samira Ebrahimi and Chassang, Antoine and Gatta, Carlo and Bengio, Yoshua},
|
|
booktitle = {International Conference on Learning Representations (ICLR)},
|
|
year = {2015}
|
|
}
|
|
|
|
@inproceedings{schick2023toolformer,
|
|
title = {Toolformer: Language Models Can Teach Themselves to Use Tools},
|
|
author = {Schick, Timo and Dwivedi-Yu, Jane and Dess{\`i}, Roberto and Raileanu, Roberta and Lomeli, Maria and Zettlemoyer, Luke and Cancedda, Nicola and Scialom, Thomas},
|
|
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
|
|
year = {2023}
|
|
}
|
|
|
|
@article{shao2024grpo,
|
|
title = {{DeepSeekMath}: Pushing the Limits of Mathematical Reasoning in Open Language Models},
|
|
author = {Shao, Zhihong and Wang, Peiyi and Zhu, Qihao and Xu, Runxin and Song, Junxiao and Bi, Xiao and Zhang, Haowei and Zhang, Mingchuan and Li, Y. K. and Wu, Y. and Guo, Daya},
|
|
journal = {arXiv preprint arXiv:2402.03300},
|
|
year = {2024}
|
|
}
|
|
|
|
@inproceedings{shazeer2017outrageously,
|
|
title = {Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer},
|
|
author = {Shazeer, Noam and Mirhoseini, Azalia and Maziarz, Krzysztof and Davis, Andy and Le, Quoc and Hinton, Geoffrey and Dean, Jeff},
|
|
booktitle = {International Conference on Learning Representations (ICLR)},
|
|
year = {2017}
|
|
}
|
|
|
|
@article{singhal2023long,
|
|
title = {A Long Way to Go: Investigating Length Correlations in {RLHF}},
|
|
author = {Singhal, Prasann and Goyal, Tanya and Xu, Jiacheng and Durrett, Greg},
|
|
journal = {arXiv preprint arXiv:2310.03716},
|
|
year = {2023}
|
|
}
|
|
|
|
@article{snell2024scaling,
|
|
title = {Scaling {LLM} Test-Time Compute Optimally Can Be More Effective Than Scaling Model Parameters},
|
|
author = {Snell, Charlie and Lee, Jaehoon and Xu, Kelvin and Kumar, Aviral},
|
|
journal = {arXiv preprint arXiv:2408.03314},
|
|
year = {2024}
|
|
}
|
|
|
|
@inproceedings{wang2022selfconsistency,
|
|
title = {Self-Consistency Improves Chain of Thought Reasoning in Language Models},
|
|
author = {Wang, Xuezhi and Wei, Jason and Schuurmans, Dale and Le, Quoc and Chi, Ed and Narang, Sharan and Chowdhery, Aakanksha and Zhou, Denny},
|
|
booktitle = {International Conference on Learning Representations (ICLR)},
|
|
year = {2023}
|
|
}
|
|
|
|
@inproceedings{wang2024executable,
|
|
title = {Executable Code Actions Elicit Better {LLM} Agents},
|
|
author = {Wang, Xingyao and Chen, Yangyi and Yuan, Lifan and Zhang, Yizhe and Li, Yunzhu and Peng, Hao and Ji, Heng},
|
|
booktitle = {International Conference on Machine Learning (ICML)},
|
|
year = {2024}
|
|
}
|
|
|
|
@inproceedings{wei2022chain,
|
|
title = {Chain-of-Thought Prompting Elicits Reasoning in Large Language Models},
|
|
author = {Wei, Jason and Wang, Xuezhi and Schuurmans, Dale and Bosma, Maarten and Ichter, Brian and Xia, Fei and Chi, Ed and Le, Quoc and Zhou, Denny},
|
|
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
|
|
year = {2022}
|
|
}
|
|
|
|
@inproceedings{yao2023react,
|
|
title = {{ReAct}: Synergizing Reasoning and Acting in Language Models},
|
|
author = {Yao, Shunyu and Zhao, Jeffrey and Yu, Dian and Du, Nan and Shafran, Izhak and Narasimhan, Karthik and Cao, Yuan},
|
|
booktitle = {International Conference on Learning Representations (ICLR)},
|
|
year = {2023}
|
|
}
|
|
|
|
@inproceedings{yue2024mmmu,
|
|
title = {{MMMU}: A Massive Multi-Discipline Multimodal Understanding and Reasoning Benchmark for Expert {AGI}},
|
|
author = {Yue, Xiang and Ni, Yuansheng and Zhang, Kai and Zheng, Tianyu and Liu, Ruoqi and Zhang, Ge and Stevens, Samuel and Jiang, Dongfu and Ren, Weiming and Sun, Yuxuan and others},
|
|
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
|
|
year = {2024}
|
|
}
|
|
|
|
@article{zhang2024tinyllama,
|
|
title = {{TinyLlama}: An Open-Source Small Language Model},
|
|
author = {Zhang, Peiyuan and Zeng, Guangtao and Wang, Tianduo and Lu, Wei},
|
|
journal = {arXiv preprint arXiv:2401.02385},
|
|
year = {2024}
|
|
}
|