OP
Ofir Press
cs.CLcs.AIcs.SEcs.LGcond-mat.othercs.CVcs.HChep-thquant-ph
On Valency
published · living versionsW_472urbcs·v1 · currentpublished
FrontierCS 2: A Benchmark for Computer Science R&D
with Qiuyang Mang, Wenhao Chai, Runyuan He, Dongruixuan Li +56
1 version
Preprints & journals
24 papers in the corpus · 2016–2026FrontierCS 2: A Benchmark for Computer Science R&D2610.29932v1 · Qiuyang Mang, Wenhao Chai, Runyuan He et al.2026 · 0 citationsarXivon Valency
ProgramBench: Can Language Models Rebuild Programs From Scratch?2605.03546v1 · John Yang, Kilian Lieret, Jeffrey Ma et al.2026 · 0 citationsarXiv
CodeClash: Benchmarking Goal-Oriented Software Engineering2511.00839v2 · John Yang, Kilian Lieret, Joyce Yang et al.2025 · 0 citationsarXiv
Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark2509.26574v4 · Minhui Zhu, Minyang Tian, Xiaocheng Yang et al.2025 · 0 citationsarXiv
AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?2507.15887v4 · Ori Press, Brandon Amos, Haoyu Zhao et al.2025 · 0 citationsarXiv
VideoGameBench: Can Vision-Language Models complete popular video games?2505.18134v3 · Alex L. Zhang, Thomas L. Griffiths, Karthik R. Narasimhan et al.2025 · 0 citationsarXiv
SWE-smith: Scaling Data for Software Engineering Agents2504.21798v2 · John Yang, Kilian Lieret, Carlos E. Jimenez et al.2025 · 6 citationsarXiv
SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?2410.03859v1 · John Yang, Carlos E. Jimenez, Alex L. Zhang et al.2024 · 3 citationsarXiv
EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities2409.16165v3 · Talor Abramovich, Meet Udeshi, Minghao Shao et al.2024 · 1 citationarXiv
AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?2407.15711v2 · Ori Yoran, Samuel Joseph Amouyal, Chaitanya Malaviya et al.2024 · 9 citationsarXiv
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering2405.15793v3 · John Yang, Carlos E. Jimenez, Alexander Wettig et al.2024 · 260 citationsarXiv
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?2310.06770v3 · Carlos E. Jimenez, John Yang, Alexander Wettig et al.2023 · 69 citationsarXiv
How Language Model Hallucinations Can Snowball2305.13534v1 · Muru Zhang, Ofir Press, William Merrill et al.2023 · 77 citationsarXiv
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model2211.05100v4 · BigScience Workshop: Teven Le Scao, Angela Fan, Christopher Akiki et al.2022 · 802 citationsarXiv
What Language Model to Train if You Have One Million GPU Hours?2210.15424v2 · Teven Le Scao, Thomas Wang, Daniel Hesslow et al.2022 · 39 citationsarXiv
Measuring and Narrowing the Compositionality Gap in Language Models2210.03350v3 · Ofir Press, Muru Zhang, Sewon Min et al.2022 · 293 citationsarXiv
Transformer Language Models without Positional Encodings Still Learn Positional Information2203.16634v2 · Adi Haviv, Ori Ram, Ofir Press et al.2022 · 61 citationsarXiv
Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation2108.12409v2 · Ofir Press, Noah A. Smith, Mike Lewis2021 · 161 citationsarXiv
Shortformer: Better Language Modeling using Shorter Inputs2012.15832v2 · Ofir Press, Noah A. Smith, Mike Lewis2020 · 53 citationsarXiv
Improving Transformer Models by Reordering their Sublayers1911.03864v2 · Ofir Press, Noah A. Smith, Omer Levy2019 · 64 citationsarXiv
Partially Shuffling the Training Data to Improve Language Models1903.04167v2 · Ofir Press2019 · 4 citationsarXiv
You May Not Need Attention1810.13409v1 · Ofir Press, Noah A. Smith2018 · 21 citationsarXiv
Language Generation with Recurrent Generative Adversarial Networks without Pre-training1706.01399v3 · Ofir Press, Amir Bar, Ben Bogin et al.2017 · 84 citationsarXiv
Using the Output Embedding to Improve Language Models1608.05859v3 · Ofir Press, Lior Wolf2016 · 615 citationsarXiv
Career total: 26 works. 24 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.