Peiyang Song

20 papers A* 2Journal 14Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Large Language Model Reasoning Failures.
CoRR
Peiyang Song, Pengrui Han, Noah Goodman
2026 J jnl
Large Language Model Reasoning Failures.
Trans. Mach. Learn. Res.
Peiyang Song, Pengrui Han, Noah Goodman
2026 J jnl
Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs.
CoRR
Pengrui Han, Xueqiang Xu, Keyang Xuan, Peiyang Song, Siru Ouyang, Runchu Tian, Yuqing Jiang, Cheng Qian, Pengcheng Jiang, Jiashuo Sun, Junxia Cui, Ming Zhong, Ge Liu, Jiawei Han, Jiaxuan You
2025 J jnl
Adaptation of Agentic AI.
CoRR
Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi, Zifeng Wang, Luxi He, Yichen Wu, Ming Zhong, Peiyang Song, Qizheng Zhang, Heng Wang, Xueqiang Xu, Hanwen Xu, Pengrui Han, Dylan Zhang, Jiashuo Sun, Chaoqi Yang, Kun Qian, Tian Wang, Changran Hu, Manling Li, Quanzheng Li, Hao Peng, Sheng Wang, Jingbo Shang, Chao Zhang, Jiaxuan You, Liyuan Liu, Pan Lu, Yu Zhang, Heng Ji, Yejin Choi, Dawn Song, Jimeng Sun, Jiawei Han
2025 J jnl
Delay-Space Arithmetic and Architecture.
IEEE Micro
Rhys Gretsch, Peiyang Song, Advait Madhavan, Jeremy Lau, Timothy Sherwood
2025 J jnl
How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns.
CoRR
Haoyue Bai, Yiyou Sun, Wenjie Hu, Shi Qiu, Maggie Ziyu Huan, Peiyang Song, Robert Nowak, Dawn Song
2025 — conf
Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean.
NeuS
Peiyang Song, Kaiyu Yang, Anima Anandkumar
2025 A* conf
LeanAgent: Lifelong Learning for Formal Theorem Proving.
ICLR
Adarsh Kumarappan, Mo Tiwari, Peiyang Song, Robert Joseph George, Chaowei Xiao, Anima Anandkumar
2025 J jnl
LeanProgress: Guiding Search for Neural Theorem Proving via Proof Progress Prediction.
CoRR
Suozhi Huang, Peiyang Song, Robert Joseph George, Anima Anandkumar
2025 J jnl
LeanProgress: Guiding Search for Neural Theorem Proving via Proof Progress Prediction.
Trans. Mach. Learn. Res.
Robert Joseph George, Suozhi Huang, Peiyang Song, Anima Anandkumar
2025 J jnl
The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs.
CoRR
Pengrui Han, Rafal Kocielnik, Peiyang Song, Ramit Debnath, Dean Mobbs, Anima Anandkumar, R. Michael Alvarez
2024 — conf
Creative and Context-Aware Translation of East Asian Idioms with GPT-4.
EMNLP (Findings)
Kenan Tang, Peiyang Song, Yao Qin, Xifeng Yan
2024 J jnl
Creative and Context-Aware Translation of East Asian Idioms with GPT-4.
CoRR
Kenan Tang, Peiyang Song, Yao Qin, Xifeng Yan
2024 — conf
Energy Efficient Convolutions with Temporal Arithmetic.
ASPLOS (2)
Rhys Gretsch, Peiyang Song, Advait Madhavan, Jeremy Lau, Timothy Sherwood
2024 — conf
In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models.
EMNLP (Findings)
Pengrui Han, Peiyang Song, Haofei Yu, Jiaxuan You
2024 J jnl
In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models.
CoRR
Pengrui Han, Peiyang Song, Haofei Yu, Jiaxuan You
2024 J jnl
LeanAgent: Lifelong Learning for Formal Theorem Proving.
CoRR
Adarsh Kumarappan, Mo Tiwari, Peiyang Song, Robert Joseph George, Chaowei Xiao, Anima Anandkumar
2024 J jnl
Towards Large Language Models as Copilots for Theorem Proving in Lean.
CoRR
Peiyang Song, Kaiyu Yang, Anima Anandkumar
2023 A* conf
LeanDojo: Theorem Proving with Retrieval-Augmented Language Models.
NeurIPS
Kaiyu Yang, Aidan M. Swope, Alex Gu, Rahul Chalamala, Peiyang Song, Shixing Yu, Saad Godil, Ryan J. Prenger, Animashree Anandkumar
2023 J jnl
LeanDojo: Theorem Proving with Retrieval-Augmented Language Models.
CoRR
Kaiyu Yang, Aidan M. Swope, Alex Gu, Rahul Chalamala, Peiyang Song, Shixing Yu, Saad Godil, Ryan Prenger, Anima Anandkumar