papers

Publications (12)

cs.LG2025

P1: Mastering Physics Olympiads with Reinforcement Learning

Jiacheng Chen, Qianjia Cheng, Fangchen Yu +25

Recent progress in large language models (LLMs) has moved the frontier from puzzle-solving to science-grade reasoning-the kind needed to tackle problems whose answers must stand ag…

cs.LG2026

Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning

Bowen Ding, Yuhan Chen, Jiayang Lyv +9

Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) dominate the post-training landscape for mathematical reasoning, yet differ fundamentally in their reliance on expert t…

cs.CL2025

Keys to Robust Edits: from Theoretical Insights to Practical Advances

Jianhao Yan, Futing Wang, Yun Luo +2

Large language models (LLMs) struggle with maintaining accurate knowledge due to conflicting/outdated parametric memories. While locate-and-edit methods address this, their relianc…

cs.CL2025

Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model

Bowen Ding, Yuhan Chen, Futing Wang +2

Large Reasoning Models (LRMs) excel at solving complex problems but face an overthinking dilemma. When handling simple tasks, they often produce verbose responses overloaded with t…

cs.CL2025

ELICIT: LLM Augmentation via External In-Context Capability

Futing Wang, Jianhao Yan, Yue Zhang +1

Enhancing the adaptive capabilities of large language models is a critical pursuit in both research and application. Traditional fine-tuning methods require substantial data and co…

cs.AI2025

SafeWork-R1: Coevolving Safety and Intelligence under the AI-45 Law

Shanghai AI Lab, :, Yicheng Bao +115

We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framewo…

cs.CL2025

Benchmarking and Rethinking Knowledge Editing for Large Language Models

Guoxiu He, Xin Song, Futing Wang +1

Knowledge editing aims to update the embedded knowledge within Large Language Models (LLMs). However, existing approaches, whether through parameter modification or external memory…

cs.CL2026

Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence

Wanying Ren, Xin Song, Futing Wang +2

Parameter-based knowledge editing updates the internal knowledge of large language models (LLMs) via localized weight modifications and has attracted significant attention. However…

cs.AI2026

P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads

Yun Luo, Futing Wang, Qianjia Cheng +28

The transition from symbolic manipulation to science-grade reasoning represents a pivotal frontier for Large Language Models (LLMs), with physics serving as the critical test ancho…

cs.CL2026

Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning

Futing Wang, Jianhao Yan, Yun Luo +6

Achieving effective test-time scaling requires models to engage in In-Context Exploration -- the intrinsic ability to generate, verify, and refine multiple reasoning hypotheses wit…

cs.CL2024

Potential and Challenges of Model Editing for Social Debiasing

Jianhao Yan, Futing Wang, Yafu Li +1

Large language models (LLMs) trained on vast corpora suffer from inevitable stereotype biases. Mitigating these biases with fine-tuning could be both costly and data-hungry. Model…

cs.AI2026

Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling

Yafu Li, Runzhe Zhan, Haoran Zhang +25

Recent progress in reasoning models has substantially advanced long-horizon mathematical and scientific problem solving, with several systems now reaching gold-medal-level performa…