5 papers
Re:Form -- Reducing Human Annotations in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny
Chuanhao Yan, Fengdi Che, Xuhan Huang +12
Existing informal language-based (e.g., human language) Large Language Models (LLMs) trained with Reinforcement Learning (RL) face a significant challenge: their verification proce…
Intrinsic Entropy of Context Length Scaling in LLMs
Jingzhe Shi, Qinwei Ma, Hongyi Liu +3
Long Context Language Models have drawn great attention in the past few years. There has been work discussing the impact of long context on Language Model performance: some find th…
PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning
Wanjia Zhao, Qinwei Ma, Jingzhe Shi +7
Benchmarks for competition-style reasoning have advanced evaluation in mathematics and programming, yet physics remains comparatively explored. Most existing physics benchmarks eva…
Gradient Imbalance in Direct Preference Optimization
Qinwei Ma, Jingzhe Shi, Can Jin +3
Direct Preference Optimization (DPO) has been proposed as a promising alternative to Proximal Policy Optimization (PPO) based Reinforcement Learning with Human Feedback (RLHF). How…
Graph Canvas for Controllable 3D Scene Generation
Libin Liu, Shen Chen, Sen Jia +6
Spatial intelligence is foundational to AI systems that interact with the physical world, particularly in 3D scene generation and spatial comprehension. Current methodologies for 3…