12 papers
Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization
Zhicheng Cai, Xinyuan Guo, Hanlin Wu +4
Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip are inherently limited by exploration co…
Weak-to-Strong Generalization via Direct On-Policy Distillation
Shiyuan Feng, Huan-ang Gao, Haohan Chi +7
Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because t…
Spectral Rewiring for Exploration, Purification, and Model Merging
Zhilong Zhang, Hongli Yu, Huan-ang Gao +5
Reinforcement learning has become a standard post-training recipe for large language models, but dense full-parameter updates create two deployment-relevant bottlenecks: suppressed…
DCFold: Efficient Protein Structure Generation with Single Forward Pass
Zhe Zhang, Yuanning Feng, Yuxuan Song +3
AlphaFold3 introduces a diffusion-based architecture that elevates protein structure prediction to all-atom resolution with improved accuracy. This state-of-the-art performance has…
ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
Jinyi Hu, Shengding Hu, Yuxuan Song +6
Autoregressive and diffusion models have achieved remarkable progress in language models and visual generation, respectively. We present ACDiT, a novel Autoregressive blockwise Con…
ShortListing Model: A Streamlined SimplexDiffusion for Discrete Variable Generation
Yuxuan Song, Zhe Zhang, Yu Pei +7
Generative modeling of discrete variables is challenging yet crucial for applications in natural language processing and biological sequence design. We introduce the Shortlisting M…