Mo Guang

MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs

SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling

RE-PO: Robust Enhanced Policy Optimization as a General Framework for LLM Alignment

BlockSpec: Blockwise Speculative Decoding for Diffusion LLMs

LearnPruner: Rethinking Attention-based Token Pruning in Vision Language Models

VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments