Picture for Chao Wang

Chao Wang

Global Policy-Space Response Oracles for Two-Player Zero-Sum Games

Add code
May 27, 2026
Viaarxiv icon

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Add code
May 26, 2026
Viaarxiv icon

StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering

Add code
May 25, 2026
Viaarxiv icon

From Correctness to Preference: A Framework for Personalized Agentic Reinforcement Learning

Add code
May 22, 2026
Viaarxiv icon

Mem-$π$: Adaptive Memory through Learning When and What to Generate

Add code
May 20, 2026
Viaarxiv icon

Agentic Interpretation: Lattice-Structured Evidence for LLM-Based Program Analysis

Add code
May 12, 2026
Viaarxiv icon

Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancing

Add code
May 11, 2026
Viaarxiv icon

Tibetan-TTS:Low-Resource Tibetan Speech Synthesis with Large Model Adaptation

Add code
May 04, 2026
Viaarxiv icon

Relative Entropy Estimation in Function Space: Theory and Applications to Trajectory Inference

Add code
Apr 22, 2026
Viaarxiv icon

Can LLM-Generated Text Empower Surgical Vision-Language Pre-training?

Add code
Apr 20, 2026
Viaarxiv icon