Chentao Cao

Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check

CoDaPO: Confidence and Difficulty-Adaptive Policy Optimization for Language Models

Observe-Then-Think: Learning to Elicit Multimodal Understanding by Decoupling Perception and Reasoning

DualCnst: Enhancing Zero-Shot Out-of-Distribution Detection via Text-Image Consistency in Vision-Language Models

From Debate to Equilibrium: Belief‑Driven Multi‑Agent LLM Reasoning via Bayesian Nash Equilibrium

Noisy Test-Time Adaptation in Vision-Language Models

Towards Efficient and Scalable Multi-agent Reasoning via Bayesian Nash Equilibrium

Text-Image Dual Consistency-Guided OOD Detection with Pretrained Vision-Language Models