Yingjie Wang

EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models

CoFact: Conformal Factuality Guarantees for Language Models under Covariate Shift

Theoretical Guarantees for Iterative Alignment of Self-Rewarding Language Models

S$^2$MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection

Unsupervised Reinforcement Learning with Verifiable Rewards via First Repeat Criterion

Towards a Theoretical Understanding of In-context Learning: Stability and Non-I.I.D Generalisation

Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG

Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

Self-Verification Provably Prevents Model Collapse in Recursive Synthetic Training

A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops

A Statistical Approach for Controlled Training Data Detection

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

S$^2$MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection