Xiyao Wang

ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation

LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

Agent Learning via Early Experience

Lemon: A Unified and Scalable 3D Multimodal Model for Universal Spatial Understanding

CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning

Where do Reasoning Models Make a Difference? Follow the Reasoning Leader for Efficient Decoding

MORSE: A Suite of Programmatically Controllable Multimodal Reasoning Environments with Steerable Difficulty

ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs

SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement

LLaVA-Critic: Learning to Evaluate Multimodal Models