Wenxuan Huang

Interleaving Reasoning for Better Text-to-Image Generation

ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance Generation

RRVF: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback

Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning

IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?

CLIP-Map: Structured Matrix Mapping for Parameter-Efficient CLIP Compression

Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models

LLaVA-RadZ: Can Multimodal Large Language Models Effectively Tackle Zero-shot Radiology Recognition?

CompBench: Benchmarking Complex Instruction-guided Image Editing

Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?

Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models

Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification