Yan Lu

CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework

When MLLMs Meet Compression Distortion: A Coding Paradigm Tailored to MLLMs

Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images

MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning

Temperature as a Meta-Policy: Adaptive Temperature in LLM Reinforcement Learning

Integer-Centric Neural Video Compression

Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models

SiMAE: Subject-identity Separation Latent Masked Autoencoder for Multi-contrast MRI Synthesis and Uncertainty Estimation

Generative Latent Video Compression

One-Step Diffusion-Based Image Compression with Semantic Distillation

Omnidirectional 3D Scene Reconstruction from Single Image

VideoVLA: Video Generators Can Be Generalizable Robot Manipulators

Image as a World: Generating Interactive World from Single Image via Panoramic Video Generation

Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding