Junjun He

UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis

StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding

HiST: Spatial Transcriptomics Prediction via Multi-Level Hyperbolic Representation Learning

MedQ-Bench: Evaluating and Exploring Medical Low-level Visual Abilities in MLLMs

THE-Tree: Can Tracing Historical Evolution Enhance Scientific Verification and Reasoning?

On the Measurement and Efficient Mitigation of Length Generalization Gaps in Large Language Models

MedITok: A Unified Tokenizer for Medical Image Synthesis and Interpretation

Escaping Low-Rank Traps: Interpretable Visual Concept Learning via Implicit Vector Quantization

SmartMat Explorer: Automated scientific research for materials discovery

Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation

Reliable Lifelong Multimodal Editing: Conflict-Aware Retrieval Meets Multi-Level Guidance

AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation

GMAI-VL & GMAI-VL-5.5M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI

SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding