Zhihong Zhu

MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models

Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models

RAGCell: Retrieval-Augmented Generation as Supervision for Versatile Single-cell Analysis

UniCoTT: A Unified Framework for Structural Chain-of-Thought Distillation

DisPose: Disentangling Pose Guidance for Controllable Human Image Animation

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

$\text{D}_{2}\text{O}$: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models