Zehui Chen

FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

AgentGym-RL: An Open-Source Framework to Train LLM Agents for Long-Horizon Decision Making via Multi-Turn RL

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

Critique-RL: Training Language Models For Critiquing Through Two-Stage Reinforcement Learning

AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios

V2P-Bench: Evaluating Video-Language Understanding with Visual Prompts for Better Human-Model Interaction

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

ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

MMSearch: Unveiling the Potential of Large Models as Multi-modal Search Engines

MindSearch: Mimicking Human Minds Elicits Deep AI Searcher

PseDet: Revisiting the Power of Pseudo Label in Incremental Object Detection

Transfering Knowledge into Efficient Tiny Models for Object Detection with Dual Prompt Distillation