Xi Chen

Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models

GenCue: Generation-Oriented Video Captions for High-Fidelity Text-to-Video

PSBench: Editing Image via GUI Agents in Photoshop

Aligning Deep Implicit Preferences by Learning to Reason Defensively

Finetune Once: Decoupling General & Domain Learning with Dynamic Boosted Annealing

U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs

ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards

Don’t Lose the Thread: Empowering Long-Horizon LLM Agents with Cognitive Resource Self-Allocation

Video Detective: Seek Critical Clues Recurrently to Answer Question from Long Videos

FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Prediction

TRACE: Temporal Grounding Video LLM via Causal Event Modeling

M2Edit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Model