Sihan Yang

The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss

MC-LLaVA: Multi-Concept Personalized Vision-Language Model

VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks

Small-Large Collaboration: Training-efficient Concept Personalization for Large VLM using a Meta Personalized Small VLM

UniCTokens-R1: Boosting Unified Personalization via Reinforcement Learning

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens