Fei Yu

Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs

TAR-TVG: Enhancing LVLMs with Timestamp Anchor-Constrained Reasoning for Temporal Video Grounding

ReDit: Reward Dithering for Improved LLM Policy Optimization

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking

RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion Models

Universal Visuo-Tactile Video Understanding for Embodied Interaction

Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models

WMarkGPT: Watermarked Image Understanding via Multimodal Large Language Models

Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models

LEARN TO LEARN CONSISTENTLY