Yibing Song

OpenFoley: Open-Set Video-to-Audio Generation with Modality-Aware Masking and Flows

$HiMaCon:$ Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data

CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step

AutoCGP: Closed-Loop Concept-Guided Policies from Unlabeled Demonstrations

REMEDY: Recipe Merging Dynamics in Large Vision-Language Models

PiCO: Peer Review in LLMs based on Consistency Optimization

Dynamic Diffusion Transformer

Re-Aligning Language to Visual Objects with an Agentic Workflow

Unleashing the Power of Selective State Space Models in Vision-Language Models