Xiaotao Gu

Kaleido: Open-Sourced Multi-Subject Reference Video Generation Model

Listens like Mel: Boosting Latent Audio Diffusion with Channel Locality

UI2Code$^N$: A Visual Language Model for Test-Time Scalable Interactive UI-to-Code Generation

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models

VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

RedHat: Towards Reducing Hallucination in Essay Critiques with Large Language Models

LVBench: An Extreme Long Video Understanding Benchmark