Picture for Kunchang Li

Kunchang Li

Make Your Training Flexible: Towards Deployment-Efficient Video Models

Add code
Mar 18, 2025
Viaarxiv icon

V-Stylist: Video Stylization via Collaboration and Reflection of MLLM Agents

Add code
Mar 15, 2025
Viaarxiv icon

TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision

Add code
Mar 10, 2025
Viaarxiv icon

VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

Add code
Dec 31, 2024
Viaarxiv icon

Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment

Add code
Dec 26, 2024
Viaarxiv icon

Causal Diffusion Transformers for Generative Modeling

Add code
Dec 17, 2024
Viaarxiv icon

Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel

Add code
Dec 11, 2024
Viaarxiv icon

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning

Add code
Oct 25, 2024
Viaarxiv icon

TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration

Add code
Oct 16, 2024
Viaarxiv icon

MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration

Add code
Aug 21, 2024
Viaarxiv icon