6 papers
PhyVLLM: Physics-Guided Video Language Model with Motion-Appearance Disentanglement
Yu-Wei Zhan, Xin Wang, Hong Chen +6
Video Large Language Models (Video LLMs) have shown impressive performance across a wide range of video-language tasks. However, they often fail in scenarios requiring a deeper und…
Multi-modal Generative AI: Multi-modal LLMs, Diffusions, and the Unification
Xin Wang, Yuwei Zhou, Bin Huang +2
Multi-modal generative AI (Artificial Intelligence) has attracted increasing attention from both academia and industry. Particularly, two dominant families of techniques have emerg…
Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning
Chendi Ge, Xin Wang, Zeyang Zhang +5
Continual multimodal instruction tuning is crucial for adapting Multimodal Large Language Models (MLLMs) to evolving tasks. However, most existing methods adopt a fixed architectur…
Modular-Cam: Modular Dynamic Camera-view Video Generation with LLM
Zirui Pan, Xin Wang, Yipeng Zhang +4
Text-to-Video generation, which utilizes the provided text prompt to generate high-quality videos, has drawn increasing attention and achieved great success due to the development…
VideoDreamer: Customized Multi-Subject Text-to-Video Generation with Disen-Mix Finetuning on Language-Video Foundation Models
Hong Chen, Xin Wang, Guanning Zeng +5
Customized text-to-video generation aims to generate text-guided videos with user-given subjects, which has gained increasing attention. However, existing works are primarily limit…
Behavior Importance-Aware Graph Neural Architecture Search for Cross-Domain Recommendation
Chendi Ge, Xin Wang, Ziwei Zhang +6
Cross-domain recommendation (CDR) mitigates data sparsity and cold-start issues in recommendation systems. While recent CDR approaches using graph neural networks (GNNs) capture co…