🏢 University of California, San Diego
Fast Video Generation with Sliding Tile Attention
·4012 words·19 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Video Understanding
🏢 University of California, San Diego
Sliding Tile Attention (STA) boosts video generation speed by 2.43-3.53x without losing quality by exploiting inherent data redundancy in video diffusion models.
Personalized Multimodal Large Language Models: A Survey
·599 words·3 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Multimodal Learning
Vision-Language Models
🏢 University of California, San Diego
This survey reveals the exciting advancements in personalized multimodal large language models (MLLMs), offering a novel taxonomy, highlighting key challenges and applications, ultimately pushing the …