Humphrey Shi

Training-Free Adaptive Frame Selection for Video-Language Understanding

Sound in Sights: Deriving Visual Insights from Audio for Comprehensive Video Understanding with Large Multimodal Models

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation

Revisiting Positional Information in Transformers in the era of Fused Attention

ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance

HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models

Generalized Neighborhood Attention: Multi-dimensional Sparse Attention at the Speed of Light

FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction

StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

ACID: A Comprehensive Dataset for AI-Created Image Detection