Daily Papers
Example-based Motion Synthesis via Generative Motion Matching
StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners
SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds
ViCo: Detail-Preserving Visual Condition for Personalized Text-to-Image Generation
Inserting Anybody in Diffusion Models via Celeb Basis
Wuerstchen: Efficient Pretraining of Text-to-Image Models
SafeDiffuser: Safe Planning with Diffusion Probabilistic Models
Bytes Are All You Need: Transformers Operating Directly On File Bytes
Brainformers: Trading Simplicity for Efficiency
Birth of a Transformer: A Memory Viewpoint
The Hidden Language of Diffusion Models
SQL-PaLM: Improved Large Language ModelAdaptation for Text-to-SQL
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
CodeTF: One-stop Transformer Library for State-of-the-art Code LLM
MuseCoco: Generating Symbolic Music from Text
Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance
Diffusion Self-Guidance for Controllable Image Generation
Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation
LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day
