Transformer Linearity, Face-Adapter Diffusion Models, Cross-Layer Attention Shrinks LLMs, Image Generation Breakthrough
May 23, 2024•10 min•Ep. 33
Listen to this episode in Metacast mobile app
Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more
Episode description
Your Transformer is Secretly Linear
Diffusion for World Modeling: Visual Details Matter in Atari
Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and
Attribute Control
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
OmniGlue: Generalizable Feature Matching with Foundation Model Guidance
Personalized Residuals for Concept-Driven Text-to-Image Generation
For the best experience, listen in Metacast app for iOS or Android