Gal Chechik

Expert Merging in Sparse Mixture of Experts with Nash Bargaining

Low Rank Weight Bases for Visual Analogies

Go Beyond Your Means: Unlearning with Per-Sample Gradient Orthogonalization

Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models

Policy Gradient with Tree Expansion

Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models

Policy Optimized Text-to-Image Pipeline Design

Multi-Shot Character Consistency for Text-to-Video Generation

IT$^3$: Idempotent Test-Time Training

Policy Gradient with Tree Expansion

ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation

Real Time Macro-Block Rate Control for Task-Aware Video Compression Using Reinforcement Learning

IT$^3$: Idempotent Test-Time Training

Make It Count: Text-to-Image Generation with an Accurate Number of Objects