Cross-modal Steering Vectors Exist Across Both Image and Text Generation Paper • 2610.36269 • Published 10 days ago • 12
LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs Paper • 2602.00462 • Published Jan 31 • 21
Learning Action and Reasoning-Centric Image Editing from Videos and Simulations Paper • 2407.03471 • Published Jul 3, 2024 • 30