Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models Paper • 2605.15961 • Published May 15 • 9
WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes Paper • 2605.15843 • Published May 15 • 6
DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo Paper • 2605.16257 • Published May 15 • 55
Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models Paper • 2605.15961 • Published May 15 • 9
Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models Paper • 2605.15961 • Published May 15 • 9
When Do Diffusion Models learn to Generate Multiple Objects? Paper • 2605.00273 • Published Apr 30 • 9
Map2World: Segment Map Conditioned Text to 3D World Generation Paper • 2605.00781 • Published May 1 • 25
When Do Diffusion Models learn to Generate Multiple Objects? Paper • 2605.00273 • Published Apr 30 • 9