DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers Paper • 2602.16968 • Published Feb 19 • 12
Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos Paper • 2512.01803 • Published Dec 1, 2025 • 5
Right Side Up? Disentangling Orientation Understanding in MLLMs with Fine-grained Multi-axis Perception Tasks Paper • 2505.21649 • Published May 27, 2025 • 3
Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations Paper • 2501.19066 • Published Jan 31, 2025 • 13
