TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times Paper • 2512.16093 • Published 8 days ago • 45
SpatialTree: How Spatial Abilities Branch Out in MLLMs Paper • 2512.20617 • Published 2 days ago • 40
StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation Paper • 2512.09363 • Published 16 days ago • 70
PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling Paper • 2505.23155 • Published May 29 • 2
LLM in a flash: Efficient Large Language Model Inference with Limited Memory Paper • 2312.11514 • Published Dec 12, 2023 • 260