Oct 2, 2026
4Director: Directing Video World Models with Rigid 3D Geometry
A video world model that lets you stage a shot from a single image: every object becomes a complete 3D mesh moved by one rigid transformation per frame, the camera lives in the same coordinate frame, and a Motion Adapter turns the rendered depth video into footage with plausible motion, appearance and lighting.
Sep 8, 2026
How to Teach Large Multimodal Models New Skills?
Fine-tuning an LMM on a new skill usually erodes what it already knew. We find that much of this 'forgetting' is a shift in the output token distribution, and that tuning only the self-attention projections, or only the MLP gate and up projections, learns almost as well as full tuning while barely forgetting.
Jul 19, 2026
FreeOrbit4D: Replaying a Single Video from Any Camera, Without Training
A training-free method that turns one monocular video into a foreground-complete 4D proxy, so a video diffusion model can re-shoot the scene from large-angle, even bullet-time, trajectories.