UCSD's LIFT Lets You Control Future Video Layouts via On-Policy Self-Distillation
UCSanDiego · hf · 2026-09-30
LIFT from UC San Diego is a unified image-to-video framework adding Layout-In-FuTure control: users specify what should appear in future views and where, addressing large viewpoint changes where the camera reveals unseen regions. On-policy self-distillation (OPSD) transfers dense-layout teacher control to a last-frame-layout student, supported by the LIFT-Vista dataset of large-viewpoint videos with consistent layout annotations. LIFT improves video quality, future-layout, and camera controllability over prior methods.
More from Multimodal
- Filmmakers jam with AI video generation wait times to shoot a music duet with Luma — mrjonfinger · 2026-09-30
- Meta's LSRM wins ECCV 2026 Best Paper Honorable Mention, scales 3D reconstruction with sparse attention — rsasaki0109 · 2026-09-30
- Meta's LSRM Wins ECCV 2026 Honorable Mention, Beats 3D Reconstruction SOTA by 2.4 dB — rsasaki0109 · 2026-09-30
- NVIDIA's LongLive-Plug: Distill Once, Deploy Training-Free Across 54 Downstream Video Models — nvidia · 2026-09-30
- Adobe Research Shows Adversarial Post-Training Restores Missing High-Frequency Detail in Pixel Diffusion — adobe-research · 2026-09-30
- MiniMax-H3 RefMod Upgrade: Packing JPEGs Into Safetensors Cuts Encoding Time and Kills Identity Bleed — acedelgado · 2026-09-30