ICML2026 to Feature Multiple Video Generation Research Papers
cindy_x_wu · x · 2026-07-05
Researchers will present several papers at ICML2026: "Motion Attribution for Video Generation" has been accepted as an oral presentation. Workshops will also feature "Addressable Memory for Video World Models" and expected variance reduction methods under diffusion teachers, among others.
Related event: MOTIVE Receives ICML Outstanding Paper Honorable Mention(6 posts)→
More from Multimodal
- Gen games don't need to be realtime — turn-based interactivity works, devs argue — djcows · 2026-10-27
- Lip sync face-off: Omniflash vs Minimax H3 on The Everlight — Uszko_Visuals · 2026-10-27
- Short film 'Odissey of Aeons' made with MiniMax H3 video generation — Musikalandia · 2026-10-27
- Remiqora Video: open-source local studio turns one idea into 4K chained AI videos — inikolax · 2026-10-27
- Single HTML/JS file generates creative art and copy in-browser with zero LLM calls — Afinetheorem · 2026-10-27
- $5k kale-img-1 fine-tuning contest won with MOSS-Image base, SDXL trails far behind — ostrisai · 2026-10-27