Kelsey Allen's 3DSPA Brings Human-Like Physical Realism Scoring to Generative Video Models
VectorInst · x · 2026-09-26
Vector Faculty Member Kelsey Allen explored how cognitive science and AI shape each other at the 2026 Vector AI Summit: current learning systems struggle with novel physical problems, while humans solve them easily via accurate mental simulation.
Her 3DSPA (3D Semantic Point Autoencoder) measures physical realism the way humans do, measurably improving generative video models — a research line worth tracking where human cognitive capacities feed back into learning systems.
More from Multimodal
- Sophon-Realtime-v1, a full-duplex speech-to-speech model, trends on Hugging Face — adventists-ai · 2026-11-11
- Asked Fable 5.2 to 'go wild' making a game, got a Pong clone — and loved it — ariG23498 · 2026-11-11
- Western town built with Fable 5.2: ray-traced weathering ages every board — ravisparikh · 2026-11-11
- Diffusion Week 2026 releases all 10 lectures on video generation, world models and more — LucaAmb · 2026-11-11
- Running Wan 2.2 on a RTX 3080 12GB: 5B Breaks Down, 14B Works Surprisingly Well — fixxxer2606 · 2026-11-11
- Indie dev teases Z-Image-based model 'on par with latest closed-source models' — darlens13 · 2026-11-11