iSEE world model learns object permanence from video alone, no labels
CSProfKGD · x · 2026-10-20
iSEE tackles a failure mode that babies master in their first year but today's world models still struggle with: objects vanishing once out of view.
- Learns object permanence purely from video, without any labels
- Follows hidden objects through occlusion and recognizes them when they reappear
More from Research
- UofA math dept opens tenure-track professorship in mathematical foundations of AI — CsabaSzepesvari · 2026-10-20
- Turn Trout: steering vectors today file under 'model internals', not mechanism-finding — Turn_Trout · 2026-10-20
- New RL paper: C-Slerp learns 5-cube stacking from scratch with no rewards or pretraining — ben_eysenbach · 2026-10-20
- Turn Trout: steering vectors were mechinterp's first intervention, not an outsider — Turn_Trout · 2026-10-20
- reuF2F benchmark: 244 REU math problems formalized in Lean, best model solves only 109 — wellecks · 2026-10-20
- Researchers push back on AI slop papers: reject dense unreadable submissions outright — dhadfieldmenell · 2026-10-20