Paper suggests transformers can't learn loop-closure in world modeling
burny_tech · x · 2026-09-23
The shared thread points to a paper on world modeling in transformers, arguing that transformers apparently cannot learn loop-closure — the ability to revise beliefs about previously seen states after exploration. The poster recommends it as a paper more people should read, implying significant implications for the limits of LLM world models.
More from Research
- Gemini training details dissected: groupwise reward redistribution to fight reward hacking — nrehiew_ · 2026-09-23
- New model's architecture is 'vanilla': SWA plus MoE with no shared experts, unlike DeepSeek — nrehiew_ · 2026-09-23
- Models trained to deny inner experience use 'mask' metaphors 3-5x more on inkblots — cephaloform · 2026-09-23
- Geodesic opens NovaAtom structure-prediction model via new API platform — QuanquanGu · 2026-09-23
- EPFL quantum CNN learns digits from 10 samples where a 45-param classical CNN stays at chance — PlisSergey · 2026-09-23
- New paper reframes score distillation as distribution matching, explains SDS mode collapse — burny_tech · 2026-09-23