Paper: Language Models Represent Space and Time in Their Internal Activations
burny_tech · x · 2026-09-25
A shared paper, 'Language Models Represent Space and Time,' shows LLMs encode linear representations of space and time in their internal activations.
Probing experiments demonstrate consistent spatial and temporal 'world model' structures inside the models, notable interpretability evidence for how LLMs organize world knowledge.
Related event: Paper Finds Language Models Internally Represent Space and Time(2 posts)→
More from Research
- New Research Examines How AI Agents Enter Markets and How Markets Should Be Designed for Them — sethlazar · 2026-09-25
- Vite core member finds methodology flaws inflating oj's memory benchmarks by 100MB+ — cnakazawa · 2026-09-25
- DeepMind Paper: One Misleading Hint Drops Coding Agent Scores by Up to 46.7% — dair_ai · 2026-09-25
- NeurIPS paper shows self-improving, self-replicating agents evolve cooperation from scratch — maxhkw · 2026-09-25
- Continuous diffusion LM RePlaid accepted at NeurIPS 2026, matches discrete diffusion scaling — ArashVahdat · 2026-09-25
- AAAI 2027 phase 1 reviews are out — CSProfKGD · 2026-09-25