Causal-JEPA: LeCun team proposes world models via object-level latent masking
burny_tech · x · 2026-08-29
The post discusses the Causal-JEPA paper (by Yann LeCun et al.), proposing an object-centric world model using latent masking. By masking object states and forcing inference from context during training, C-JEPA addresses interaction-dependent dynamics. It shows 20% improvement in counterfactual reasoning and uses only 1% of the input features for comparable performance in control tasks compared to patch-based models.
More from Research
- Anthropic shows AI researchers autonomously improving alignment of other models — VraserX · 2026-08-30
- Learn Positional Encodings derivation from first principles — zainhas · 2026-08-30
- COLM Paper Traces Capability Provenance in LLMs via Gradient Attribution — ziv_ravid · 2026-08-30
- Toby Ord paper argues recursive self-improvement has physical limits — Exponential View (Azeem Azhar) · 2026-08-30
- AI Formalization Tools Fable and Sol Spot First Repairable Error in Published Literature — Sauers_ · 2026-08-30
- Mark Schmidt Posts ICML Tutorial Video: Is Numerical Optimization Theory Irrelevant to ML Practice in 2026? — MarkSchmidtUBC · 2026-08-30