Yilun Du: Energy-Based Models Enable Robot Generalization by Construction
du_yilun · x · 2026-09-09
Yilun Du shares his research perspective 'Generalization by Construction' on moving robot generalization beyond collecting more demonstrations.
- Robots can use inference to solve tasks they were never explicitly trained on — planning actions and goals before acting with learned world models
- For placing a mug on a crowded table, learning to evaluate whether a candidate placement is stable and reachable relies on simpler, more reusable relationships than the full scene-to-placement mapping
- Inference compares and refines candidate placements; energy-based models (EBMs) provide a natural landscape for this search
Related event: Du Yilun Proposes Reasoning-Driven Robot Generalization(3 posts)→
More from Embodied
- Burgundy iPhone 18 Pro shown off at Apple event — iamfakhrealam · 2026-09-10
- Project CETI's AI uncovers vowel-like patterns in sperm whale vocalizations — begusgasper · 2026-09-10
- Waymo co-CEO Dmitri Dolgov, at Google's self-driving project since 2009, to speak at SPC — adityaag · 2026-09-10
- Vapor Chambers Are Now a Given: Even Whurley Says There's No Going Back — whurley · 2026-09-10
- A20 Pro: 40% faster than iPhone 17 Pro, 2x neural engine compute for on-device AI — testingcatalog · 2026-09-10
- A20 Pro chip revealed: 2nm process, doubled 32-core neural engine, 50% more bandwidth — iamfakhrealam · 2026-09-10