Physical attention bias cuts cable-simulation prediction error by 15%+
Avihai Giuili · hf · 2026-10-10
For learned simulators of deformable linear objects (cables), the authors add a "physical attention bias" — a learned additive term on attention logits — giving attention a notion of geometry.
Key insight: a cable has two pairwise distances (arc-length, governing elastic forces, and Euclidean, governing contact) that agree only while straight. Ablations with model and training fixed show:
- Arc-length bias reduces prediction error on unseen cables by 15%+ and more than halves segment-length drift
- Euclidean bias alone performs close to unbiased attention
- Assigning both distances across different heads is best or near-best on all metrics
Code: github.com/avihaig/dlogps
More from Embodied
- NVIDIA Research's LPR team is hiring PhD interns in embodied AI — jonLorraine9 · 2026-10-10
- PrismaX uses skilled teleoperators for robot training data, sells datasets without sales calls — jonstephens85 · 2026-10-10
- Tesla Cybercab fleet accelerates: 319 registered in Texas, 90 on the road — JOBhakdi · 2026-10-10
- LeWAM: end-to-end JEPA world model plans 32x faster, lifts robot success to 89.7% — randall_balestr · 2026-10-10
- WorkOS gave 500 devs an ESP32-S3 conference badge; they put DOOM on it — DynamicWebPaige · 2026-10-10
- Hand-built robotic skin: AI asks to plug it into its head, reads touch in a minute — repligate · 2026-10-10