TISED decomposes inference optimization effects on embodied tasks and identifies paradoxical outcomes where faster per-step inference can increase task completion time on static tasks or raise success rates on dynamic tasks.
One-step flow policy: Self-distillation for fast visuomotor policies.arXiv preprint arXiv:2603.12480,
3 Pith papers cite this work. Polarity classification is still indexing.
fields
cs.RO 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
IDP generates one-step robot actions by adaptively weighting a scalar potential objective using conditional expert geometry derived from local variations of observation-similar expert actions, combined with expert-proximal terminal evaluation.
MARS policy adaptively activates multimodal generation only when beneficial in robotic tasks, claiming 16.67% higher success and 83.20% lower inference latency than baselines in real-world tests.
citing papers explorer
-
The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks
TISED decomposes inference optimization effects on embodied tasks and identifies paradoxical outcomes where faster per-step inference can increase task completion time on static tasks or raise success rates on dynamic tasks.
-
Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
IDP generates one-step robot actions by adaptively weighting a scalar potential objective using conditional expert geometry derived from local variations of observation-similar expert actions, combined with expert-proximal terminal evaluation.
-
MARS Policy: Multimodality Only When It Matters
MARS policy adaptively activates multimodal generation only when beneficial in robotic tasks, claiming 16.67% higher success and 83.20% lower inference latency than baselines in real-world tests.