A modular benchmark of 100 dexterous manipulation tasks across 3 arms and 6 hands with 3,180 demonstrations reveals that current policies (Diffusion Policy, DP3, OpenVLA, π0.5) achieve only 34% mean success, exposing unsolved challenges in contact-rich and precise manipulation.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.RO 4years
2026 4representative citing papers
A single RGB image is converted into a layered, simulation-ready robot scene that supports trajectory replay, synthetic data generation, and meaningful sim-real policy evaluation, plus a 564-scene DROID-Sim companion set.
ELASTIC learns a state-dependent meta-policy that allocates sequential and parallel test-time compute for generative control policies, outperforming fixed baselines in simulation and reducing real-robot latency by 34% at matched success.
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.
citing papers explorer
-
DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation
A modular benchmark of 100 dexterous manipulation tasks across 3 arms and 6 hands with 3,180 demonstrations reveals that current policies (Diffusion Policy, DP3, OpenVLA, π0.5) achieve only 34% mean success, exposing unsolved challenges in contact-rich and precise manipulation.
-
RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation
A single RGB image is converted into a layered, simulation-ready robot scene that supports trajectory replay, synthetic data generation, and meaningful sim-real policy evaluation, plus a 564-scene DROID-Sim companion set.
-
ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies
ELASTIC learns a state-dependent meta-policy that allocates sequential and parallel test-time compute for generative control policies, outperforming fixed baselines in simulation and reducing real-robot latency by 34% at matched success.
-
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.