arXiv:2606. 28385v1 Announce Type: cross Abstract: Recent advances in robot world models enable synthetic video generation for embodied prediction and planning.
RoboCurate is a framework that generates synthetic robot data with verified action labels by executing predicted actions in a simulator and comparing the resulting motion to the generated video. It expands scene diversity using generative models with structured editing and filters out physically implausible videos with a vision‑language model before action verification. The approach yields large performance gains across multiple manipulation benchmarks, outperforming real‑data‑only baselines by up to 179.9% in certain settings.
RoboPhys-3D is a 3D‑grounded embodied world model benchmark built on RoboTwin 2.0, featuring 50 manipulation tasks, 5,000 episodes, and 25,000 multi‑view ground‑truth videos. It evaluates video world models by processing both generated and ground‑truth videos through the same 3D reconstruction pipeline, allowing the separation of reconstruction‑induced from generation‑induced errors. The benchmark defines 50 metrics across four sub‑dimensions—pixel fidelity, 3D geometry consistency, state understanding, and task completeness—and introduces the Average Full Score and RoboPhyscore for holistic assessment, with RoboPhyscore showing strong correlation with human judgments.
arXiv:2610.04432v2 Announce Type: replace Abstract: Building interactive simulators from real-world observations is a promising way to scale embodied data, but current pipelines still rely heavily on...
arXiv:2608.24885v1 Announce Type: cross Abstract: Action-conditioned world models are increasingly used as learned simulators for policy evaluation and improvement, yet their effectiveness rests on a...
arXiv:2603. 22876v2 Announce Type: replace-cross Abstract: Learning a generalist control policy for robotic manipulation typically relies on large-scale datasets.
PhysicsLENS is a new dataset and benchmark designed to evaluate how well video generation models capture physical properties relevant to robotics. It consists of matched scenario pairs that share the same conditioning frame and task but differ in underlying physics, and it covers seven physical domains such as collision, gravity, and friction. The benchmark includes over 400 human-annotated labels from four video generation models, revealing that many plausible-looking videos still ignore the specified physical property.
arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.
Robotic foundation models achieve impressive performance on standard manipulation benchmarks, yet these evaluations typically assume clean, timely, and consistent visual observations throughout execut...
Action-conditioned world models are increasingly used as learned simulators for policy evaluation and improvement, yet their effectiveness rests on an unverified assumption: generated futures faithful...
LIBERO-VPro is a benchmark designed to assess the closed‑loop visual robustness of robotic foundation models by systematically perturbing visual inputs during task execution. It spans four dimensions—Visual Evidence Degradation, Camera Staleness, Visual Source Consistency, and Task‑Relevant Scene Variation—across 12 challenge categories, 96 settings, and 3,296 task‑condition cases. Evaluations on six models over 196,000 simulated episodes and 200 real‑world rollouts show that high nominal performance can hide significant weaknesses in visual grounding, adaptation, and sensitivity to stale or missing observations.
arXiv:2607. 26903v1 Announce Type: new Abstract: The key bottleneck in embodied AI is not model architecture but data.