robocasa
Here are 19 public repositories matching this topic...
Official codebase for Spotter: Let the Embodied Model Lead, and the VLM Reflect for It
-
Updated
Nov 16, 2026 - Python
Efficient inference / rollout for Cosmos 3 Nano / Edge robot policies
-
Updated
Oct 10, 2026 - Python
A simple, efficient, and extensible evaluation framework for robot policies across diverse benchmarks, supporting both local and remote execution
-
Updated
Oct 30, 2026 - Python
Run and compare robot VLAs and world-action models in LIBERO and RoboCasa with reproducible local evidence.
-
Updated
Sep 30, 2026 - Python
1-click robot foundation model (VLA, world action model, LLM agent) simulation and evaluation on AWS GPU instances with AWS CDK
-
Updated
Nov 17, 2026 - Python
PointmapVLA: a vision-language-action model that sees in metric 3D via robot-base-frame pointmaps. Code, checkpoints and fine-tuning/eval for LIBERO, LIBERO-Plus and RoboCasa.
-
Updated
Oct 19, 2026 - Python
Chat-driven RoboCasa simulation control plugin for DeepSeek Harness
-
Updated
Oct 28, 2026 - Python
Paired perturbation and recovery datasets for robot learning, with native simulator evidence, replay and audit tools.
-
Updated
Sep 24, 2026 - Python
Confidence-aware world-aligned 3D scene memory and SmolVLA integration for RoboCasa
-
Updated
Oct 21, 2026 - Python
Official code of StereoLift: Enhancing Vision-Language-Action Models for Precise Manipulation via Stereo Lifting
-
Updated
Nov 17, 2026 - Python
AMD ROCm Physical AI training, evaluation, simulation, rendering, and reproducible evidence suite
-
Updated
Aug 6, 2026 - Python
A vision-language agent plans and supervises mask-conditioned grasping with ACT or π0.5 in ManiSkill. Includes a RoboCasa pick-and-place workbench and verified rollouts.
-
Updated
Nov 18, 2026 - Python
VIBTARVE: VLM-initiated behavior-tree auditing of robot VLA execution. Common-evidence replay, multi-model evaluation, and human-reviewed RoboCasa GR1 tabletop recordings from GR00T N1.6.
-
Updated
Oct 27, 2026 - Python
Action-conditioned latent world model and experiment code for RoboCasa365.
-
Updated
Aug 4, 2026 - Python
SmolWAM (0.88B world-action model) on RoboCasa: zero-shot 0/30, fine-tuned 9/20 in held-out kitchens
-
Updated
Oct 15, 2026 - Python
MOPS Data Generation
-
Updated
Apr 16, 2026 - Python
Faster inference for World Action Models (FastWAM, DiT4DiT) on AMD GPUs: GEAK optimized kernels, fewer denoising steps, and Compact Action Experts.
-
Updated
Oct 23, 2026 - Python
Add this topic to your repo
To associate your repository with the robocasa topic, visit your repo's landing page and select "manage topics."