Reading Modes
Open Artifacts with links to supporting source material.
850 selected reportsLast 30 days 753 recordsAll coverage 2,512 records
TouchScale is a 500-hour human visual-tactile dataset collected with unified sensors and synchronization, showing scaling benefits in both perception and robotic manipulation. The dataset enables cross-sensor generalization and improves robot task success rates from 22.5% to 57.5% through mid-training. The study highlights the potential of large-scale visual-tactile data to enhance embodied AI systems.
This paper presents OpenWAM, an open framework for world-action models (WAM) that aims to standardize the evaluation of different WAM designs. The framework includes a three-stage training process, a shared MoT architecture, and four configurable interaction modes. It introduces modular components like IDM and FDM, trained on a large-scale 'counterfactual' dataset, leading to improved task success rates in both simulation and real-world robotic tasks.
Kyvern is an Apache-2.0 Python library that records a robot's decisions in a signed, hash-linked chain, allowing external verification. It supports ROS 2 with an example safety controller and provides tools for generating compliance reports. While not yet a certified safety system, it offers a framework for accountability and transparency in autonomous systems.
Developers are using NVIDIA Omniverse libraries combined with frontier AI models to build simulation applications for robotics. The article details workflows for creating animated 3D assets, testing robotic disassembly in CAD environments, reconstructing editable building models from site scans, analyzing industrial equipment operating scenarios, assembling simulation scenes with open-source assets, and stress-testing warehouse simulations at scale. NVIDIA writers describe these projects as demonstrations of agent-assisted creation and simulation capabilities within the Omniverse ecosystem.
Odyssey, an AI research company, has released Odyssey-3, its most powerful world model to date. This model enables intelligent systems to understand, predict, and interact with both physical and virtual environments. It has been adopted by companies like Flexion and demonstrated across six domains, including robotics, humanoids, vehicles, AI training, drones, and games.
NVIDIA has released a trained policy model for the Cosmos3-Nano robot, fine-tuned on the LIBERO-10 environment. The model achieves 93.3% success in standard scenes and 83.2% in perturbed scenes. It is part of a synthetic data study and is licensed under NVIDIA's Open Model License.
Amazon has launched the Physical AI Toolchain on AWS, an open-source platform that combines architecture guidance, deployment automation, and ready-to-use code. It integrates with NVIDIA's Physical AI stack to support the full development lifecycle of physical AI, enabling machines to perceive, understand, and act in the real world. The toolchain includes synthetic data generation, model training, simulation, edge deployment, and continuous improvement, powered by AWS services and NVIDIA's physical AI ecosystem.
TouchScale is a 500-hour human vision-tactile dataset collected with unified sensors and synchronization, showing scaling benefits in both perception and robotic manipulation. The dataset enables cross-sensor generalization and improves robot task success rates without action labels, suggesting a new path for embodied AI training.
This article analyzes the GitHub daily chart to explore the rising popularity of teleoperation in robotics and the dynamics within the open-source community. The author points out that evaluating projects should focus on direction rather than just star counts, emphasizing key technical aspects such as URDF models, kinematics, input device abstraction layers, and ROS communication systems. Additionally, the article provides five dimensions for evaluating repositories and a five-minute checklist to help readers filter high-quality projects.
NVIDIA has released a trained policy model for the Cosmos3-Nano robot, fine-tuned on LIBERO-10 tasks. The model demonstrates success rates of 94.5% in standard scenes and 87.1% in perturbed scenes, with training data and evaluation details provided.
NVIDIA has released a policy model trained on the LIBERO-10 environment, part of the Cosmos Cookbook recipe, with performance metrics across standard and perturbed scenes. The model is available under the NVIDIA Open Model License and can be loaded by the cosmos-framework policy server.
NVIDIA has released a trained policy model for the Cosmos3-Nano framework, specifically adapted for the LIBERO-10 environment. The model was trained on a combination of real and synthetic data, achieving success rates of 93.9% in standard scenes and 84.7% in perturbed scenes. The model is part of a broader study on restyling demonstrations and is available under the NVIDIA Open Model License.
NVIDIA has published a policy model trained on LIBERO-10 data as part of the Cosmos Cookbook, enabling sim-to-real transfer and policy evaluation. The model is exported as a checkpoint with EMA weights and can be loaded by the cosmos-framework policy server. Training data and restyled demonstrations are sourced from the LIBERO_LeRobot_v3 repository.
NVIDIA has released a policy model trained on LIBERO-10, part of the Cosmos Cookbook recipe. The model, trained with 379 real demonstrations and 1137 duplicates, achieves 94.2% success in standard scenes and 85.3% in perturbed scenes. The model is available under the NVIDIA Open Model License.
NVIDIA has released a policy model trained on LIBERO-10, part of the Cosmos Cookbook recipe, with performance metrics showing 93.9% success in standard scenes and 85.1% in perturbed scenes. The model is available under the NVIDIA Open Model License.
DialoStack is a set of ROS 2 packages that enables structured spoken dialogue for robots, using Python for dialogue flow and LLMs for interpretation and response generation. It is open-source (MIT), supports slot-filling, explanation, and quiz dialogue types, and includes speech and vision I/O. The tool is designed for use in human-robot interaction scenarios and is available on GitHub.
TouchScale is a 500-hour human vision-touch dataset collected using a unified sensor setup, enabling scaling benefits in both perception and robotic manipulation. The dataset improves robot task success rates through mid-training with human data, demonstrating the potential of large-scale human experience in training embodied agents.
This article provides an in-depth analysis of the popular projects on the GitHub Trending list on September 24, 2026, covering AI Agents, robot teleoperation, quantitative data services, and life efficiency tools. The article dissects the technical implementations and application scenarios of several trending projects, while also addressing common issues developers face when using GitHub, such as access latency and expired student authentication. Additionally, it offers practical advice on how to effectively use daily chart projects for learning and contribution.
This paper presents a systematic analysis of Vision-Language-Action (VLA) research, focusing on datasets, benchmarks, and data engines. It identifies key challenges in data fidelity, scalability, and evaluation, and proposes a structured approach to address these issues. The authors release an open-source repository to support the community.
This GitHub repository is a curated list of Vision-Language-Action (VLA) models, architectures, benchmarks, and datasets for robotics and embodied AI, with a focus on 2025–2026. It includes foundational models like RT-1, RT-2, and OpenVLA, as well as advanced models such as π0, GR00T N1, and Gemini Robotics. The repository also features architectural innovations, benchmarks like LIBERO and RoboTwin 2.0, and open-source code for many of the models.
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).