Track recent robotics research publications, benchmarks, datasets, model releases, and technical papers. Browse dated, source-backed robotics company events
· research publication · Perceptron · Foundation Models
Evidence notes
Isaac 0.5 accepts images, video, language instructions, robot state and previous actions, and can return grounded visual outputs, task progress or robot actions.
Training combined more than 35 robot systems, 100,000 hours of robot experience, one million hours of general video and three trillion multimodal tokens.
Perceptron published model weights on Hugging Face, training and inference code on GitHub, and a technical report; LeRobot support is included.
· research publication · Lightwheel · Data Infrastructure
Evidence notes
The collection spans seven environment categories, 128 scene classes, more than 15,000 collection scenes and more than 15,000 tasks.
Head- and wrist-mounted views are paired with depth, hand-pose, full-body-pose and event-level semantic annotations for manipulation, coordination and task-sequence learning.
The first tranche is distributed through Hugging Face and AtomGit, and Lightwheel said the project will be donated to the OpenAtom Foundation for incubation.
· research publication · Generalist · GEN-1 · Foundation Models
Evidence notes
Across 10 tasks, Generalist reports 59% average success from one 3–12 second in-context demonstration and 83% after 10 gradient steps on five minutes of task data.
The multimodal model maintains 30 seconds of video context alongside sensor, language and proprioceptive inputs, and produces action trajectories at 100 Hz.
The release also shows prompts transferring from simulation to a physical robot and, in some cases, from human-hand demonstrations to immediate robot execution.
· research publication · Skild AI · S1 · Foundation Models
Evidence notes
S1 applies in-context learning to seen and unseen manipulation tasks, including plant potting, pancake preparation, pour-over coffee and kit assembly.
Skild reports unseen tasks lasting up to 10 minutes and a sevenfold improvement over language-only prompting on its evaluation set.
The official release demonstrates transfer from a human video example to robot execution, including an 11-minute demonstration-to-execution plant-potting workflow.
A new episode format with topic-group chunking reduced storage by about 68% and made sample reads approximately 2.9 times faster.
An Airflow-based ingestion architecture increased throughput from 14,000 to 440,000 episode-hours per week, cutting million-hour processing from roughly 16 months to under three weeks.
Warehouse-backed curation and memory-mapped tables reduced time to first training batch from about 48 hours to under one minute across a 43-million-episode dataset.
The release covers real-robot post-training, inference and deployment, plus evaluation code for RoboCasa, RoboCasa365, VLABench and RoboDojo.
Xiaomi-Robotics-1 was pre-trained on more than 100,000 hours of embodiment-free UMI trajectories and post-trained on more than 10,000 hours of cross-embodiment data.
The Apache-2.0 repository links the 5B base model and benchmark-specific checkpoints distributed through Xiaomi Robotics on Hugging Face.
GAIA-4 reconstructs logged road scenes directly from recorded sensor data without HD maps, hand-built scene graphs or a separate annotation stack.
Its world-on-rails mode changes the ego vehicle trajectory while holding other road users to their logged behaviour, providing a deterministic comparison baseline.
The model generates coherent camera and radar observations and also supports reactive-agent scenarios for interactive safety evaluation.
HOST was evaluated across 50 novel manipulation tasks and achieved 62% average success on the eight-task baseline-comparison set.
Average skill-acquisition time was 29 seconds, with a 43-point advantage over the strongest compared method without parameter updates.
The project page, implementation code and paper are publicly available; the work was developed with researchers from Tsinghua University and Beijing Institute of Technology.