181 dated model releases
Browse published model records with source-backed, day-level release dates. Results stay pinned to one Catalog generation as you move between pages.
Source-backed models.
lerobot · 2026-10-15
A LeRobot EnvHub environment built natively in NVIDIA Isaac Sim 6.2: an SO-101 arm in the turquoise of the LeRobot kits, four painted wooden 3 cm cubes and a green open box on a table in a simple room, simulated by PhysX and rendered with RTX.
0 downloads
30% confidence · verified 2026-10-22
lerobot · 2026-10-15
A LeRobot EnvHub environment: an SO-101 arm in the turquoise of the LeRobot kits, four painted wooden 3 cm cubes (red, green, blue, yellow) and a green open box on a table in a simple room, simulated with MuJoCo. Each reset places the cubes, the box and the front camera with seeded offsets.
0 downloads
30% confidence · verified 2026-10-22
lerobot · 2026-10-07
Checkpoint fine-tuned by the authors on RoboTwin 2.0 (checkpoints/globalstep50000).
341 downloads
53% confidence · verified 2026-10-22
lerobot · 2026-10-07
Pre-trained base checkpoint, the starting point for fine-tuning on a new robot.
234 downloads
53% confidence · verified 2026-10-22
Reward AI · 2026-09-14
OM-1 (Omnibody Model 1) is Reward AI's general-purpose robot policy learned only from human demonstrations captured with the wearable Omnibody Hand, with no teleoperation or on-robot data, and deployed across robot arms and humanoids at human speed.
Artifacts not listed
23% confidence · verified 2026-09-15
robbyant · 2026-09-04
We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. - Unbounded Interaction Horizon: Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully crafted causal pretraining paradigm. - Rapid Response Time:…
0 downloads
43% confidence · verified 2026-10-22
robbyant · 2026-09-04
We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. - Unbounded Interaction Horizon: Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully crafted causal pretraining paradigm. - Rapid Response Time:…
0 downloads
43% confidence · verified 2026-10-22
robbyant · 2026-09-04
We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. - Unbounded Interaction Horizon: Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully crafted causal pretraining paradigm. - Rapid Response Time:…
0 downloads
43% confidence · verified 2026-10-22
Generalist AI · 2026-08-19
GEN-1.5 is Generalist AI's embodied foundation model for learning robot skills in context from short demonstrations, using video, sensor, language, and proprioceptive inputs to produce action trajectories.
Artifacts not listed
23% confidence · verified 2026-08-26
Skild AI · 2026-08-18
S1 is Skild AI's robotic foundation model for in-context execution from a single video demonstration, including source-reported unseen and long-horizon tasks without post-training.
Artifacts not listed
23% confidence · verified 2026-08-26
Dyna Robotics · 2026-08-10
Dyna-2 is Dyna Robotics' world-action model, pre-trained on more than one million hours of egocentric human video and evaluated on held-out human and robot data.
Artifacts not listed
23% confidence · verified 2026-08-26
lerobot · 2026-08-05
This is a lossless key-layout conversion of IPEC-COMMUNITY/EO-1-3B at revision fe0a015d9349bdf886d898809213b3574eedf1f9 for LeRobot's native eo1 policy implementation.
215 downloads
58% confidence · verified 2026-10-22
lerobot · 2026-07-28
Byte-identical tensor conversion of tencent/Hy-Embodied-0.5-VLA-RoboTwin at revision bd7bba6f5934ad62293a2a34f74760c6a3ef2ff8.
51 downloads
58% confidence · verified 2026-10-22
lerobot · 2026-07-28
Byte-identical tensor conversion of tencent/Hy-Embodied-0.5-VLA-UMI at revision 3f53d1f8d2bc587c523cfdc9f1041ceee42c2524.
54 downloads
53% confidence · verified 2026-10-22
lerobot · 2026-07-28
This is a deterministic LeRobot-format conversion of BeingBeyond/Being-H05-2B. It contains the policy configuration, serialized preprocessor and postprocessor pipelines, tokenizer, conversion report, and safetensors weights.
0 downloads
58% confidence · verified 2026-10-22
lerobot · 2026-07-28
This is a deterministic LeRobot-format conversion of BeingBeyond/Being-H05-2B_robocasa. It contains the policy configuration, serialized preprocessor and postprocessor pipelines, tokenizer, conversion report, and safetensors weights.
0 downloads
58% confidence · verified 2026-10-22
lerobot · 2026-07-28
Official model catalog record.
0 downloads
48% confidence · verified 2026-10-05
robbyant · 2026-07-08
Official model catalog record.
471 downloads
63% confidence · verified 2026-07-28
robbyant · 2026-07-08
We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. - Unbounded Interaction Horizon: Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully crafted causal pretraining paradigm. - Rapid Response Time:…
135 downloads
58% confidence · verified 2026-10-22
Robbyant · 2026-07-08
Infinite Worlds with Versatile Interactions
1.5K stars
25% confidence · verified 2026-10-08
robbyant · 2026-07-08
We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. - Unbounded Interaction Horizon: Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully crafted causal pretraining paradigm. - Rapid Response Time:…
0 downloads
58% confidence · verified 2026-10-22
Robbyant · 2026-07-07
A whole-body VLA release focused on broader cross-embodiment transfer, mobile manipulation, and predictive dynamics supervision.
Code · Weights
53% confidence · verified 2026-10-08
3 linked datasets
Robbyant · 2026-07-06
Self-supervised learning for spatial perception
981 stars
25% confidence · verified 2026-10-08
robbyant · 2026-07-06
LingBot-Vision is a family of self-supervised Vision Transformer backbones for dense spatial perception. The models are pretrained with masked boundary modeling, a boundary-centric objective that encourages spatially structured patch features while retaining strong semantic representations.
2 downloads
43% confidence · verified 2026-10-22
