Search public pages, research tools, and SAVRN solutions.
asimov-flex is an open-weight model for robotics from Emre Can Kartal, released under BSD 3-Clause License. Its published files total 928.4 KB.
Velocity-commanded walking policy for Asimov 1, trained in Isaac Lab with PPO. It is a base walk meant for later skills to build on: forward, backward and sideways walking, turning while walking or on the spot, and standing still.
By Emre Can Kartal, published under bsd-3-clause, revision 9735ab536a16.
Velocity-commanded walking policy for Asimov 1, trained in Isaac Lab with PPO. It is a base walk meant for later skills to build on: forward, backward and sideways walking, turning while walking or on the spot, and standing still. The gait was shaped with a reference cycle from an everyday human walk (CMU motion capture, retargeted with GMR) and a light AMP style reward. It was then trained further for balance (pushes from every direction, steady forces, harder terrain) and for robustness to differences between simulation and the robot (IMU tilt bias, motor strength and gain changes, extra mass, command latency, joint friction, low-friction floors). A terrain height map was used by the…
Velocity-commanded walking policy for Asimov 1, trained in Isaac Lab with PPO. It is a base walk meant for later skills to build on: forward, backward and sideways walking, turning while walking or on the spot, and standing still. The gait was shaped with a reference cycle from an everyday human walk (CMU motion capture, retargeted with GMR) and a light AMP style reward. It was then trained further for balance (pushes from every direction, steady forces, harder terrain) and for robustness to differences between simulation and the robot (IMU tilt bias, motor strength and gain changes, extra mass, command latency, joint friction, low-friction floors). A terrain height map was used by the critic during training only; the policy itself uses only the robot's joint and body sensors.
Tested in simulation only (Isaac Lab, and MuJoCo with the public Asimov 1 model). It has not been run on the real robot.
policy.onnx is the exported policy for inference, producing joint-position actions.agent.yaml records the actor-critic and AMP training settings, including the motion data configuration.env.yaml records the simulation and locomotion task settings, including observations, actions, commands, and rewards.target = default_pose + 0.25 * action, no filter.(sin(2 pi phi), cos(2 pi phi)), with phi in [0, 1).phi += 0.02 / period.period is 0.8 s at command speeds up to 0.2 m/s and 0.7 s at 0.8 m/s and above, linear in between (planar command speed).|v_xy| + |w_z| <= 0.1 the robot stands: the clock outputs (0, 0) and phi stays at 0.phi = 0 (both feet down); the right foot lifts first.Falls are the share of test episodes; pushes are velocity impulses, worst of 4 directions.
| Test | Result |
|---|---|
| Falls on flat ground, all test commands | 0% |
| Velocity tracking error, 0.25 to 0.8 m/s | 11% or less |
| Standing push 0.8 m/s, Isaac Lab | 9% falls |
| Standing push 0.8 m/s from the front / back, MuJoCo | 0% / 9% falls |
| Walking push 0.8 m/s, MuJoCo | 9% falls |
| 6 cm stairs up / ±6 cm rough ground | 22% / 25% falls |
Known limits: very hard standing pushes (1.0 m/s) from the front often cause a fall; recovery from front pushes in MuJoCo varies between nearby training checkpoints; a tilt bias of 5° or more in the IMU and command latency above about 40 ms make falls more likely.
5 files, 928.4 KB in total. The weights are 1 file totalling 841.5 KB in onnx.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| policy.onnx | Weights | 841.5 KB | 374a2e5f73be |
| agent.yaml | Configuration | 3.2 KB | — |
| env.yaml | Configuration | 79.3 KB | — |
| README.md | Documentation | 2.9 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
Released by Emre Can Kartal through its official repository on Hugging Face. Read the license.
| Precision | Weights in memory |
|---|---|
| As published | 841.5 KB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Yes. asimov-flex is released under BSD 3-Clause License. The BSD 3-Clause License is permissive. It permits commercial use and redistribution with the copyright notice, and forbids using the authors' names to endorse derived products without permission.
LIBERO 4in1（liberospatial / liberoobject / liberogoal / libero10）共 53.19 GB 的 Wan2.2-VAE 编码 latent 缓存： 训练 LIBERO policy（action head / VLA）时直接读取 latent 缓存，避免重复 VAE 编码。 - 窗口模式: windowed（--windowed） - 输出:.pt 文件，每 episode 一个 - dataset（推荐）: https://huggingface.co/datasets/MangoGoes/libero4in1wan2.2vaelatentdataset - model（本仓库）: https://huggingface.co/MangoGoes/libero4in1wan2.2vaelatentcosmosstyle
Wan2.2-TI2V-5B video DiT + 48-joint action head, trainingmode=joint. The base is suhyeok's finalized B-method recipe: a teacher-forced (sigma=0.25) self-EMA teacher plus an iBOT prototype loss at L18 L18, gamma=0.01, two-view. On top of it the 3 PAST cond latent frames are pooled into one motion frame before a chosen block. These are NOT the surrogate ctxpool runs. The surrogate line (older base, pd8 x GA1) lives in hmkang/wamctxpoolxattn and hmkang/wamctxpoolavg. Do not compare across the two sets. Geometry: 4-latin (numframesin=25, numframesout=41, fdf 2) = 4 cond + 2 future latent slots, 96 tokens per latent frame, 576 tokens per row. Effective batch 16 clips x GA 2 x 2 views = 64 rows…
weighted/imatrix quants of https://huggingface.co/DeepCybo/PhysBrain1.5-8B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/PhysBrain1.5-8B-GGUF This is a vision model - mmproj files (if any) will be in the static repository. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…
static quants of https://huggingface.co/MirilAI/Miril-DroneVLM-2B-2 For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant…
Own lineage: PPO from scratch (nb1, commit 46c48b1) continued as nb2 and nb4 (commit fac88cc), checkpoint 850 (1.328 s); evolution strategies on the weights against the Arena sprint scorer (0.952 s); then the network frozen and wrapped in a step counter carried in the headroll action that adds joint-target and forward-command offsets from about 0.5 m to the line, found by CMA-ES on the event's official seeds: 0.940 s. No other entry's weights used. Simulation only. A perpetual policy for the microduck (61-D observation, 14 actions, 50 Hz). Runs until told otherwise — a gait, loaded into a policy slot. The observation normalizer is baked into policy.onnx; feed raw observations. manifest.json…
EgoSteer-3B-RealMan is the generalist policy from EgoSteer: A Full-Stack System Towards Steerable Dexterous Manipulation from Egocentric Videos. It is a world-model-enhanced Vision-Language-Action (VLA) policy built on a Qwen3-VL backbone with a flow-matching action expert, post-trained from EgoSteer-3B-Base on real-world demonstrations collected on the RealMan robot. This is a robot-ready dual-camera (head + chest) checkpoint, corresponding to EgoSteer-9.6K-DG in the paper. For the base model to fine-tune on your own data, see EgoSteer-3B-Base. Our full-stack system integrates EgoSmith (data pipeline), Robot Stack (deployment), and EgoSteer (policy) to learn from 9.6k hours of large-scale…