Search public pages, research tools, and SAVRN solutions.
PredActor_Artifacts is an open-weight model for robotics from Raymon Yip, released under MIT License. Its published files total 595.3 MB.
Official evaluation checkpoints for PredActor, a predictive action diffusion controller for steerable Unitree G1 locomotion.
By Raymon Yip, published under mit, revision 9a81a58eecd6.
Official evaluation checkpoints for PredActor, a predictive action diffusion controller for steerable Unitree G1 locomotion. The model jointly predicts future states and actions, uses its internal state trajectory for guidance, and directly executes the selected 29-DoF action. This repository contains the two learned artifacts required by the public - the released PDP051 text-conditioned PredActor policy; - the fine-tuned G1 MotionCLIP encoder used for semantic conditioning. Source code, the browser-based evaluator, and G1 robot assets are maintained in the public PredActor repository. Training datasets, experiment outputs, hardware deployment bundles, and additional checkpoints are not…
Official evaluation checkpoints for PredActor, a predictive action diffusion controller for steerable Unitree G1 locomotion. The model jointly predicts future states and actions, uses its internal state trajectory for guidance, and directly executes the selected 29-DoF action.
This repository contains the two learned artifacts required by the public MuJoCo evaluation path:
Source code, the browser-based evaluator, and G1 robot assets are maintained in the public PredActor repository. Training datasets, experiment outputs, hardware deployment bundles, and additional checkpoints are not included here.
Install uv, then run:
git clone https://github.com/MasterYip/PredActor.git
cd PredActor
uv sync --locked
uv run --locked python scripts/hf_download.py --filter checkpoints
uv run --locked predactor-eval
The downloader recreates the expected layout under the Git-ignored
Artifacts/ directory and verifies the published byte sizes and SHA-256
identities. The evaluator opens http://127.0.0.1:8765/, uses CUDA when
available, and otherwise falls back to CPU.
| Artifact | Role | Size | SHA-256 |
|---|---|---|---|
checkpoints/predactor/pdp051/latest.ckpt |
Text-conditioned PredActor policy | 49,212,894 bytes | 2d963b32786f2989c6472726df9fcfe6b385590127e12e1f549a4b7d77488b2e |
checkpoints/motionclip/g1-model-xyz-clip/checkpoint_0100.pth.tar |
Fine-tuned G1 MotionCLIP encoder | 542,749,069 bytes | 66a127df4958b346089b2020f2705c7456d9db0ee8b4bd9518608b708b35fc3c |
SHA256SUMS records the same checkpoint identities in a format accepted by
sha256sum --check.
PredActor_Artifacts/
|-- README.md
|-- SHA256SUMS
|-- assets/
| |-- predactor-readme-banner.svg
| |-- predactor-preview.png
| `-- institution-strip.svg
|-- checkpoints/
| |-- predactor/pdp051/latest.ckpt
| `-- motionclip/g1-model-xyz-clip/checkpoint_0100.pth.tar
`-- dataset/
`-- README.md
dataset/ is reserved for future public datasets and currently contains no
dataset payloads.
g1prdp_cond_diffuse evaluation profile.These artifacts support research reproduction and local simulation evaluation of the released PredActor controller. They are intended for use with the hash-pinned public code and configuration. The MotionCLIP checkpoint is the semantic encoder expected by the released policy and should not be substituted without revalidating compatibility.
The PredActor project page contains the method overview and simulation and hardware demonstrations. The public code repository provides the reproducible MuJoCo evaluation workflow.
PredActor is released under the MIT License. Third-party dependencies and robot assets remain subject to their respective upstream terms.
The paper citation will be added with the archival release. Until then, please reference the PredActor project page and the public repository.
13 files, 595.3 MB in total. The weights are 1 file totalling 49.2 MB in ckpt.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| checkpoints/predactor/pdp051/latest.ckpt | Weights | 49.2 MB | 2d963b32786f |
| README.md | Documentation | 6.5 KB | — |
| dataset/README.md | Documentation | 145 B | — |
| SHA256SUMS | Other | 238 B | — |
| assets/institution-strip.svg | Other | 729.4 KB | — |
| assets/predactor-icon-on-dark.svg | Other | 1.9 KB | — |
| assets/predactor-icon-on-light.svg | Other | 1.9 KB | — |
| assets/predactor-preview.png | Other | 2.6 MB | 6d9f0b631c1e |
| assets/predactor-readme-banner.svg | Other | 7.3 KB | — |
| assets/predactor-wordmark-on-dark.svg | Other | 2.9 KB | — |
| assets/predactor-wordmark-on-light.svg | Other | 2.9 KB | — |
| checkpoints/motionclip/g1-model-xyz-clip/checkpoint_0100.pth.tar | Other | 542.7 MB | 66a127df4958 |
| .gitattributes | Repository | 1.6 KB | — |
Released by Raymon Yip through its official repository on Hugging Face. Read the license.
| Precision | Weights in memory |
|---|---|
| As published | 49.2 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Yes. PredActor_Artifacts is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
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…