|
Download README.md from JIAlonglong/Anchored-Path-Matching: direct link, hf CLI and curl.
- Browser
- Download file 2.68 kB
-
https://huggingface.co/JIAlonglong/Anchored-Path-Matching/resolve/main/README.md
- Command line
-
hf download hf://JIAlonglong/Anchored-Path-Matching/README.md
-
curl -L -o README.md https://huggingface.co/JIAlonglong/Anchored-Path-Matching/resolve/main/README.md
2.68 kB
| library_name: pytorch | |
| license: apache-2.0 | |
| pipeline_tag: robotics | |
| tags: | |
| - robotics | |
| - world-action-model | |
| - model-distillation | |
| - anchored-path-matching | |
| # Anchored Path Matching weights | |
| This repository stages target/EMA inference weights for [*Distilling World Action Models for Efficient Bimanual Manipulation via Anchored Path Matching*](https://huggingface.co/papers/2611.22592). | |
| Project page: https://jialonglong.github.io/Anchored-Path-Matching/ | |
| Code: https://github.com/JIAlonglong/Anchored-Path-Matching | |
| Publication status: **uploading / incomplete**. | |
| Formal APM matches the frozen teacher and student **instantaneous direction | |
| fields** at the same detached student-reached state and time. It also uses a | |
| restart endpoint anchor and anchor-priority gradient projection. | |
| ## Audited artifacts | |
| | ID | Storage | Paper status | | |
| |---|---|---| | |
| | `shared` | `bases/stage1-shared/model.safetensors` | exact | | |
| | `continued` | Stage I base + `variants/continued` | exact | | |
| | `original-no-field` | `bases/stage2-original-no-field/model.safetensors` | exact | | |
| | `original-field-projected` | Stage II base + matching adapter | exact | | |
| | `restart-no-field` | Stage II base + matching adapter | exact | | |
| | `apm` | Stage II base + matching adapter | exact | | |
| | `restart-field-no-projection` | not published | unresolved | | |
| The unresolved row is intentionally absent: no immutable EMA checkpoint in the | |
| supplied project tree matched the formal instantaneous-field, Clean-only, | |
| routed-topology predicate. A finite-local Clean/Random checkpoint was found but | |
| is classified as auxiliary, not relabeled as a paper checkpoint. | |
| Every uploaded variant was materialized with its declared base and matched | |
| against the immutable source EMA using a logical digest over tensor names, | |
| dtypes, shapes, and raw bytes. See `manifest.json`, `audit.json`, | |
| `checksums.sha256`, and `verification/`. | |
| ## Guidance contract | |
| - text-condition dropout probability: `0.1` | |
| - teacher-target video/action CFG: `5 / 1` | |
| - deployment video/action CFG: `5 / 1` | |
| - guidance mode: composed at inference | |
| - supported student budgets: `1`, `2`, and `4` steps | |
| Text-condition dropout is not a guidance scale. | |
| ## Materialization | |
| The repository is not marked complete yet. Once the matching code revision is | |
| public, install it and materialize a variant with: | |
| ```bash | |
| python tools/materialize.py \ | |
| --base bases/stage2-original-no-field/model.safetensors \ | |
| --artifact variants/apm \ | |
| --output apm-materialized | |
| ``` | |
| Only target/EMA inference tensors are included. Online weights, optimizer and | |
| scheduler states, trainer recovery state, datasets, simulator assets, and the | |
| LingBot-VA teacher are not redistributed. |