Instructions to use QuixoteH/RoboSyn-dp-click-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use QuixoteH/RoboSyn-dp-click-ft with LeRobot:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
RoboSyn-dp-click-ft
Diffusion Policy for RoboSynChallenge click_bell, fine-tuned from the released
RoboSynChallenge/DP_sim_click_bell (rev fb8c9551) for 20k steps (lr 1e-5, bs 32) on the official
sim dataset (1000 episodes) plus 125 demonstrations we generated with the official EmbodiChain expert under
stronger domain randomization (camera pose, lighting, object/robot initial ranges). Same config and
normalization as the released checkpoint. Used by policy/robosyn_mix in https://github.com/QuixoteH/RoboSyn
(team LBWSquare, RoboSynChallenge NeurIPS 2026).
- Downloads last month
- 15