Xun49/Event-aligned-domino-clean1

Event-Aligned — DOMINO

Event-Aligned model for DOMINO manipulation, built on pretrained LingBot-VA base.

Code | Models | Project page

Event-aligned visual-action sampling (left) and DOMINO success rates under a matched training sequence budget (right).

Method

• Event-aligned supervision: preserve dense interaction evidence and sample transitions more sparsely, keeping training chunks within event boundaries.
• Execution validity prediction: identify valid action slots and skip redundant actions introduced by repeated-frame padding.

Inference uses observations and a task instruction. No event annotations are required during inference.

Download

Download the DOMINO model from the model collection:

python -m pip install -U huggingface_hub
hf download Xun49/Event-aligned-domino-clean1 --local-dir ./model/event-aligned_domino_clean1

Download the complete repository, including transformer/, vae/, text_encoder/, and tokenizer/. See the code repository for setup, inference, and evaluation.

Results

Method	DOMINO success rate (%)	Manipulation score
LingBot-VA baseline	32.57	45.55
Event-Aligned	42.83	55.92

Evaluation covers 35 DOMINO tasks, clean Level 1, Aloha-AgileX embodiment, motion coefficient 0.1, and 100 episodes per task.

License and attribution

The model weights are released under the Apache License 2.0.

Built on the Robbyant Team's LingBot-VA. The companion code is also Apache-2.0 licensed. Retain applicable upstream licenses and attribution. Please also credit Causal World Modeling for Robot Control.

Citation

@misc{yang2026eventaligned,
  title         = {Event-Aligned Visual Action Reasoning for World Action Models},
  author        = {Yang, Xiaomeng and Wu, Yushu and Gao, Yi and Lei, Yuhao and Zhang, Xuan and Zhao, Pu and Wang, Yanzhi},
  year          = {2026},
  eprint        = {2610.09427},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CV},
  url           = {https://arxiv.org/abs/2610.09427}
}