The checkpoint obtained 96.4% success (482/500) on LIBERO-Goal: 50 rollouts for each of the 10 tasks. Evaluation used 20 video denoising steps and 50 action denoising steps.

Task ID	Successes	Episodes	Success rate
0	50	50	100%
1	50	50	100%
2	38	50	76%
3	49	50	98%
4	49	50	98%
5	50	50	100%
6	50	50	100%
7	50	50	100%
8	50	50	100%
9	46	50	92%

Training

433 demonstrations, two 128×128 camera views, and 4,000 updates on 4 × H200. Full configuration and training recipe.

Loading

Download this repository and replace the base model's transformer/ directory with the transformer/ directory from this checkpoint while retaining the base model's tokenizer/, text_encoder/, and vae/.

Limitations

Evaluation covers LIBERO-Goal only. This is a multi-step LingBot-VA model, not a one-step Flash-WAM distillation.

pengyue-polaron/lingbot-va-libero-goal-step4000

LingBot-VA LIBERO-Goal — Step 4000

Evaluation

Training

Loading

Limitations

pengyue-polaron/
lingbot-va-libero-goal-step4000