How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914574411759616 |
|---|---|
| author | Kim, Bosung Wang, Ruiyi Acuna, David Jung, Jaehun Trevithick, Alexander Cui, Brandon Choi, Yejin Ammanabrolu, Prithviraj |
| author_facet | Kim, Bosung Wang, Ruiyi Acuna, David Jung, Jaehun Trevithick, Alexander Cui, Brandon Choi, Yejin Ammanabrolu, Prithviraj |
| contents | Scaling robot policy learning is bottlenecked by the cost of collecting demonstrations, while language annotations for existing demonstrations are comparatively cheap. We study language density as a lever for extracting more signal from a fixed robot or egocentric-video corpus. We introduce DeMiAn (Dense Multi-aspect Annotation), a two-stage approach that first re-labels demonstration segments with VLM-generated annotations along four complementary aspects: physical motion, scene composition, arm pose, and reasoning. A learned instructor then maps a task description and initial scene snapshot to a task-appropriate annotation at deployment, running asynchronously so generation latency is hidden behind policy execution. Across over 1M robot manipulation clips and 50K EgoVerse human-egocentric videos, DeMiAn improves both a vision-language-action policy and a video-based world-action model without collecting new demonstrations. On RoboCasa, the instructor raises success by 5 points over a task-only baseline and comes within 3 points of a per-task oracle. No fixed annotation aspect dominates across tasks, showing that selecting the right dense language matters. DeMiAn also improves composite-task and out-of-distribution performance, and shifts the compute-performance frontier in both mid-training and post-training after accounting for annotation-generation FLOPs. These results position dense re-annotation as a practical scaling lever for robot policy learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_17077 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning Kim, Bosung Wang, Ruiyi Acuna, David Jung, Jaehun Trevithick, Alexander Cui, Brandon Choi, Yejin Ammanabrolu, Prithviraj Robotics Artificial Intelligence Scaling robot policy learning is bottlenecked by the cost of collecting demonstrations, while language annotations for existing demonstrations are comparatively cheap. We study language density as a lever for extracting more signal from a fixed robot or egocentric-video corpus. We introduce DeMiAn (Dense Multi-aspect Annotation), a two-stage approach that first re-labels demonstration segments with VLM-generated annotations along four complementary aspects: physical motion, scene composition, arm pose, and reasoning. A learned instructor then maps a task description and initial scene snapshot to a task-appropriate annotation at deployment, running asynchronously so generation latency is hidden behind policy execution. Across over 1M robot manipulation clips and 50K EgoVerse human-egocentric videos, DeMiAn improves both a vision-language-action policy and a video-based world-action model without collecting new demonstrations. On RoboCasa, the instructor raises success by 5 points over a task-only baseline and comes within 3 points of a per-task oracle. No fixed annotation aspect dominates across tasks, showing that selecting the right dense language matters. DeMiAn also improves composite-task and out-of-distribution performance, and shifts the compute-performance frontier in both mid-training and post-training after accounting for annotation-generation FLOPs. These results position dense re-annotation as a practical scaling lever for robot policy learning. |
| title | How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2605.17077 |