UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912915339083776 |
|---|---|
| author | Yang, Jiabing Chen, Yixiang Xu, Yuan Li, Peiyan Wu, Xiangnan Wen, Zichen Fang, Bowen Yu, Tao Zhang, Zhengbo Li, Yingda Wang, Kai Liu, Jing Liu, Nianfeng Huang, Yan Wang, Liang |
| author_facet | Yang, Jiabing Chen, Yixiang Xu, Yuan Li, Peiyan Wu, Xiangnan Wen, Zichen Fang, Bowen Yu, Tao Zhang, Zhengbo Li, Yingda Wang, Kai Liu, Jing Liu, Nianfeng Huang, Yan Wang, Liang |
| contents | Vision-Language-Action (VLA) models leverage pretrained Vision-Language Models (VLMs) as backbones to map images and instructions to actions, demonstrating remarkable potential for generalizable robotic manipulation. To enhance performance, existing methods often incorporate extra observation cues (e.g., depth maps, point clouds) or auxiliary modules (e.g., object detectors, encoders) to enable more precise and reliable task execution, yet these typically require costly data collection and additional training. Inspired by the finding that Feed-Forward Network (FFN) in language models can act as "key-value memory", we propose Uncertainty-aware Observation Reinjection (UAOR), an effective, training-free and plug-and-play module for VLA models. Specifically, when the current language model layer exhibits high uncertainty, measured by Action Entropy, it reinjects key observation information into the next layer's Feed-Forward Network (FFN) through attention retrieval. This mechanism helps VLAs better attend to observations during inference, enabling more confident and faithful action generation. Comprehensive experiments show that our method consistently improves diverse VLA models across simulation and real-world tasks with minimal overhead. Notably, UAOR eliminates the need for additional observation cues or modules, making it a versatile and practical plug-in for existing VLA pipelines. The project page is at https://uaor.jiabingyang.cn. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18020 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models Yang, Jiabing Chen, Yixiang Xu, Yuan Li, Peiyan Wu, Xiangnan Wen, Zichen Fang, Bowen Yu, Tao Zhang, Zhengbo Li, Yingda Wang, Kai Liu, Jing Liu, Nianfeng Huang, Yan Wang, Liang Computer Vision and Pattern Recognition Robotics Vision-Language-Action (VLA) models leverage pretrained Vision-Language Models (VLMs) as backbones to map images and instructions to actions, demonstrating remarkable potential for generalizable robotic manipulation. To enhance performance, existing methods often incorporate extra observation cues (e.g., depth maps, point clouds) or auxiliary modules (e.g., object detectors, encoders) to enable more precise and reliable task execution, yet these typically require costly data collection and additional training. Inspired by the finding that Feed-Forward Network (FFN) in language models can act as "key-value memory", we propose Uncertainty-aware Observation Reinjection (UAOR), an effective, training-free and plug-and-play module for VLA models. Specifically, when the current language model layer exhibits high uncertainty, measured by Action Entropy, it reinjects key observation information into the next layer's Feed-Forward Network (FFN) through attention retrieval. This mechanism helps VLAs better attend to observations during inference, enabling more confident and faithful action generation. Comprehensive experiments show that our method consistently improves diverse VLA models across simulation and real-world tasks with minimal overhead. Notably, UAOR eliminates the need for additional observation cues or modules, making it a versatile and practical plug-in for existing VLA pipelines. The project page is at https://uaor.jiabingyang.cn. |
| title | UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2602.18020 |