10 Open Challenges Steering the Future of Vision-Language-Action Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915606257729536 |
|---|---|
| author | Poria, Soujanya Majumder, Navonil Hung, Chia-Yu Bagherzadeh, Amir Ali Li, Chuan Kwok, Kenneth Wang, Ziwei Tan, Cheston Wu, Jiajun Hsu, David |
| author_facet | Poria, Soujanya Majumder, Navonil Hung, Chia-Yu Bagherzadeh, Amir Ali Li, Chuan Kwok, Kenneth Wang, Ziwei Tan, Cheston Wu, Jiajun Hsu, David |
| contents | Due to their ability of follow natural language instructions, vision-language-action (VLA) models are increasingly prevalent in the embodied AI arena, following the widespread success of their precursors -- LLMs and VLMs. In this paper, we discuss 10 principal milestones in the ongoing development of VLA models -- multimodality, reasoning, data, evaluation, cross-robot action generalization, efficiency, whole-body coordination, safety, agents, and coordination with humans. Furthermore, we discuss the emerging trends of using spatial understanding, modeling world dynamics, post training, and data synthesis -- all aiming to reach these milestones. Through these discussions, we hope to bring attention to the research avenues that may accelerate the development of VLA models into wider acceptability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_05936 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | 10 Open Challenges Steering the Future of Vision-Language-Action Models Poria, Soujanya Majumder, Navonil Hung, Chia-Yu Bagherzadeh, Amir Ali Li, Chuan Kwok, Kenneth Wang, Ziwei Tan, Cheston Wu, Jiajun Hsu, David Robotics Artificial Intelligence Due to their ability of follow natural language instructions, vision-language-action (VLA) models are increasingly prevalent in the embodied AI arena, following the widespread success of their precursors -- LLMs and VLMs. In this paper, we discuss 10 principal milestones in the ongoing development of VLA models -- multimodality, reasoning, data, evaluation, cross-robot action generalization, efficiency, whole-body coordination, safety, agents, and coordination with humans. Furthermore, we discuss the emerging trends of using spatial understanding, modeling world dynamics, post training, and data synthesis -- all aiming to reach these milestones. Through these discussions, we hope to bring attention to the research avenues that may accelerate the development of VLA models into wider acceptability. |
| title | 10 Open Challenges Steering the Future of Vision-Language-Action Models |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2511.05936 |