OpenVLA: An Open-Source Vision-Language-Action Model · HackerPapers discussions

OpenVLA: An Open-Source Vision-Language-Action Model — mentioned by intalentive

Wed, 12 Mar 2025 17:00:37 GMT

https://arxiv.org/abs/2406.09246

Paper and discussion history. A mention is not an endorsement.

OpenVLA: An Open-Source Vision-Language-Action Model — mentioned by m_ke

Wed, 01 Jan 2025 12:24:36 GMT

VLA - Vision Language Action models https://arxiv.org/abs/2406.09246 It turns out you can take a vision language foundational model that has a broad understanding of visual and textual knowledge and fine tune it to output robot actions given a sequence of images and previous actions. This approach beats all previous methods by a wide margin and transfers across tasks.

Paper and discussion history. A mention is not an endorsement.

OpenVLA: An Open-Source Vision-Language-Action Model — mentioned by chillel

Wed, 27 Nov 2024 04:57:46 GMT

just coming back to this thread, this paper is quite a good read: https://arxiv.org/html/2406.09246v3#S3 and as a follow-on, this blog post by Physical Intelligence was interesting: https://www.physicalintelligence.company/blog/pi0

Paper and discussion history. A mention is not an endorsement.

OpenVLA: An Open-Source Vision-Language-Action Model — HN submission

Tue, 06 Aug 2024 16:25:24 GMT

OpenVLA: An Open-Source Vision-Language-Action Model

Discussing the performance of OpenVLA (https://arxiv.org/pdf/2406.09246). Has anyone gotten this to work for in domain or out of domain robots?

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.