VLA
Visual Language Action models—AI systems using LLM technology to process visual input and language to produce robot control actions, combining vision, language, and action in a single architecture.
As defined in Yann LeCun Says LLMs Have 2 Years Left…
Where it comes up · 3
- Yann LeCun Says LLMs Have 2 Years Left…1 claim
- Dylan Patel - The Infinite Demand for Tokens, Claude Mythos, and Supply Constraints - [Invest Like the Best, EP.469]1 claim
- Yann LeCun's $1B Bet Against LLMs [Part 1]1 claim
Most important claims · 3 of 3Search all claims for “VLA” →
- Visual Language Action (VLA) models—systems using LLM technology to produce robot control actions from vision and language input—are now seen as a failure because they are not reliable enough and require too much training data.Yann LeCun Says LLMs Have 2 Years Left…
- Vision-language-action robot models are inefficient in data and cannot scale their data fast enough, so they are unlikely to be the approach that ultimately scales, and few-shot learning breakthroughs in robotics could come within six to 18 months.Dylan Patel - The Infinite Demand for Tokens, Claude Mythos, and Supply Constraints - [Invest Like the Best, EP.469]
- In part two of the video series, the creators will explore V-JEPA-2 implementations to see exactly how these models stack up against LLM-driven approaches.Yann LeCun's $1B Bet Against LLMs [Part 1]