LADA: latent actions imitate language from few observation-language pairs
abursuc · x · 2026-09-17
At the #ssad2026 workshop, the author introduces LADA (Latent Action Driving Annotations), a low-cost strategy that imitates the function of language from only a few observation-language pairs by learning to produce latent actions. The author offers an intuition for why it works: it breaks a difficult problem into two simpler ones. Details are in the linked material.
More from Embodied
- GPT-Policy: In-Context Robot Learning with VLM Agents, No Gradient Updates — Dongzhou Cheng · 2026-09-17
- World Labs' Atlas Scans by Generative Guessing; NeRF Creator Admits Productization Is Hard — cen6wkf · 2026-09-17
- CXMT's LPDDR5X lands in flagship phone as Nubia ships $885 Doubao AI handset — pstAsiatech · 2026-09-17
- Key open challenges for VLAs: language, evaluation, deployment, causal reasoning — abursuc · 2026-09-17
- A Primer on Latent Action Models From the #ssad2026 Talks — abursuc · 2026-09-17
- FIVE-VLA Runs Driving With Just 640M Parameters, 7.5x More Efficient Than SimLingo — abursuc · 2026-09-17