Vision-language-action models
Technique · World Models & Robotics · 2 items since Jul 2026
Models that map camera images and instructions directly to robot actions.
Related
- Organizations
Trends
Items
- Aug 28
CMU's R³ teaches robots to reason in language
A post-training recipe mid-trains off-the-shelf VLMs on reasoning traces, then applies single-step, rubric-based RL from offline action data, using free-form language as test-time compute to steer low-level manipulation and improve exploration and generalization.
- Jul 25
TurboVLA runs robot policies on a consumer GPU
Mapping vision and language directly to action, skipping the LLM-centric language pathway, reaches 97.7% average success on LIBERO with 0.2B parameters, 31.2 ms latency, and 0.9 GB of VRAM on an RTX 4090.