@svlevine: If you want a robot to do something well, you need to know how to talk to it. If you don't, you can learn, with Semanti…
Summary
This paper presents Semantic Action RL, which uses reinforcement learning over Vision-Language-Action (VLA) prompts to enable robots to learn new tasks quickly in the real world.
View Cached Full Text
Cached at: 07/03/26, 06:39 PM
If you want a robot to do something well, you need to know how to talk to it. If you don’t, you can learn, with Semantic Action RL! In our paper, @JagdeepBhatia8, @ajwagenmaker, @verityw_ show how RL over VLA prompts enables new tasks and learns blazing fast in the real world! https://t.co/McHnRxCTQ4
Similar Articles
RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models
RoboSemanticBench is a benchmark that diagnoses semantic grounding in action prediction for vision-language-action models, revealing that while robots can grasp objects, they fail to select semantically correct targets based on instruction semantics.
AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models
Proposes AR-VLA, an autoregressive action expert that generates continuous action sequences with long-term memory for context-aware robotic policy training, improving trajectory smoothness and task success rates over reactive VLA models.
InSight: Self-Guided Skill Acquisition via Steerable VLAs
InSight presents a framework for autonomous skill acquisition in vision-language-action (VLA) models by enabling steerability at the primitive-action level and using a VLM-guided data flywheel to generate demonstrations, achieving manipulation tasks like block flipping and pouring without human demonstrations.
Robots Need More than VLA and World Models
This position paper argues that advancing robot intelligence requires integrating unstructured behavioral data through specialized interfaces for labeling, embodiment mapping, world modeling, and reward inference, rather than relying solely on scaling Vision-Language-Action (VLA) models and world models.
IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation
IntentVLA is a history-conditioned visual-language-action framework that improves robot imitation learning stability by encoding short-horizon intents from visual observations, addressing challenges from partial observability and ambiguous observations. It also introduces AliasBench, an ambiguity-aware benchmark for evaluating such methods.