paper
TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies
paperactiveprovisional
tempovla-learning-speed-controllable-vision-language-action-policies-3e885955·1 events·first seen 12d agoAliases: TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies
Co-occurring entities
More like this (12)
LabVLA: Grounding Vision-Language-Action Models in Scientific LaboratoriesVision-Language-Action modelVision-Language-Action modelsTempoVLAModeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Modelsvisual language modelVisual Verification Enables Inference-time Steering and Autonomous Policy ImprovementGeometric Action Model for Robot Policy LearningVision-Language ModelsCHORUS: Decentralized Multi-Embodiment Collaboration with One VLA PolicyLearning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber AgentsReroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models
Recent events (1)
TempoVLA: Speed-Controllable Vision-Language-Action Policy for Robot Manipulation
Researchers introduce TempoVLA, a Vision-Language-Action model that enables explicit speed control during robot manipulation by conditioning on a speed signal rather than inheriting a fixed speed from training data. The system pairs Variable-Speed Trajectory Augmentation (VSTA), which re-times demonstrations by merging or splitting actions, with a model-side conditioning mechanism. Experiments in simulation and real-world tasks show flexible bidirectional speed control, with dynamic adaptation—accelerating in low-risk transit phases and decelerating for high-risk contact stages—achieved by coupling with a large multimodal model.