paper
Visual Verification Enables Inference-time Steering and Autonomous Policy Improvement
paperactiveprovisional
visual-verification-enables-inference-time-steering-and-autonomous-policy-improvement-d8a47cce·1 events·first seen 8h agoAliases: Visual Verification Enables Inference-time Steering and Autonomous Policy Improvement
Co-occurring entities
More like this (12)
Predicting Future Behaviors in Reasoning Models Enables Better SteeringAgentic Chain-of-Thought Steering for Efficient and Controllable LLM ReasoningTempoVLA: Learning Speed-Controllable Vision-Language-Action PoliciesState-Conditioned Dynamic SteeringSelf-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV NavigationWhere Does the Answer Come From? Benchmarking View-Level Visual Evidence Identification in Multi-View MLLMs for Autonomous DrivingLearning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber AgentsActivation SteeringAgentic Chain-of-Thought SteeringPlanning-aligned Token Compression for Long-Context Autonomous DrivingRe-imagining ISO 26262 in the Age of Autonomous Vehicles: Enhancing Controllability through Transferability and Predictabilityrepresentation-level steering
Recent events (1)
VERITAS: Visual verification enables inference-time steering and autonomous improvement for robot policies
Researchers introduce VERITAS, a generator-verifier framework pairing a pre-trained generalist robot policy with a gradient-free visual verifier to steer actions at inference time without additional training. Verified rollouts are also used for offline self-improvement via fine-tuning, achieving performance gains comparable to expert demonstrations but without human intervention. The work demonstrates that inference-time verification is a scalable mechanism for autonomous policy improvement during deployment.