Copertina

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Yilin, Tian, Ran, Swamy, Gokul, Bajcsy, Andrea
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Robotics Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

When to Act, Ask, or Learn: Uncertainty-Aware Policy Steering
di: Yuan, Jessie, et al.
Pubblicazione: (2026)

Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment
di: Tian, Ran, et al.
Pubblicazione: (2024)

AnySafe: Adapting Latent Safety Filters at Runtime via Safety Constraint Parameterization in the Latent Space
di: Agrawal, Sankalp, et al.
Pubblicazione: (2025)

Your Learned Constraint is Secretly a Backward Reachable Tube
di: Qadri, Mohamad, et al.
Pubblicazione: (2025)

Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification
di: Wu, Yilin, et al.
Pubblicazione: (2025)

Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis
di: Nakamura, Kensuke, et al.
Pubblicazione: (2025)

Position: Good Embodied Reward Models Need Bad Behavior Data
di: Tian, Ran, et al.
Pubblicazione: (2026)

StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement
di: Seo, Junwon, et al.
Pubblicazione: (2026)

Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures
di: Seo, Junwon, et al.
Pubblicazione: (2025)

Adapting by Analogy: OOD Generalization of Visuomotor Policies via Functional Correspondence
di: Gupta, Pranay, et al.
Pubblicazione: (2025)

Latent Policy Steering through One-Step Flow Policies
di: Im, Hokyun, et al.
Pubblicazione: (2026)

Steering Your Diffusion Policy with Latent Space Reinforcement Learning
di: Wagenmaker, Andrew, et al.
Pubblicazione: (2025)

From Code to Action: Hierarchical Learning of Diffusion-VLM Policies
di: Peschl, Markus, et al.
Pubblicazione: (2025)

How to Train Your Latent Control Barrier Function: Smooth Safety Filtering Under Hard-to-Model Constraints
di: Nakamura, Kensuke, et al.
Pubblicazione: (2025)

Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
di: Wang, Yiqi, et al.
Pubblicazione: (2025)

Conformalized Teleoperation: Confidently Mapping Human Inputs to High-Dimensional Robot Actions
di: Zhao, Michelle, et al.
Pubblicazione: (2024)

LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots
di: Wu, Peilin, et al.
Pubblicazione: (2024)

ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignment
di: Cai, Shaofei, et al.
Pubblicazione: (2025)

Symmetry-Aware Steering of Equivariant Diffusion Policies: Benefits and Limits
di: Park, Minwoo, et al.
Pubblicazione: (2025)

VLM as Strategist: Adaptive Generation of Safety-critical Testing Scenarios via Guided Diffusion
di: Wu, Xinzheng, et al.
Pubblicazione: (2025)

Conformal Decision Theory: Safe Autonomous Decisions from Imperfect Predictions
di: Lekeufack, Jordan, et al.
Pubblicazione: (2023)

Not All Errors Are Made Equal: A Regret Metric for Detecting System-level Trajectory Prediction Failures
di: Nakamura, Kensuke, et al.
Pubblicazione: (2024)

Uncertainty Comes for Free: Human-in-the-Loop Policies with Diffusion Models
di: He, Zhanpeng, et al.
Pubblicazione: (2025)

Enhancing Robot Navigation Policies with Task-Specific Uncertainty Managements
di: Puthumanaillam, Gokul, et al.
Pubblicazione: (2025)

Adaptive Motion Generation Using Uncertainty-Driven Foresight Prediction
di: Hiruma, Hyogo, et al.
Pubblicazione: (2024)

Learning Generalizable Visuomotor Policy through Dynamics-Alignment
di: Lee, Dohyeok, et al.
Pubblicazione: (2025)

SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment
di: Xue, Rong, et al.
Pubblicazione: (2025)

Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning
di: Wang, Yixiao, et al.
Pubblicazione: (2024)

FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance
di: Kim, Sungha, et al.
Pubblicazione: (2026)

Latent-Conditioned Policy Gradient for Multi-Objective Deep Reinforcement Learning
di: Kanazawa, Takuya, et al.
Pubblicazione: (2023)

An Real-Sim-Real (RSR) Loop Framework for Generalizable Robotic Policy Transfer with Differentiable Simulation
di: Shi, Lu, et al.
Pubblicazione: (2025)

Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance
di: Nakamoto, Mitsuhiko, et al.
Pubblicazione: (2024)

An Efficient Reachability-Based Framework for Provably Safe Autonomous Navigation in Unknown Environments
di: Bajcsy, Andrea, et al.
Pubblicazione: (2019)

From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models
di: Gumbsch, Christian, et al.
Pubblicazione: (2026)

Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback
di: Zhao, Michelle, et al.
Pubblicazione: (2024)

Adaptive Outer-Loop Control of Quadrotors via Reinforcement Learning
di: Saj, Vishnu, et al.
Pubblicazione: (2026)

Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners
di: Ng, Wen Zheng Terence, et al.
Pubblicazione: (2025)

Continual Driving Policy Optimization with Closed-Loop Individualized Curricula
di: Niu, Haoyi, et al.
Pubblicazione: (2023)

V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language Models
di: You, Junwei, et al.
Pubblicazione: (2024)

GRAPE: Generalizing Robot Policy via Preference Alignment
di: Zhang, Zijian, et al.
Pubblicazione: (2024)