Copertina

Training-free Generation of Temporally Consistent Rewards from VLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhao, Yinuo, Yuan, Jiale, Xu, Zhiyuan, Hao, Xiaoshuai, Zhang, Xinyi, Wu, Kun, Che, Zhengping, Liu, Chi Harold, Tang, Jian
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Robotics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Efficient Training of Generalizable Visuomotor Policies via Control-Aware Augmentation
di: Zhao, Yinuo, et al.
Pubblicazione: (2024)

HACTS: a Human-As-Copilot Teleoperation System for Robot Learning
di: Xu, Zhiyuan, et al.
Pubblicazione: (2025)

ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning
di: Wu, Kun, et al.
Pubblicazione: (2024)

Real-world Reinforcement Learning from Suboptimal Interventions
di: Zhao, Yinuo, et al.
Pubblicazione: (2025)

FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency
di: Su, Yifei, et al.
Pubblicazione: (2025)

A Survey on Robotics with Foundation Models: toward Embodied AI
di: Xu, Zhiyuan, et al.
Pubblicazione: (2024)

RoboAug: One Annotation to Hundreds of Scenes via Region-Contrastive Data Augmentation for Robotic Manipulation
di: Wang, Xinhua, et al.
Pubblicazione: (2026)

SwitchVLA: Execution-Aware Task Switching for Vision-Language-Action Models
di: Li, Meng, et al.
Pubblicazione: (2025)

Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation
di: Wu, Kun, et al.
Pubblicazione: (2024)

LaST$_{0}$: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model
di: Liu, Zhuoyang, et al.
Pubblicazione: (2026)

ArtVIP: Articulated Digital Assets of Visual Realism, Modular Interaction, and Physical Fidelity for Robot Learning
di: Jin, Zhao, et al.
Pubblicazione: (2025)

CRAFT: Adapting VLA Models to Contact-rich Manipulation via Force-aware Curriculum Fine-tuning
di: Zhang, Yike, et al.
Pubblicazione: (2026)

Training-free Task-oriented Grasp Generation
di: Wang, Jiaming, et al.
Pubblicazione: (2025)

XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations
di: Fan, Shichao, et al.
Pubblicazione: (2025)

Visual Robotic Manipulation with Depth-Aware Pretraining
di: Wang, Wanying, et al.
Pubblicazione: (2024)

RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation
di: Zhang, Yixue, et al.
Pubblicazione: (2026)

Diffusion Trajectory-guided Policy for Long-horizon Robot Manipulation
di: Fan, Shichao, et al.
Pubblicazione: (2025)

MLA: A Multisensory Language-Action Model for Multimodal Understanding and Forecasting in Robotic Manipulation
di: Liu, Zhuoyang, et al.
Pubblicazione: (2025)

Grounding Robot Generalization in Training Data via Retrieval-Augmented VLMs
di: Gao, Jensen, et al.
Pubblicazione: (2026)

RoboPARA: Dual-Arm Robot Planning with Parallel Allocation and Recomposition Across Tasks
di: Duan, Shiying, et al.
Pubblicazione: (2025)

SYMBOLIZER: Symbolic Model-free Task Planning with VLMs
di: Azirar, Sami, et al.
Pubblicazione: (2026)

Discrete Policy: Learning Disentangled Action Space for Multi-Task Robotic Manipulation
di: Wu, Kun, et al.
Pubblicazione: (2024)

HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation
di: Bai, Shuanghao, et al.
Pubblicazione: (2026)

STARRY: Spatial-Temporal Action-Centric World Modeling for Robotic Manipulation
di: Tian, Yuxuan, et al.
Pubblicazione: (2026)

Language-Conditioned Robotic Manipulation with Fast and Slow Thinking
di: Zhu, Minjie, et al.
Pubblicazione: (2024)

Object-Centric Instruction Augmentation for Robotic Manipulation
di: Wen, Junjie, et al.
Pubblicazione: (2024)

RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL
di: Tang, Yinzhou, et al.
Pubblicazione: (2025)

SM$^3$: Self-Supervised Multi-task Modeling with Multi-view 2D Images for Articulated Objects
di: Wang, Haowen, et al.
Pubblicazione: (2024)

RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models
di: Wu, Hao, et al.
Pubblicazione: (2026)

Reward Training Wheels: Adaptive Auxiliary Rewards for Robotics Reinforcement Learning
di: Wang, Linji, et al.
Pubblicazione: (2025)

Robot Policy Learning with Temporal Optimal Transport Reward
di: Fu, Yuwei, et al.
Pubblicazione: (2024)

TC-IDM: Grounding Video Generation for Executable Zero-shot Robot Motion
di: Mi, Weishi, et al.
Pubblicazione: (2026)

AffordGrasp: In-Context Affordance Reasoning for Open-Vocabulary Task-Oriented Grasping in Clutter
di: Tang, Yingbo, et al.
Pubblicazione: (2025)

Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation
di: He, Jingyang, et al.
Pubblicazione: (2026)

Training People to Reward Robots
di: Sun, Endong, et al.
Pubblicazione: (2025)

Igniting VLMs toward the Embodied Space
di: Zhai, Andy, et al.
Pubblicazione: (2025)

Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models
di: Wu, Yanru, et al.
Pubblicazione: (2026)

Diffusion Meets Options: Hierarchical Generative Skill Composition for Temporally-Extended Tasks
di: Feng, Zeyu, et al.
Pubblicazione: (2024)

Volume-Consistent Kneading-Based Deformation Manufacturing for Material-Efficient Shaping
di: Li, Lei, et al.
Pubblicazione: (2025)

ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training
di: Yan, Ge, et al.
Pubblicazione: (2025)