Copertina

TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Shirui, Harrison, Cole, Lee, Ying-Chun, Yang, Angela Jin, Ren, Zhongzheng, Ratliff, Lillian J., Duan, Jiafei, Fox, Dieter, Krishna, Ranjay
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Robotics Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

EVE: Enabling Anyone to Train Robots using Augmented Reality
di: Wang, Jun, et al.
Pubblicazione: (2024)

THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation
di: Pumacay, Wilbert, et al.
Pubblicazione: (2024)

Manipulate-Anything: Automating Real-World Robots using Vision-Language Models
di: Duan, Jiafei, et al.
Pubblicazione: (2024)

SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
di: Fang, Haoquan, et al.
Pubblicazione: (2025)

RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics
di: Yuan, Wentao, et al.
Pubblicazione: (2024)

FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action Models
di: Lin, Zijun, et al.
Pubblicazione: (2025)

VLS: Steering Pretrained Robot Policies via Vision-Language Models
di: Liu, Shuo, et al.
Pubblicazione: (2026)

Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning
di: Tur, Yalcin, et al.
Pubblicazione: (2026)

AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation
di: Duan, Jiafei, et al.
Pubblicazione: (2024)

dUltra: Ultra-Fast Diffusion Language Models via Reinforcement Learning
di: Chen, Shirui, et al.
Pubblicazione: (2025)

RefDecoder: Enhancing Visual Generation with Conditional Video Decoding
di: Fan, Xiang, et al.
Pubblicazione: (2026)

On the Limitations and Possibilities of Nash Regret Minimization in Zero-Sum Matrix Games under Noisy Feedback
di: Maiti, Arnab, et al.
Pubblicazione: (2023)

MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation
di: Deshpande, Abhay, et al.
Pubblicazione: (2026)

Selective Visual Representations Improve Convergence and Generalization for Embodied AI
di: Eftekhar, Ainaz, et al.
Pubblicazione: (2023)

RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation
di: Wang, Yi Ru, et al.
Pubblicazione: (2025)

Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents
di: Liu, Junyan, et al.
Pubblicazione: (2024)

PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation
di: Liu, Runze, et al.
Pubblicazione: (2023)

Ablate-to-Validate: Are Vision-Language Models Really Using Continuous Thought Tokens?
di: Zhang, Tianyi, et al.
Pubblicazione: (2026)

RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields
di: Sagar, Som, et al.
Pubblicazione: (2024)

Query-Efficient Algorithm to Find all Nash Equilibria in a Two-Player Zero-Sum Matrix Game
di: Maiti, Arnab, et al.
Pubblicazione: (2023)

Safe Probabilistic Planning for Human-Robot Interaction using Conformal Risk Control
di: Gonzales, Jake, et al.
Pubblicazione: (2026)

MolmoAct2: Action Reasoning Models for Real-world Deployment
di: Fang, Haoquan, et al.
Pubblicazione: (2026)

FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations
di: Hsieh, Cheng-Yu, et al.
Pubblicazione: (2025)

PEEK: Guiding and Minimal Image Representations for Zero-Shot Generalization of Robot Manipulation Policies
di: Zhang, Jesse, et al.
Pubblicazione: (2025)

Convergence of Learning Dynamics in Stackelberg Games
di: Fiez, Tanner, et al.
Pubblicazione: (2019)

Distribution-Free Guarantees for Systems with Decision-Dependent Noise
di: Zhang, Heling, et al.
Pubblicazione: (2024)

Adaptive Calibration in Non-Stationary Environments
di: Liu, Junyan, et al.
Pubblicazione: (2026)

Zero-Shot Tokenizer Transfer
di: Minixhofer, Benjamin, et al.
Pubblicazione: (2024)

When Rubrics Fail: Error Enumeration as Reward in Reference-Free RL Post-Training for Virtual Try-On
di: Ikezogwo, Wisdom, et al.
Pubblicazione: (2026)

Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning
di: Deng, Wenlong, et al.
Pubblicazione: (2025)

Sample Complexity Reduction via Policy Difference Estimation in Tabular Reinforcement Learning
di: Narang, Adhyyan, et al.
Pubblicazione: (2024)

A Learning Algorithm That Attains the Human Optimum in a Repeated Human-Machine Interaction Game
di: Isa, Jason T., et al.
Pubblicazione: (2025)

You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass
di: Yang, Yinuo, et al.
Pubblicazione: (2026)

Lycopene intake and the risk of erectile dysfunction in US adults: The National Health and Nutrition Examination Survey 2001–2004
di: Jiafei Jin
Pubblicazione: (2024)

vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models
di: Choi, Suhwan, et al.
Pubblicazione: (2026)

From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detection
di: Liu, Yixin, et al.
Pubblicazione: (2026)

Zero Shot Coordination for Sparse Reward Tasks with Diverse Reward Shapings
di: Powell, Keenan, et al.
Pubblicazione: (2026)

Dynamics of Learning under User Choice: Overspecialization and Peer-Model Probing
di: Narang, Adhyyan, et al.
Pubblicazione: (2026)

Strategically Robust Multi-Agent Reinforcement Learning with Linear Function Approximation
di: Gonzales, Jake, et al.
Pubblicazione: (2026)

Online Learning for Uninformed Markov Games: Empirical Nash-Value Regret and Non-Stationarity Adaptation
di: Liu, Junyan, et al.
Pubblicazione: (2026)