Image de couverture de livre

$π$-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Siting, Wang, Xiaofeng, Zhu, Zheng, Pei, Minnan, Cui, Xinyu, Deng, Cheng, Zhao, Jian, Huang, Guan, Zhang, Haifeng, Wang, Jun
Format:	Preprint
Publié:	2026
Sujets:	Robotics Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SpatialViz-Bench: A Cognitively-Grounded Benchmark for Diagnosing Spatial Visualization in MLLMs
par: Wang, Siting, et autres
Publié: (2025)

Shallow-π: Knowledge Distillation for Flow-based VLAs
par: Jeon, Boseong, et autres
Publié: (2026)

SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation
par: Luan, Wuyang, et autres
Publié: (2026)

Finer Parameter Steps for Low-Rank PEFT: A Controlled Study with CP Tensor Adapters
par: Wang, Xinjue, et autres
Publié: (2026)

$π_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
par: Chen, Kang, et autres
Publié: (2025)

Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?
par: Yan, Renye, et autres
Publié: (2026)

Preconditioned One-Step Generative Modeling for Bayesian Inverse Problems in Function Spaces
par: Cheng, Zilan, et autres
Publié: (2026)

DiffusionNFT: Online Diffusion Reinforcement with Forward Process
par: Zheng, Kaiwen, et autres
Publié: (2025)

Unconditionally Long-Time Stable Variable-Step Second-Order Exponential Time-Differencing Schemes for the Incompressible NSE
par: Wang, Haifeng, et autres
Publié: (2026)

Activating Wider Areas in Image Super-Resolution
par: Cheng, Cheng, et autres
Publié: (2024)

Reasoning Fails Where Step Flow Breaks
par: Xu, Xiaoyu, et autres
Publié: (2026)

One-Step Bellman Alignment Enables Provably Efficient Transfer in Online RL
par: Chen, Elynn, et autres
Publié: (2026)

Training-free Online Video Step Grounding
par: Zanella, Luca, et autres
Publié: (2025)

FASTER: Rethinking Real-Time Flow VLAs
par: Lu, Yuxiang, et autres
Publié: (2026)

Step Automata
par: Wang, Yong
Publié: (2026)

Read Before You Think: Mitigating LLM Comprehension Failures with Step-by-Step Reading
par: Han, Feijiang, et autres
Publié: (2025)

Step by Step Network
par: Han, Dongchen, et autres
Publié: (2025)

One-Step Flow Policy Mirror Descent
par: Chen, Tianyi, et autres
Publié: (2025)

Finer-Grained Hardness of Kernel Density Estimation
par: Alman, Josh, et autres
Publié: (2024)

Running VLAs at Real-time Speed
par: Ma, Yunchao, et autres
Publié: (2025)

FaithRL: Learning to Reason Faithfully through Step-Level Faithfulness Maximization
par: Gui, Runquan, et autres
Publié: (2026)

One Step Is Enough: Dispersive MeanFlow Policy Optimization
par: Zou, Guowei, et autres
Publié: (2026)

COMET: NFT Price Prediction with Wallet Profiling
par: Wang, Tianfu, et autres
Publié: (2024)

SLEA-RL: Step-Level Experience Augmented Reinforcement Learning for Multi-Turn Agentic Training
par: Wang, Prince Zizhuang, et autres
Publié: (2026)

Reinforcing VLAs in Task-Agnostic World Models
par: Wang, Yucen, et autres
Publié: (2026)

DSFlow: Dual Supervision and Step-Aware Architecture for One-Step Flow Matching Speech Synthesis
par: Lin, Bin, et autres
Publié: (2026)

WFR-MFM: One-Step Inference for Dynamic Unbalanced Optimal Transport
par: Wang, Xinyu, et autres
Publié: (2026)

Counted NFT Transfers
par: Wang, Qin, et autres
Publié: (2026)

Letter to the Editor: Caution Needed in Interpreting Step‐to‐Step Transitions in Stroke Rehabilitation
par: Mario Núñez‐Lisboa, et autres
Publié: (2025)

cVLA: Towards Efficient Camera-Space VLAs
par: Argus, Max, et autres
Publié: (2025)

Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation
par: Liu, Yong, et autres
Publié: (2025)

Controllable Flow Matching for Online Reinforcement Learning
par: Wang, Bin, et autres
Publié: (2025)

FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models
par: Zhang, Yang, et autres
Publié: (2024)

StepTool: Enhancing Multi-Step Tool Usage in LLMs via Step-Grained Reinforcement Learning
par: Yu, Yuanqing, et autres
Publié: (2024)

STEVE Series: Step-by-Step Construction of Agent Systems in Minecraft
par: Zhao, Zhonghan, et autres
Publié: (2024)

StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
par: Wang, Daoyu, et autres
Publié: (2026)

MFSR: MeanFlow Distillation for One Step Real-World Image Super Resolution
par: Wang, Ruiqing, et autres
Publié: (2026)

Teen Spaces: The Step-by-Step Library Makeover, Second Edition
par: Bolan, Kimberly
Publié: (2008)

EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation
par: Tan, Xiaofeng, et autres
Publié: (2026)

Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step
par: Wang, Zezhong, et autres
Publié: (2024)