Imagen de Portada

Neural Implicit Action Fields: From Discrete Waypoints to Continuous Functions for Vision-Language-Action Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Haoyun, Zhao, Jianzhuang, Chang, Xinyuan, Shi, Tianle, Meng, Chuanzhang, Tan, Jiayuan, Xiong, Feng, Lin, Tong, Huo, Dongjie, Xu, Mu, Dong, SongLin, Ma, Zhiheng, Gong, Yihong, Zhong, Sheng
Formato:	Preprint
Publicado:	2026
Materias:	Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models
por: Tang, Zuojin, et al.
Publicado: (2026)

Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models
por: Yang, Huoren, et al.
Publicado: (2026)

ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning
por: Yang, Yandan, et al.
Publicado: (2026)

Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
por: He, Haisen, et al.
Publicado: (2026)

Trajectory-Diversity-Driven Robust Vision-and-Language Navigation
por: Li, Jiangyang, et al.
Publicado: (2026)

Unleashing the Potential of All Test Samples: Mean-Shift Guided Test-Time Adaptation
por: Han, Jizhou, et al.
Publicado: (2025)

ReMoT: Reinforcement Learning with Motion Contrast Triplets
por: Wan, Cong, et al.
Publicado: (2026)

VDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-Reflection
por: Wang, Qiang, et al.
Publicado: (2025)

ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment
por: Chen, Yuzhi, et al.
Publicado: (2026)

GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery
por: Han, Jizhou, et al.
Publicado: (2026)

Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation
por: Xiao, Junjin, et al.
Publicado: (2026)

Seeing Space and Motion: Enhancing Latent Actions with Geometric and Dynamic Awareness for Vision-Language-Action Models
por: Cai, Zhejia, et al.
Publicado: (2025)

Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding
por: Lin, Tao, et al.
Publicado: (2025)

ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models
por: Yang, Cheng, et al.
Publicado: (2026)

Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
por: Liang, Zhixuan, et al.
Publicado: (2025)

Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery
por: Han, Jizhou, et al.
Publicado: (2025)

ABot-Claw: A Foundation for Persistent, Cooperative, and Self-Evolving Robotic Agents
por: Huo, Dongjie, et al.
Publicado: (2026)

Continually Evolving Skill Knowledge in Vision Language Action Model
por: Wu, Yuxuan, et al.
Publicado: (2025)

Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs
por: Zhao, Jianchao, et al.
Publicado: (2026)

RotVLA: Rotational Latent Action for Vision-Language-Action Model
por: Li, Qiwei, et al.
Publicado: (2026)

World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems
por: Li, Runze, et al.
Publicado: (2026)

Implicit Action Chunking for Smooth Continuous Control
por: Liang, Bosun, et al.
Publicado: (2026)

ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models
por: Zhong, Linqing, et al.
Publicado: (2026)

DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype
por: Wang, Qiang, et al.
Publicado: (2025)

Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery
por: Han, Jizhou, et al.
Publicado: (2026)

CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning
por: Huang, Dongchi, et al.
Publicado: (2025)

Addressing the Waypoint-Action Gap in End-to-End Autonomous Driving via Vehicle Motion Models
por: Rodríguez-Vidal, Jorge Daniel, et al.
Publicado: (2026)

Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning
por: Gao, Xinyuan, et al.
Publicado: (2024)

Action-Driven Processes for Continuous-Time Control
por: He, Ruimin, et al.
Publicado: (2025)

Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
por: Yang, Zemin, et al.
Publicado: (2026)

Continuous Reasoning for Vision-Language-Action
por: Wu, Yueh-Hua, et al.
Publicado: (2026)

Beyond Distributions: Geometric Action Control for Continuous Reinforcement Learning
por: Lin, Zhihao
Publicado: (2025)

ReViP: Mitigating False Completion in Vision-Language-Action Models with Vision-Proprioception Rebalance
por: Li, Zhuohao, et al.
Publicado: (2026)

Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation
por: Lin, Bingqian, et al.
Publicado: (2023)

CEAT: Continual Expansion and Absorption Transformer for Non-Exemplar Class-Incremental Learning
por: Gao, Xinyuan, et al.
Publicado: (2024)

SWAG: Storytelling With Action Guidance
por: Patel, Zeeshan, et al.
Publicado: (2024)

PlantoGraphy: Incorporating Iterative Design Process into Generative Artificial Intelligence for Landscape Rendering
por: Huang, Rong, et al.
Publicado: (2024)

Harnessing Temporal Causality for Advanced Temporal Action Detection
por: Liu, Shuming, et al.
Publicado: (2024)

A Survey on Vision-Language-Action Models for Autonomous Driving
por: Jiang, Sicong, et al.
Publicado: (2025)

Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming
por: Tong, Baoshun, et al.
Publicado: (2026)