Imagen de Portada

FLUX: Accelerating Cross-Embodiment Generative Navigation Policies via Rectified Flow and Static-to-Dynamic Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gong, Zeying, Zhong, Yangyi, Ding, Yiyi, Hu, Tianshuai, Zhao, Guoyang, Kong, Lingdong, Li, Rong, You, Jiadi, Liang, Junwei
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

Stairway to Success: An Online Floor-Aware Zero-Shot Object-Goal Navigation Framework via LLM-Driven Coarse-to-Fine Exploration
por: Gong, Zeying, et al.
Publicado: (2025)

NavThinker: Action-Conditioned World Models for Coupled Prediction and Planning in Social Navigation
por: Hu, Tianshuai, et al.
Publicado: (2026)

From Cognition to Precognition: A Future-Aware Framework for Social Navigation
por: Gong, Zeying, et al.
Publicado: (2024)

SD-OVON: A Semantics-aware Dataset and Benchmark Generation Pipeline for Open-Vocabulary Object Navigation in Dynamic Scenes
por: Qiu, Dicong, et al.
Publicado: (2025)

PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting
por: Gong, Zeying, et al.
Publicado: (2023)

3EED: Ground Everything Everywhere in 3D
por: Li, Rong, et al.
Publicado: (2025)

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding
por: Li, Rong, et al.
Publicado: (2024)

Zero-Shot 3D Visual Grounding from Vision-Language Models
por: Li, Rong, et al.
Publicado: (2025)

Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future
por: Hu, Tianshuai, et al.
Publicado: (2025)

Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras
por: Kong, Lingdong, et al.
Publicado: (2025)

CE-Nav: Flow-Guided Reinforcement Refinement for Cross-Embodiment Local Navigation
por: Yang, Kai, et al.
Publicado: (2025)

CEI: A Unified Interface for Cross-Embodiment Visuomotor Policy Learning in 3D Space
por: Wu, Tong, et al.
Publicado: (2026)

PostRainBench: A comprehensive benchmark and a new model for precipitation forecasting
por: Tang, Yujin, et al.
Publicado: (2023)

Embodiment-Agnostic Navigation Policy Trained with Visual Demonstrations
por: Curtis, Nimrod, et al.
Publicado: (2024)

Pushing the Limits of Cross-Embodiment Learning for Manipulation and Navigation
por: Yang, Jonathan, et al.
Publicado: (2024)

Visual Grounding from Event Cameras
por: Kong, Lingdong, et al.
Publicado: (2025)

SocialNav-Map: Dynamic Mapping with Human Trajectory Prediction for Zero-Shot Social Navigation
por: Zhang, Lingfeng, et al.
Publicado: (2025)

Mirage: Cross-Embodiment Zero-Shot Policy Transfer with Cross-Painting
por: Chen, Lawrence Yunliang, et al.
Publicado: (2024)

1.58-bit FLUX
por: Yang, Chenglin, et al.
Publicado: (2024)

Beyond Waypoints: Dual-Heatmap Grounding for Cross-Embodiment Semantic Navigation
por: Yun, Kaijie, et al.
Publicado: (2026)

Rectified Flow For Structure Based Drug Design
por: Zhang, Daiheng, et al.
Publicado: (2024)

AdaTracker: Learning Adaptive In-Context Policy for Cross-Embodiment Active Visual Tracking
por: Wu, Kui, et al.
Publicado: (2026)

VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation
por: Tan, Junwen, et al.
Publicado: (2026)

Shadow: Leveraging Segmentation Masks for Cross-Embodiment Policy Transfer
por: Lepert, Marion, et al.
Publicado: (2025)

Toward Embodiment Equivariant Vision-Language-Action Policy
por: Chen, Anzhe, et al.
Publicado: (2025)

FastFLUX: Pruning FLUX with Block-wise Replacement and Sandwich Training
por: Cai, Fuhan, et al.
Publicado: (2025)

FLUX: Geometry-Aware Longitudinal Flow Matching with Mixture of Experts
por: Caro, Josue Ortega, et al.
Publicado: (2026)

X-Nav: Learning End-to-End Cross-Embodiment Navigation for Mobile Robots
por: Wang, Haitong, et al.
Publicado: (2025)

Accelerating Rectified Flow Models via Trajectory-Aware Caching
por: Liu, Xiao, et al.
Publicado: (2026)

FLUX that Plays Music
por: Fei, Zhengcong, et al.
Publicado: (2024)

Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows
por: Zhang, Shujian, et al.
Publicado: (2024)

Learning Adaptive Cross-Embodiment Visuomotor Policy with Contrastive Prompt Orchestration
por: Zhang, Yuhang, et al.
Publicado: (2026)

X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations
por: Pace, Maximus A., et al.
Publicado: (2025)

Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing
por: Li, Zhiyuan, et al.
Publicado: (2026)

ReSeFlow: Rectifying SE(3)-Equivariant Policy Learning Flows
por: Wang, Zhitao, et al.
Publicado: (2025)

UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies
por: Gupta, Harsh, et al.
Publicado: (2025)

DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes
por: Bian, Hengwei, et al.
Publicado: (2024)

PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
por: Yan, Hanshu, et al.
Publicado: (2024)

GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency
por: Lu, Dongyue, et al.
Publicado: (2024)

FLUX: Data Worth Training On
por: Gowtham, et al.
Publicado: (2026)