Imagen de Portada

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Choi, Suhwan, Jung, Jaeyoon, Seong, Haebin, Kim, Minchan, Kim, Minyeong, Cho, Yongjun, Kim, Yoonshik, Park, Yubeen, Yu, Youngjae, Lee, Yunsung
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Computer Vision and Pattern Recognition Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CostNav: A Navigation Benchmark for Real-World Economic-Cost Evaluation of Physical AI Agents
por: Seong, Haebin, et al.
Publicado: (2025)

CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction
por: Choi, Suhwan, et al.
Publicado: (2024)

KOFFVQA: An Objectively Evaluated Free-form VQA Benchmark for Large Vision-Language Models in the Korean Language
por: Kim, Yoonshik, et al.
Publicado: (2025)

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

ESREAL: Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models
por: Kim, Minchan, et al.
Publicado: (2024)

BiC-MPPI: Goal-Pursuing, Sampling-Based Bidirectional Rollout Clustering Path Integral for Trajectory Optimization
por: Jung, Minchan, et al.
Publicado: (2024)

MuNES: Multifloor Navigation Including Elevators and Stairs
por: Jung, Donghwi, et al.
Publicado: (2024)

Temporal Action Representation Learning for Tactical Resource Control and Subsequent Maneuver Generation
por: Jung, Hoseong, et al.
Publicado: (2026)

Dynamic Policy Learning for Legged Robot with Simplified Model Pretraining and Model Homotopy Transfer
por: Kang, Dongyun, et al.
Publicado: (2025)

Multi-Modal Grounded Planning and Efficient Replanning For Learning Embodied Agents with A Few Examples
por: Kim, Taewoong, et al.
Publicado: (2024)

Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents
por: Kim, Byeonghwi, et al.
Publicado: (2023)

Action Deviation-Aware Inference for Low-Latency Wireless Robots
por: Park, Jeyoung, et al.
Publicado: (2025)

ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments
por: Kim, Taewoong, et al.
Publicado: (2024)

Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
por: Liu, Huihan, et al.
Publicado: (2026)

Explainable Adversarial-Robust Vision-Language-Action Model for Robotic Manipulation
por: Kim, Ju-Young, et al.
Publicado: (2025)

RetoVLA: Reusing Register Tokens for Spatial Reasoning in Vision-Language-Action Models
por: Koo, Jiyeon, et al.
Publicado: (2025)

Test-Time Training for Visual Foresight Vision-Language-Action Models
por: Park, Sangwu, et al.
Publicado: (2026)

Hallucination-Aware Generative Pretrained Transformer for Cooperative Aerial Mobility Control
por: Ahn, Hyojun, et al.
Publicado: (2025)

GOTPR: General Outdoor Text-based Place Recognition Using Scene Graph Retrieval with OpenStreetMap
por: Jung, Donghwi, et al.
Publicado: (2025)

VCA: Vision-Click-Action Framework for Precise Manipulation of Segmented Objects in Target Ambiguous Environments
por: Kim, Donggeon, et al.
Publicado: (2026)

Systematic Vulnerability Audit of Post-Hoc XAI under Common Corruptions: A Factor Analysis Across Vision Benchmarks
por: Kim, Minyeong
Publicado: (2026)

Systematic Vulnerability Audit of Post-Hoc XAI under Common Corruptions: A Factor Analysis Across Vision Benchmarks
por: Kim, Minyeong
Publicado: (2026)

MEM: Multi-Scale Embodied Memory for Vision Language Action Models
por: Torne, Marcel, et al.
Publicado: (2026)

No More Potentially Dynamic Objects: Static Point Cloud Map Generation based on 3D Object Detection and Ground Projection
por: Woo, Soojin, et al.
Publicado: (2024)

3D Operation of Autonomous Excavator based on Reinforcement Learning through Independent Reward for Individual Joints
por: Yoo, Yoonkyu, et al.
Publicado: (2024)

HalLoc: Token-level Localization of Hallucinations for Vision Language Models
por: Park, Eunkyu, et al.
Publicado: (2025)

Sparse Identification of Nonlinear Dynamics-based Model Predictive Control for Multirotor Collision Avoidance
por: Lee, Jayden Dongwoo, et al.
Publicado: (2024)

PHASOR: Phase-Anchored Universal Action Representations for Humanoid Embodiments
por: Kim, Kihyun, et al.
Publicado: (2026)

DM0: An Embodied-Native Vision-Language-Action Model towards Physical AI
por: Yu, En, et al.
Publicado: (2026)

Verifier-free Test-Time Sampling for Vision Language Action Models
por: Jang, Suhyeok, et al.
Publicado: (2025)

ACG: Action Coherence Guidance for Flow-based Vision-Language-Action models
por: Park, Minho, et al.
Publicado: (2025)

Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
por: Kim, Dongyoung, et al.
Publicado: (2025)

ReFeree: Radar-based efficient global descriptor using a Feature and Free space for Place Recognition
por: Choi, Byunghee, et al.
Publicado: (2024)

mmWave Radar-Based Non-Line-of-Sight Pedestrian Localization at T-Junctions Utilizing Road Layout Extraction via Camera
por: Park, Byeonggyu, et al.
Publicado: (2025)

AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models
por: Heo, Hyeongjun, et al.
Publicado: (2026)

Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents
por: Choi, Wonje, et al.
Publicado: (2024)

HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy
por: Koo, Myungkyu, et al.
Publicado: (2025)

RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AI
por: Tai, Cong, et al.
Publicado: (2025)

ReFeree: Radar-Based Lightweight and Robust Localization using Feature and Free space
por: Kim, Hogyun, et al.
Publicado: (2024)

A Humanoid Visual-Tactile-Action Dataset for Contact-Rich Manipulation
por: Kwon, Eunju, et al.
Publicado: (2025)