Image de couverture de livre

UAM: A Dual-Stream Perspective on Forgetting in VLA Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Jianke, Luo, Yuanfei, Hu, Yucheng, Chen, Xiaoyu, Guo, Yanjiang, Liu, Ziyang, Xu, Hongbin, Lan, Tian, Chen, Jianyu
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent
par: Zhang, Jianke, et autres
Publié: (2025)

VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models
par: Zhang, Jianke, et autres
Publié: (2026)

Improving Vision-Language-Action Model with Online Reinforcement Learning
par: Guo, Yanjiang, et autres
Publié: (2025)

HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers
par: Zhang, Jianke, et autres
Publié: (2024)

Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
par: Hu, Yucheng, et autres
Publié: (2024)

Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training
par: Huang, Suning, et autres
Publié: (2026)

Learn to Memorize and to Forget: A Continual Learning Perspective of Dynamic SLAM
par: Li, Baicheng, et autres
Publié: (2024)

UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving
par: Lu, Hao, et autres
Publié: (2025)

Zero-Forgetting CISS via Dual-Phase Cognitive Cascades
par: Lu, Yuquan, et autres
Publié: (2026)

The Empirical Impact of Forgetting and Transfer in Continual Visual Odometry
par: Cudrano, Paolo, et autres
Publié: (2024)

MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving
par: Huang, Yuzhou, et autres
Publié: (2026)

SAM4D: Segment Anything in Camera and LiDAR Streams
par: Xu, Jianyun, et autres
Publié: (2025)

Dual-Perspective Knowledge Enrichment for Semi-Supervised 3D Object Detection
par: Han, Yucheng, et autres
Publié: (2024)

UAM: A Unified Attention-Mamba Backbone of Multimodal Framework for Tumor Cell Classification
par: Chen, Taixi, et autres
Publié: (2025)

BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation
par: Hu, Yucheng, et autres
Publié: (2026)

ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
par: Luo, Yawen, et autres
Publié: (2026)

VLA-IAP: Training-Free Visual Token Pruning via Interaction Alignment for Vision-Language-Action Models
par: Cheng, Jintao, et autres
Publié: (2026)

VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models
par: Ranjan, Ravi, et autres
Publié: (2026)

VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration
par: Yu, Hanxun, et autres
Publié: (2026)

StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation
par: Shi, Yiran, et autres
Publié: (2026)

MAIN-VLA: Modeling Abstraction of Intention and eNvironment for Vision-Language-Action Models
par: Zhou, Zheyuan, et autres
Publié: (2026)

Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation
par: Lin, Hongbin, et autres
Publié: (2025)

Continual Learning for Remote Physiological Measurement: Minimize Forgetting and Simplify Inference
par: Liang, Qian, et autres
Publié: (2024)

HVOFusion: Incremental Mesh Reconstruction Using Hybrid Voxel Octree
par: Liu, Shaofan, et autres
Publié: (2024)

EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
par: Yang, Yantai, et autres
Publié: (2025)

Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs
par: Niu, Jiahui, et autres
Publié: (2026)

DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action
par: Fang, Zhen, et autres
Publié: (2025)

Learning Streaming Video Representation via Multitask Training
par: Yan, Yibin, et autres
Publié: (2025)

Uni-Renderer: Unifying Rendering and Inverse Rendering Via Dual Stream Diffusion
par: Chen, Zhifei, et autres
Publié: (2024)

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning
par: Tan, Zhangyun, et autres
Publié: (2026)

MambaRefine-YOLO: A Dual-Modality Small Object Detector for UAV Imagery
par: Cao, Shuyu, et autres
Publié: (2025)

Pyramid Deep Fusion Network for Two-Hand Reconstruction from RGB-D Images
par: Ren, Jinwei, et autres
Publié: (2023)

MambaMap: Online Vectorized HD Map Construction using State Space Model
par: Yang, Ruizi, et autres
Publié: (2025)

FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction
par: Chen, Fangda, et autres
Publié: (2026)

Improving SAM for Camouflaged Object Detection via Dual Stream Adapters
par: Liu, Jiaming, et autres
Publié: (2025)

LLaDA-VLA: Vision Language Diffusion Action Models
par: Wen, Yuqing, et autres
Publié: (2025)

ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving
par: Sheng, Zihao, et autres
Publié: (2026)

Dual-Adapter: Training-free Dual Adaptation for Few-shot Out-of-Distribution Detection
par: Chen, Xinyi, et autres
Publié: (2024)

Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failures
par: Luo, Yuechen, et autres
Publié: (2026)

IntentionVLA: Generalizable and Efficient Embodied Intention Reasoning for Human-Robot Interaction
par: Chen, Yandu, et autres
Publié: (2025)