VLA [NVIDIA]
VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agents
George Eskandar et al. · V2V转换实现策略迁移，无需新数据采集
cs.CV
閱讀原文
VLA 研究日報 Pulsar
LIVE
— AI 線今日無資料 —— AI 线今日无资料 —
VLA 線VLA 线 · cs.RO · cs.AI · cs.LG
- NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos [中科院] Yuxue Yang et al. · 4D世界模型，无明确机器人操作实验 CS.CV
- When Sensing Varies with Contexts: Context-as-Transform for Tactile Few-Shot Class-Incremental Learning [中科大] Yifeng Lin et al. · 触觉少样本分类，非VLA动作生成 CS.AI
- Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning Jai Bardhan et al. · 机器人世界模型，但VLA应用路径不明确 CS.RO
- Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models 视频世界模型记忆机制，缺机器人实验 HF-PAPER
- ArtPro: Self-Supervised Articulated Object Reconstruction with Adaptive Integration of Mobility Proposals [北大] Xuelu Li et al. · 关节物体重建，感知层非VLA策略 CS.CV
- Unified Camera Positional Encoding for Controlled Video Generation Cheng Zhang et al. · 视频生成相机控制，embodied AI提及但非核心 CS.CV
- VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agents [NVIDIA] George Eskandar et al. · V2V转换实现策略迁移，无需新数据采集 CS.CV
- Beyond Attention Magnitude: Leveraging Inter-layer Rank Consistency for Efficient Vision-Language-Action Models Peiju Liu et al. · VLA推理加速，层间秩一致性替代注意力幅度 CS.CV
- KitchenTwin: Semantically and Geometrically Grounded 3D Kitchen Digital Twins Quanyun Wu et al. · 厨房数字孪生环境，非VLA方法 CS.CV
- Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbols Xianchao Zeng et al. · VLA失败诊断与视觉符号学习框架 CS.RO
- Constant-Time Motion Planning with Manipulation Behaviors Nayesha Gandotra et al. · 传统运动规划，非VLA架构 CS.RO
- Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning Rickmer Krohn et al. · 多感官预训练，RL非VLA CS.RO
VLA 研究日報VLA 研究日报
共 24 篇
🔧 技術技术
VLA
Beyond Attention Magnitude: Leveraging Inter-layer Rank Consistency for Efficient Vision-Language-Action Models
Peiju Liu et al. · VLA推理加速，层间秩一致性替代注意力幅度
cs.CV
閱讀原文
VLA
Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbols
Xianchao Zeng et al. · VLA失败诊断与视觉符号学习框架
cs.RO
閱讀原文
VLA
LaMP: Learning Vision-Language-Action Policies with 3D Scene Flow as Latent Motion Prior
Xinkai Wang et al. · 3D场景流作为VLA潜在运动先验，新架构
cs.RO
閱讀原文
VLA
Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance
Wenxuan Song et al. · 离散扩散VLA实时加速，明确部署路径
cs.RO
閱讀原文
📖 背景閱讀背景阅读
VLA [中科院]
NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
Yuxue Yang et al. · 4D世界模型，无明确机器人操作实验
cs.CV
閱讀原文
VLA [中科大]
When Sensing Varies with Contexts: Context-as-Transform for Tactile Few-Shot Class-Incremental Learning
Yifeng Lin et al. · 触觉少样本分类，非VLA动作生成
cs.AI
閱讀原文
VLA
Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning
Jai Bardhan et al. · 机器人世界模型，但VLA应用路径不明确
cs.RO
閱讀原文
VLA
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
视频世界模型记忆机制，缺机器人实验
hf-papers
閱讀原文
VLA [北大]
ArtPro: Self-Supervised Articulated Object Reconstruction with Adaptive Integration of Mobility Proposals
Xuelu Li et al. · 关节物体重建，感知层非VLA策略
cs.CV
閱讀原文
VLA
Unified Camera Positional Encoding for Controlled Video Generation
Cheng Zhang et al. · 视频生成相机控制，embodied AI提及但非核心
cs.CV
閱讀原文
VLA
KitchenTwin: Semantically and Geometrically Grounded 3D Kitchen Digital Twins
Quanyun Wu et al. · 厨房数字孪生环境，非VLA方法
cs.CV
閱讀原文
VLA
Constant-Time Motion Planning with Manipulation Behaviors
Nayesha Gandotra et al. · 传统运动规划，非VLA架构
cs.RO
閱讀原文
VLA
Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning
Rickmer Krohn et al. · 多感官预训练，RL非VLA
cs.RO
閱讀原文
VLA
RoboMatch: A Unified Mobile-Manipulation Teleoperation Platform with Auto-Matching Network Architecture for Long-Horizon Tasks
Hanyu Liu et al. · 遥操作平台系统，非VLA方法
cs.RO
閱讀原文
VLA [Garg]
SoftMimicGen: A Data Generation System for Scalable Robot Learning in Deformable Object Manipulation
Masoud Moghani et al. · 数据生成系统，非VLA架构创新
cs.RO
閱讀原文
VLA
Towards Embodied AI with MuscleMimic: Unlocking full-body musculoskeletal motor learning at scale
Chengkun Li et al. · 肌肉骨骼运动学习，非VLA
cs.RO
閱讀原文
VLA
LILAC: Language-Conditioned Object-Centric Optical Flow for Open-Loop Trajectory Generation
Motonari Kambara et al. · 光流轨迹生成，非端到端VLA
cs.RO
閱讀原文
VLA
MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation
Yang Liu et al. · 扩散VLA但摘要缺基准实验细节 [💧灌水]
cs.RO
閱讀原文
VLA
ThermoAct:Thermal-Aware Vision-Language-Action Models for Robotic Perception and Decision-Making
Young-Chae Son et al. · 热成像VLA新模态，但实验细节不足
cs.RO
閱讀原文
VLA [π]
$\pi$, But Make It Fly: Physics-Guided Transfer of VLA Models to Aerial Manipulation
Johnathan Tucker et al. · π0迁移到空中操作，但摘要缺实验基准
cs.RO
閱讀原文
VLA
SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models
Xiyang Wu et al. · VLA安全攻击框架，非策略改进
cs.RO
閱讀原文
VLA
FODMP: Fast One-Step Diffusion of Movement Primitives Generation for Time-Dependent Robot Actions
Xirui Shi et al. · 运动原语扩散，非VLA架构
cs.RO
閱讀原文
VLA
PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos
关节物体感知，非VLA策略
hf-papers
閱讀原文