VLA
Learning When to See and When to Feel: Adaptive Vision-Torque Fusion for Contact-Aware Manipulation
Jiuzhou Lei et al. · 视觉-力矩自适应融合，触觉VLA可直接复用
cs.RO
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
- Causal Scene Narration with Runtime Safety Supervision for Vision-Language-Action Driving 驾驶VLA安全监督，非核心操作方向 HF-PAPER
- Learning When to See and When to Feel: Adaptive Vision-Torque Fusion for Contact-Aware Manipulation Jiuzhou Lei et al. · 视觉-力矩自适应融合，触觉VLA可直接复用 CS.RO
- AnchorVLA: Anchored Diffusion for Efficient End-to-End Mobile Manipulation Jia Syuen Lim et al. · 锚定扩散保持多动作假设，移动操作VLA CS.RO
- Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prior Haochen Niu et al. · 可行动作邻域先验提升VLA微调效率 CS.RO
- Posterior Optimization with Clipped Objective for Bridging Efficiency and Stability in Generative Policy Learning Yuhui Chen et al. · 生成策略RL微调，非直接VLA架构 CS.RO
- Cross-Modal Visuo-Tactile Object Perception Anirvan Dutta et al. · 视触感知方法，缺VLA动作生成验证 CS.RO
- AffordTissue: Dense Affordance Prediction for Tool-Action Specific Tissue Interaction Aiza Maksutova et al. · 手术VLA专用，领域过窄 CS.RO
- DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning Yang Zhou et al. · 驾驶世界动作模型，非操作VLA CS.RO
- UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving Yongkang Li et al. · 标题宏大但驾驶专用，非通用VLA [💧灌水] CS.RO
- UAV-Track VLA: Embodied Aerial Tracking via Vision-Language-Action Models Qiyao Zhang et al. · UAV跟踪VLA，应用场景过窄 CS.RO
- Pixel Motion Diffusion is What We Need for Robot Control [Ryoo] E-Ro Nguyen et al. · 像素运动扩散统一框架，语言条件控制 CS.RO
- Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learning Patrick Yin et al. · 大规模RL灵巧操作，非VLA架构 CS.RO
VLA 研究日報VLA 研究日报
共 25 篇
🔧 技術技术
VLA
AnchorVLA: Anchored Diffusion for Efficient End-to-End Mobile Manipulation
Jia Syuen Lim et al. · 锚定扩散保持多动作假设，移动操作VLA
cs.RO
閱讀原文
VLA
Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prior
Haochen Niu et al. · 可行动作邻域先验提升VLA微调效率
cs.RO
閱讀原文
VLA [Ryoo]
Pixel Motion Diffusion is What We Need for Robot Control
E-Ro Nguyen et al. · 像素运动扩散统一框架，语言条件控制
cs.RO
閱讀原文
VLA
RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks
Ruiying Li et al. · VLA长视野任务扩展，Agentic框架
cs.AI
閱讀原文
VLA
Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models
Jiawei Chen et al. · VLA对抗鲁棒性研究，填补安全空白
cs.CV
閱讀原文
📖 背景閱讀背景阅读
VLA
Causal Scene Narration with Runtime Safety Supervision for Vision-Language-Action Driving
驾驶VLA安全监督，非核心操作方向
hf-papers
閱讀原文
VLA
Posterior Optimization with Clipped Objective for Bridging Efficiency and Stability in Generative Policy Learning
Yuhui Chen et al. · 生成策略RL微调，非直接VLA架构
cs.RO
閱讀原文
VLA
Cross-Modal Visuo-Tactile Object Perception
Anirvan Dutta et al. · 视触感知方法，缺VLA动作生成验证
cs.RO
閱讀原文
VLA
AffordTissue: Dense Affordance Prediction for Tool-Action Specific Tissue Interaction
Aiza Maksutova et al. · 手术VLA专用，领域过窄
cs.RO
閱讀原文
VLA
DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning
Yang Zhou et al. · 驾驶世界动作模型，非操作VLA
cs.RO
閱讀原文
VLA
UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving
Yongkang Li et al. · 标题宏大但驾驶专用，非通用VLA [💧灌水]
cs.RO
閱讀原文
VLA
UAV-Track VLA: Embodied Aerial Tracking via Vision-Language-Action Models
Qiyao Zhang et al. · UAV跟踪VLA，应用场景过窄
cs.RO
閱讀原文
VLA
Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learning
Patrick Yin et al. · 大规模RL灵巧操作，非VLA架构
cs.RO
閱讀原文
VLA
D-SPEAR: Dual-Stream Prioritized Experience Adaptive Replay for Stable Reinforcement Learning in Robotic Manipulation
Yu Zhang et al. · RL经验回放改进，非VLA直接相关
cs.RO
閱讀原文
VLA
DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale
Sicheng Zuo et al. · 驾驶VGA模型，标题夸大贡献模糊 [💧灌水]
cs.AI
閱讀原文
VLA [HKU|Liu][SJTU|Ma]
EgoSim: Egocentric World Simulator for Embodied Interaction Generation
Jinkun Hao et al. · 第一人称世界模拟器，VLA训练数据生成
cs.AI
閱讀原文
VLA
EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents
Wenjia Wang et al. · 人体场景重建，VLA数据收集辅助
cs.CV
閱讀原文
VLA
PAM: A Pose-Appearance-Motion Engine for Sim-to-Real HOI Video Generation
Mingju Gao et al. · HOI视频生成，非直接VLA控制
cs.CV
閱讀原文
VLA
World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
世界模型验证，与JEPA-VLA方向重叠
hf-papers
閱讀原文
VLA
Safety, Security, and Cognitive Risks in World Models
Manoj Parmar · 世界模型安全综述，无具体方法
cs.RO
閱讀原文
VLA
F3DGS: Federated 3D Gaussian Splatting for Decentralized Multi-Agent World Modeling
Morui Zhu et al. · 联邦3D高斯重建，多代理非VLA核心
cs.RO
閱讀原文
VLA [Cremers]
EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation
Abhishek Saroha et al. · 第一人称6DoF运动生成，感知非控制
cs.CV
閱讀原文
VLA
Deterministic World Models for Verification of Closed-loop Vision-based Systems
Yuang Geng et al. · 世界模型验证，与Paper 21方向重叠
cs.CV
閱讀原文
VLA
Demystifying Transition Matching: When and Why It Can Beat Flow Matching
Jaihoon Kim et al. · 生成模型理论分析，非VLA直接应用
cs.CV
閱讀原文