Image de couverture de livre

Boosting Action-Information via a Variational Bottleneck on Unlabelled Robot Videos

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Haoyu, Cheng, Long
Format:	Preprint
Publié:	2025
Sujets:	Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow
par: Chen, Yixiang, et autres
Publié: (2025)

Extracting Visual Plans from Unlabeled Videos via Symbolic Guidance
par: Yang, Wenyan, et autres
Publié: (2025)

Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning
par: Yu, Dongjie, et autres
Publié: (2026)

CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations
par: Liang, Anthony, et autres
Publié: (2025)

Information Filtering via Variational Regularization for Robot Manipulation
par: Zhang, Jinhao, et autres
Publié: (2026)

BridgeACT: Bridging Human Demonstrations to Robot Actions via Unified Tool-Target Affordances
par: Han, Yifan, et autres
Publié: (2026)

Walk Like Dogs: Learning Steerable Imitation Controllers for Legged Robots from Unlabeled Motion Data
par: Kang, Dongho, et autres
Publié: (2025)

Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulation
par: Tan, Huajie, et autres
Publié: (2026)

Human2Robot: Learning Robot Actions from Paired Human-Robot Videos
par: Xie, Sicheng, et autres
Publié: (2025)

Enhancing Reusability of Learned Skills for Robot Manipulation via Gaze Information and Motion Bottlenecks
par: Takizawa, Ryo, et autres
Publié: (2025)

Automated Action Generation based on Action Field for Robotic Garment Smoothing and Alignment
par: Cheng, Hu, et autres
Publié: (2025)

Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prior
par: Niu, Haochen, et autres
Publié: (2026)

Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation
par: Bai, Shuanghao, et autres
Publié: (2025)

ManipDreamer: Boosting Robotic Manipulation World Model with Action Tree and Visual Guidance
par: Li, Ying, et autres
Publié: (2025)

Learning a Stable Dynamic System with a Lyapunov Energy Function for Demonstratives Using Neural Networks
par: Zhang, Yu, et autres
Publié: (2023)

Unlabeled Multi-Robot Motion Planning with Improved Separation Trade-offs
par: Farhana, Tsuri, et autres
Publié: (2026)

OmniVTLA: Vision-Tactile-Language-Action Model with Semantic-Aligned Tactile Sensing
par: Cheng, Zhengxue, et autres
Publié: (2025)

Remote Life Support Robot Interface System for Global Task Planning and Local Action Expansion Using Foundation Models
par: Obinata, Yoshiki, et autres
Publié: (2024)

Precise Action-to-Video Generation Through Visual Action Prompts
par: Wang, Yuang, et autres
Publié: (2025)

EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards
par: Wang, Ruixiang, et autres
Publié: (2026)

Stabilizing Dynamic Systems through Neural Network Learning: A Robust Approach
par: Zhang, Yu, et autres
Publié: (2024)

Learning Variable Impedance Skills from Demonstrations with Passivity Guarantee
par: Zhang, Yu, et autres
Publié: (2023)

DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control
par: Ma, Teli, et autres
Publié: (2026)

ConLA: Contrastive Latent Action Learning from Human Videos for Robotic Manipulation
par: Dai, Weisheng, et autres
Publié: (2026)

$τ_0$-WM: A Unified Video-Action World Model for Robotic Manipulation
par: Zhou, Pengfei, et autres
Publié: (2026)

Enhanced Prediction of Multi-Agent Trajectories via Control Inference and State-Space Dynamics
par: Zhang, Yu, et autres
Publié: (2024)

See, Learn, Assist: Safe and Self-Paced Robotic Rehabilitation via Video-Based Learning from Demonstration
par: Alabbas, Ali, et autres
Publié: (2026)

PoseDiff: A Unified Diffusion Model Bridging Robot Pose Estimation and Video-to-Action Control
par: Zhang, Haozhuo, et autres
Publié: (2025)

Action Images: End-to-End Policy Learning via Multiview Video Generation
par: Zhen, Haoyu, et autres
Publié: (2026)

Graph Neural Planning and Predictive Control for Multi-Robot Communication-Constrained Unlabeled Motion Planning
par: Goarin, Manohari, et autres
Publié: (2026)

ViSA-Flow: Accelerating Robot Skill Learning via Large-Scale Video Semantic Action Flow
par: Chen, Changhe, et autres
Publié: (2025)

CLASS: Contrastive Learning via Action Sequence Supervision for Robot Manipulation
par: Lee, Sung-Wook, et autres
Publié: (2025)

Learning Long-Horizon Robot Manipulation Skills via Privileged Action
par: Mao, Xiaofeng, et autres
Publié: (2025)

Interactive Robot-Environment Self-Calibration via Compliant Exploratory Actions
par: Chanrungmaneekul, Podshara, et autres
Publié: (2024)

ActionReasoning: Robot Action Reasoning in 3D Space with LLM for Robotic Brick Stacking
par: Wang, Guangming, et autres
Publié: (2026)

JailWAM: Jailbreaking World Action Models in Robot Control
par: Liu, Hanqing, et autres
Publié: (2026)

BLURR: A Boosted Low-Resource Inference for Vision-Language-Action Models
par: Ma, Xiaoyu, et autres
Publié: (2025)

VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model
par: Wang, Beichen, et autres
Publié: (2024)

Gradient-based Regularization for Action Smoothness in Robotic Control with Reinforcement Learning
par: Lee, I, et autres
Publié: (2024)

Instruct2Act: From Human Instruction to Actions Sequencing and Execution via Robot Action Network for Robotic Manipulation
par: Sharma, Archit, et autres
Publié: (2026)