paper-with-me

Papers

IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

2024-10-17 · Xiaoyu Chen, Junliang Guo, Tianyu He, Chuheng Zhang, Pushi Zhang, Derek Cathera Yang, Li Zhao, Jiang Bian

We introduce Image-GOal Representations (IGOR), aiming to learn a unified, semantically consistent action space across human and various robots. Through this unified latent action space, IGOR enables knowledge transfer among large-scale robot and human activity data. We achieve this by compressing visual changes between an initial image and its goal state into latent actions. IGOR allows us to generate latent action labels for internet-scale video data. This unified latent action space enables the training of foundation policy and world models across a wide variety of tasks performed by both robots and humans. We demonstrate that: (1) IGOR learns a semantically consistent action space for both human and robots, characterizing various possible motions of objects representing the physical interaction knowledge; (2) IGOR can "migrate" the movements of the object in the one video to other videos, even across human and robots, by jointly using the latent action model and world model; (3) IGOR can learn to align latent actions with natural language through the foundation policy model, and integrate latent actions with a low-level policy model to achieve effective robot control. We believe IGOR opens new possibilities for human-to-robot knowledge transfer and control.

📄 PDF Abstract BibTeX arXiv:2411.00785

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer Learning

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

MambaControl: Anatomy Graph-Enhanced Mamba ControlNet with Fourier Refinement for Diffusion-Based Disease Trajectory Prediction

2025-05-15 · Hao Yang, Tao Tan, Shuai Tan, Weiqin Yang 외

Modelling disease progression in precision medicine requires capturing complex spatio-temporal dynamics while preserving anatomical integrity. Existing methods often struggle with longitudinal dependencies and structural…

AnatomyDisease PredictionMambaPrediction+2

Spatially Covariant Image Registration with Text Prompts

2023-11-27 · Xiang Chen, Min Liu, Rongguang Wang, Renjiu Hu 외

Medical images are often characterized by their structured anatomical representations and spatially inhomogeneous contrasts. Leveraging anatomical priors in neural networks can greatly enhance their utility in resource-c…

Computational EfficiencyImage RegistrationImage SegmentationSemantic Segmentation

Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation

2023-02-13 · Bingqian Lin, Yi Zhu, Xiaodan Liang, Liang Lin 외

Vision-Language Navigation (VLN) is a challenging task which requires an agent to align complex visual observations to language instructions to reach the goal position. Most existing VLN agents directly learn to align th…

Re-RankingVision-Language Navigation

Steerable Anatomical Shape Synthesis with Implicit Neural Representations

2025-04-04 · Bram de Wilde, Max T. Rietberg, Guillaume Lajoinie, Jelmer M. Wolterink

Generative modeling of anatomical structures plays a crucial role in virtual imaging trials, which allow researchers to perform studies without the costs and constraints inherent to in vivo and phantom studies. For clini…

SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models

2023-05-30 · NeurIPS 2023 11

Computer end users have spent billions of hours completing daily tasks like tabular data processing and project timeline scheduling. Most of these tasks are repetitive and error-prone, yet most end users lack the skill t…

BenchmarkingCode GenerationRobot Task PlanningScheduling+1