Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 8 of 8 for “"Domain Gaps"”.

  1. Learning Sim-to-Real Robot Parkour from RGB Images

    … challenges in sim-to-real transfer due to large domain gaps. This work proposes a novel approach for training an RGB parkour policy and demonstrates that it achieves performance comparable to depth-based approaches in simulation. Furthermore, we successfully deploy and evaluate our RGB policy on …

    mit Repository record for Learning Sim-to-Real Robot Parkour from RGB Images (opens in a new tab)

  2. Low-cost Agents with Language Perception and Dynamic Inference

    … data but also serves as a bridge to minimize domain gaps between different environments. However, transformer-based agents are burdened with high inference costs, especially when handling long-horizon visual content. To mitigate this, we introduce two strategies: (1) reducing visual input …

    mit Repository record for Low-cost Agents with Language Perception and Dynamic Inference (opens in a new tab)

  3. Opportunities for System Dynamics Research in Operations Management for Public Policy

    … identify several overarching methodological and domain gaps for future research. Finally, we propose a process for using system dynamics with traditional operations management methodologies.

    mit Repository record for Opportunities for System Dynamics Research in Operations Management for Public Policy (opens in a new tab)

  4. Essays in System Dynamics for Operations Management: Policy, Platforms and Pricing

    … identify several overarching methodological and domain gaps for future research. Finally, we propose a process for using SD with traditional OM methodologies. Chapter 2 is joint work with Geoffrey Parker and Edward Anderson. We develop the Value Creation Lens, a framework, grounded in theory, for …

    mit Repository record for Essays in System Dynamics for Operations Management: Policy, Platforms and Pricing (opens in a new tab)

  5. Leveraging Geometric Priors for In-the-wild Pose Estimation and 3D Reconstruction

    … underlying priors, they often suffer from domain gaps and require large labeled datasets. In contrast, optimization-based approaches, which do not require labeled data, can adapt to individual instances but are sensitive to initialization. To address these challenges in solving real-world …

    umn Repository record for Leveraging Geometric Priors for In-the-wild Pose Estimation and 3D Reconstruction (opens in a new tab)

  6. Quake-OVUDA: Component-Level AI-Based Post-Earthquake Building Inspections with Vision–Language Guided Unsupervised Domain Adaptation

    … for the real world. Training Unsupervised Domain Adaptation (UDA) models, using synthetic, automatically generated imagery, has shown promise in reducing reliance on manual labeling and improving the adaptation of features learned from the synthetic domain to the real-world domain of …

    houston Repository record for Quake-OVUDA: Component-Level AI-Based Post-Earthquake Building Inspections with Vision–Language Guided Unsupervised Domain Adaptation (opens in a new tab)

  7. Generative 3D scene modeling: algorithm and applications

    … scale is becoming increasingly important across domains such as agriculture, autonomous driving, immersive gaming, and robot learning. However, manually constructing such environments is prohibitively expensive and often introduces domain gaps from real-world distributions. Generative modeling of …

    uiuc Repository record for Generative 3D scene modeling: algorithm and applications (opens in a new tab)

  8. Open-world deep learning applied to pollen detection

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms

    uiuc Repository record for Open-world deep learning applied to pollen detection (opens in a new tab)