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 20 of 21 for “"Zero-shot Generalization"”.
-
Uncertainty-aware fusion of foundation and task-specific models for cardiac MRI segmentation
… Segment Anything Model (SAM), demonstrate strong zero-shot generalization but lack precision with anatomically challenging structures. In contrast, convolutional neural network (CNN)-based models achieve high accuracy on domain-specific data but struggle to generalize to unseen data. To address …
-
Integrating structural and semantic understanding for robust knowledge graph construction: From knowledge graph completion to zero-shot entity linking
… first part of this research focuses on the Few-shot Knowledge Graph Completion (FKGC) problem, where models must predict missing facts for relations with only a handful of reference examples. Existing methods often suffer from suboptimal negative sampling and static entity representations. To …
-
Improving single and multi-agent deep reinforcement learning methods
… adapt to new environments and tasks, showcasing zero-shot generalization capabilities and resulting in higher sample efficiency. Lastly, we investigate independent policybased methods in cooperative MARL, where each agent considers other agents as part of the environment. We show that such …
-
Generalized Environment-Enabled Object Grasping using a Fixture-Aware Double Deep Q-Network
… higher success than baselines, it also performs zero-shot generalization to novel scenes with unseen object configurations.
-
Advancing Task-Oriented Dialog Systems: Scalability, Generalization, and Evaluation
… faces three critical barriers: scalability, generalization, and evaluation. Scalability is primarily restricted by the human-annotation bottleneck, as current systems depend on vast quantities of manually labeled data for every new domain, making deployment prohibitively expensive. …
-
Toward Robust, Reliable, and Generalizable Models for Tabular Data
… TabuLa. TabuLa exhibits the ability to perform zero-shot generalization to new tables, a capability not possible with existing state-of-the-art tabular models such as XGBoost and TabPFN. TabuLa also outperforms these state-of-the-art models in few-shot generalization, with sample efficiency up …
-
BENCHMARKING AND ENHANCING GENERALIZATION IN MULTILINGUAL SPEECH EMOTION RECOGNITION
… learning models, SER systems often struggle with generalization across diverse languages and unseen data distributions, limiting their real-world applicability. This thesis addresses these challenges by first introducing a large-scale benchmark to evaluate the robustness and adaptability of …
-
A Transformer-Based Multi-Agent Reinforcement Learning Framework for Asynchronous Mission Planning of Heterogeneous Robotic Teams
… Furthermore, the framework exhibits robust zero-shot generalization, successfully maintaining coordination despite novel environment scales, unseen team compositions, dynamic obstacles, and severe communication or localization failures without retraining.
-
On Deep Learning for Nonprehensile Manipulation
… baselines and demonstrating successful zero-shot transfer to a physical robot. Second, we propose the Hierarchical Reinforcement Learning - Diffusion Policy (HeRD), a hybrid architecture designed to solve long-horizon manipulation tasks. We identify that while Reinforcement Learning (RL) …
-
Robust multi-modal imaging in the presence of incomplete modalities
… showing that channel-adaptive approaches improve generalization and efficiency over fixed-channel baselines. We then introduced Diverse Channel ViT (DiChaViT) to tackle the issue of redundant feature learning in MCI-ViTs by encouraging diversity in learned representations through a novel channel …
-
Generalized Model to Enable Zero-shot Imitation Learning for Versatile Robots
… the Cross-modal Reasoning Model (CMRM), a novel zero-shot Imitation Learning policy, to tackle long-horizontal robotic tasks. The RFID inventory task is a typical long-horizontal robotic task that can be formulated as a Partially Observable Markov Decision Process (POMDP); the robot should be …
-
Towards Trustworthy Machine Learning Systems
… in the textual context to improve their zero-shot generalization. Second, interpretability is a desired property of trustworthy ML systems, which makes black-box ML models more accountable. In addition, interpretability tools also help practitioners debug and improve their models. …
-
Capability-Aware Shared Hypernetworks for Heterogeneous Multi-Agent Coordination
… sacrificing diversity, sample efficiency or generalization to unseen agents and teams. First, inspired by work from trait-based heterogeneous task allocation, we explore how capability-awareness enables generalization to unseen agents and teams. We thoroughly evaluate our GNN-based …
-
Towards Unified and Generalizable Multimodal Foundation Models
… naturally acquire and construct knowledge. Generalization, in turn, enables models to adapt to novel tasks in open-world environments under human-specified instructions or principles. Together, unification and generalizability constitute two fundamental pillars for advancing toward …
-
Adaptable Policies and Accelerated Infrastructure for Learning for Heterogeneous Multi-Robot Coordination
… and expressivity at the cost of efficiency and generalization to unseen robots. (2) Existing platforms for training multi-robot policies often force a tradeoff between optimization for multi-agent learning, robotics relevance, and sim-to-real deployment capability. Existing multi-agent benchmark …
-
Towards generalizable motion planning: Efficient and safe learning-based frameworks
… most learning-based planners suffer from poor generalization, requiring retraining when deployed in new scenes or on different robot platforms. This thesis presents two learning-based frameworks designed to address these challenges. First, the Path Planning and Collision Checking Network …
-
Generative modeling and scalable test-time optimization using diffusion and flow models
… demonstrates the state-of-the-art performance in zero-shot inversion and semantic image editing, supported by both theory and large-scale human evaluations. To address structural limitations in diffusion language models, we introduce the concept of anchoring. In Anchored Diffusion Language Models …
-
Towards efficient and robust reinforcement learning via synthetic environments and offline data
… for test-time inference, significantly improving zero-shot generalization to novel dynamics. Going beyond commonly used forward dynamics models, we propose an alternative paradigm, <em>Synthetic Experience Replay</em>, which uses generative modeling to directly model and upsample the agent's …
-
Towards Adaptable and Deployable Wildlife Detection from Aerial Imagery
… manual counting and limited model generalization. While camera trap–based approaches are used for species identification and behavioural monitoring at fixed locations, aerial imagery acquired from drones and aircraft enables large-area coverage and is commonly used to estimate …
-
All Malware Looks Similar Until It Doesn’t
… are evaluated through similarity search and zero-shot clustering, with particular focus on their ability to generalize beyond malware families observed during training. To this end, Siamese metric learning approaches based on triplet loss are applied using multi-layer perceptrons for static, …
Page 1 of 2