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 528 for “"test time"”.
-
Test-Time Training for Image Inpainting
… For optimal results, the user image at inference time should belong to the same domain as the training examples, which greatly limits the range of inputs a trained network can be used for. Moreover, collecting new data is hard, and training on different datasets requires a great amount of …
-
Learning under Test-Time Feedback: Reduction, Learning, Optimization
… own predictions, leading to a phenomenon we call test-time feedback (TTF). TTF denotes the mismatch between performance on the per-step training objective and downstream performance along the model's test-time rollouts, where prediction errors feed back into the model and potentially compound with …
-
Test-Time Adaptation with Steering Primitives for Realigning Representations
This work investigates test-time adaptation, the problem of adapting a pretrained model to distribution shift at deployment using only unlabeled test data. Existing methods typically adapt by updating the model’s own parameters, which limits both what can be adapted and where adaptation can occur …
-
Towards Model Adaptation at Test-time in Open-World Environments
… excel under the assumption that training and test datasets share the same distribution. However, this assumption rarely holds in open-world applications, where training data cannot capture the evolving nature of real-world environments. This gap, termed distribution shift or domain shift, …
-
TEST-TIME ADAPTATION OF LEARNED IMAGE PRIORS FOR MEDICAL IMAGE RECONSTRUCTION
This thesis studies test-time adaptation of learned image priors for medical image reconstruction under distribution shift. It considers two representative prior types: denoiser-based priors in unrolled reconstruction networks and diffusion priors represented by score networks. For denoiser-based …
-
Improving Video Highlight Detection via Unsupervised Learning and Test-Time Adaptation
… often exhibit limited generalization to unseen test videos, as they rely on generic highlight detection models trained on fixed datasets. This leads to suboptimal performance on unseen test videos due to domain shifts and unique video-specific characteristics not captured during training. To …
-
Driver-gas Tailoring For Test-time Extension Using Unconventional Driver Mixtures
… is of great importance to increase experimental test times, and this can be done by tailoring the interface between the driver and driven gases. Using unconventional driver-gas tailoring with the assistance of tailoring curves, shock-tube test times were increased from 1 to 15 ms for …
-
Efficient and Test-Time Adaptive Visual Object Tracking in the Wild
… on in-distribution (ID) datasets, i.e., on the testing portion of the same datasets used for training. However, they incur high computational costs and hardware constraints, making their deployment in the wild for mobile, autonomous, and IoT applications still challenging. Efficient visual …
-
Benchmarking Test-Time DNN Adaptation at Edge with Compute-In-Memory
… (DNNs) deployed at the edge can deteriorate over time due to shifts in the data distribution. For heightened robustness, it’s crucial for DNNs to continually refine and improve their predictive capabilities. However, adaptation in resource-limited edge environments is fraught with challenges: (i) …
-
New methodology for low power and less test time in VLSI testing
… (IC) has brought up many challenges in IC testing industry. The most challenging problems are the overhead of power dissipation, of test data volume, and of test time. These three challenges are expected to get worse as IC gets more complex and the system-on chip (SOC) gets deeper and more …
-
Generative modeling and scalable test-time optimization using diffusion and flow models
… framework for generative modeling and scalable test-time optimization, grounded in posterior sampling, stochastic optimal control, and structured anchoring. Modern diffusion-based generative models achieve remarkable quality, yet their use in inverse problems, personalization, editing, and …
-
ADVANCING TEST-TIME COMPUTE SCALING IN LANGUAGE MODELS: FROM TRAINING TO INFERENCE
… models increasingly benefit from scaling test-time computation, but effective scaling requires more than simply allocating additional inference compute. This thesis studies four complementary bottlenecks across the model lifecycle: context capacity, reasoning capability, efficient …
-
Investigating the application of test-time machine learning methods for geophysics inverisons
… on leveraging machine learning (ML) methods in a test-time learning manner to improve geophysical inversions. The research explores the potential of implicit regularization effects inherent in certain ML models, which do not require training datasets, so these methods are test-time learning …
-
Learning at Test Time: Adapting Models with Synthetic Data and Environment Interaction
… unavailable during training. This thesis studies test-time context mismatch: the setting in which information needed for reliable model behavior is only revealed at deployment time. It investigates how two kinds of test-time information, limited unannotated real data and environment interaction, …
-
Time-Series Representation Learning through Dynamic Temporal Reordering and Test-Time Adaptation
Time-series applications span domains such as energy, healthcare, finance, and climate modeling, where the ability to learn rich temporal representations and remain robust under distribution shift is critical. However, existing models often rely on fixed temporal structures that overlook non-local …
-
RecTTA: Reconstruction-based Test-Time Adaptation For Robust Trajectory Prediction In Dynamic Environments
… thesis introduces RecTTA (Reconstruction-based Test-Time Adaptation), a groundbreaking framework that fundamentally transforms trajectory prediction from static inference to dynamic adaptation. Unlike existing domain-specific adaptation methods, RecTTA leverages input trajectory reconstruction …
-
Supervised Machine Learning Under Test-Time Resource Constraints: A Trade-off Between Accuracy and Cost
… and cost must be strictly accounted for during test-time. A typical problem is that if an application consumes x additional units of cost during test-time, but will improve accuracy by y percent, should the additional x resources be allocated? The core of this problem is a trade-off between …
Page 1 of 27