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 99 for “"In-Context Learning"”.

  1. Explore the In-context Learning Capability of Large Language Models

    … Large Language Models (LLMs) has marked the beginning of a new age in AI capabilities, particularly in the domain of natural language understanding and processing. Among the forefront of these advancements is the exploration of in-context learning, a paradigm that enables models to adapt to new …

    waterloo Repository record for Explore the In-context Learning Capability of Large Language Models (opens in a new tab)

  2. Investigating an in-context learning approach for SPARQL query generation

    … across a wide range of natural language processing tasks. Among adaptation strategies, fine-tuning is effective but computationally expensive, while in-context learning (ICL) offers a cheaper and more flexible alternative, particularly appealing for enterprise settings where finetuning is often …

    brazil-ufrgs Repository record for Investigating an in-context learning approach for SPARQL query generation (opens in a new tab)

  3. Mathematical Foundations of Modern Machine Learning: Generative Models and In-Context Learning

    … approximation-theoretic aspects of modern machine learning models, focusing on two distinct settings: diffusion and flow-based generative models and transformer-based in-context learning models. For generative models, we first prove upper bounds on the distribution estimation error for …

    umn Repository record for Mathematical Foundations of Modern Machine Learning: Generative Models and In-Context Learning (opens in a new tab)

  4. Advancing data-efficient deep learning: non-parametric transformers, active testing, and in-context learning

    … larger datasets has played an important role in the practical success of deep learning. Unfortunately, in many real-world scenarios, high quality data may be scarce, such that the naive application of deep learning can fall short of expectations. A large variety of prior work aims to remedy …

    oxford Repository record for Advancing data-efficient deep learning: non-parametric transformers, active testing, and in-context learning (opens in a new tab)

  5. Detecting Zero-Day Attacks in IEC-61850 based Digital Substations via In-Context Learning

    … on the electrical power grids have been increasing every year. In this thesis, we address the critical challenge of detecting novel/zero-day attacks in digital substations that employ the IEC-61850 communication protocol. While many heuristic and ML-based methods have been proposed for …

    vt Repository record for Detecting Zero-Day Attacks in IEC-61850 based Digital Substations via In-Context Learning (opens in a new tab)

  6. Non-parametric deep learning with applications in active learning

    <p>We challenge a common assumption underlying most supervised <i>deep learning</i>: that a model makes a prediction depending only on its parameters and the features of a <i>single input</i>. To this end, we introduce a general-purpose deep learning architecture---<strong>Non-Parametric …

    oxford Restricted access

  7. Exploring the In-Context Estimation Capabilities of Transformer Models

    In recent years, the research community has observed the remarkable capability of transformer models to perform in-context learning (ICL). In this paradigm, the model's parameters are fixed and it must solve a problem using examples presented at test-time. This requires the model to use the given …

    tamu Repository record for Exploring the In-Context Estimation Capabilities of Transformer Models (opens in a new tab)

  8. State Space Model Based Channel Estimation

    This thesis aims to understand the in-context learning capabilities of state space model based deep learning architectures for channel estimation. The channel values in a wireless communication system can be viewed as a time series and hence various sequence modeling approaches can be used to …

    tamu Repository record for State Space Model Based Channel Estimation (opens in a new tab)

  9. Universal in-context approximation

    … research and practice from task-specific training to in-context learning via prompting. This raises a fundamental question: can a model with fixed weights solve novel tasks as effectively as a fine-tuned one? This thesis investigates the theoretical capabilities and limitations of in-context …

    oxford Repository record for Universal in-context approximation (opens in a new tab)

  10. Data-centric strategies for machine translation: efficient acquisition, cleaning, and exploitation of parallel resources

    … corpora are an essential resource for crosslingual natural language processing. Particularly in machine translation (MT), dedicated systems heavily rely on massive amounts of this data for training, while large language models (LLMs) require less parallel data to be adapted for translation …

    alicante Repository record for Data-centric strategies for machine translation: efficient acquisition, cleaning, and exploitation of parallel resources (opens in a new tab)

  11. Exploring Active Learning Algorithms for Data Efficient Language Models

    Supervised learning is based in the premise that models can effectively solve tasks by learning from numerous examples, mapping inputs to outputs through iterative learning. However, contemporary deep learning models often require vast amounts of labeled data, termed training examples, for optimal …

    whiterose Download PDF for Exploring Active Learning Algorithms for Data Efficient Language Models (opens in a new tab)

  12. Study of Pretraining Bias and Frequencies

    Usage of language models in an in-context learning environment has been adapted for a wide range of tasks. Recent works have showcased the impact of pretraining data on the in-context performance of language models. In this work, we experiment with numbers having high and low frequencies in the …

    vt Repository record for Study of Pretraining Bias and Frequencies (opens in a new tab)

  13. mSCAN - a Multilingual Dataset for Compositional Generalization Evaluation

    … of these benchmarks evaluate performance in English only, leaving open the question of whether these results generalize to other languages. As an initial step to answering this question, we introduce mSCAN, a multilingual adaptation of the SCAN dataset covering Mandarin Chinese, French, …

    washington Repository record for mSCAN - a Multilingual Dataset for Compositional Generalization Evaluation (opens in a new tab)

  14. Complexity of In-Context Concept Learning in Language Models

    … that contribute to the success and shortcomings of in-contextlearning, which refers to the ability of some language models to perform a new task during inference using only a few labeled examples, for Large Language Models (LLMs). Drawing on insights from the literature on human concept …

    washington Repository record for Complexity of In-Context Concept Learning in Language Models (opens in a new tab)

  15. Expressivity and learnability of sequence models

    In this thesis, we study the representational capabilities and learnability of sequence models, with a focus on Transformers, the backbone of modern large language models. We first investigate expressivity: whether and how efficiently an architecture can represent a target function. For a range of …

    oxford Repository record for Expressivity and learnability of sequence models (opens in a new tab)

  16. Retrieval augmented retrieval with in-context examples

    We investigate whether in-context examples, widely used in decoder-only language models (LLMs), can improve embedding model performance in retrieval tasks. Unlike in LLMs, naively prepending in-context examples (query-document pairs) to the target query at inference time does not work out of the …

    texas Repository record for Retrieval augmented retrieval with in-context examples (opens in a new tab)

  17. Scaling Online Reinforcement Learning In Embodied AI To 64K Steps

    Intelligent embodied agents need to quickly adapt to new scenarios by integrating long histories of experience into decision-making. For instance, a robot in an unfamiliar house initially wouldn't know the locations of objects needed for tasks and might perform inefficiently. However, as it gathers …

    gatech Repository record for Scaling Online Reinforcement Learning In Embodied AI To 64K Steps (opens in a new tab)

Page 1 of 5