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 9 of 9 for “"context inference"”.

  1. Practical reinforcement learning for adaptive robotic manipulation: Sample efficiency, sim-to-real transfer, and context inference

    … data efficiency, sim-to-real transfer, and context-aware generalization to unseen tasks. The first contribution addresses the sample-efficiency challenge. Demonstration Exploitation by Abstract Symmetry of Environments (Demo-EASE), introduces a sample-efficient RL framework with limited …

    uvic Repository record for Practical reinforcement learning for adaptive robotic manipulation: Sample efficiency, sim-to-real transfer, and context inference (opens in a new tab)

  2. Efficient algorithms for scaling large language models

    … scaling along two key dimensions: model size and context length. In the text domain, larger models enable stronger reasoning and generation capabilities, while longer contexts allow models to process complex inputs such as documents, interaction histories, and tool outputs, enabling emerging …

    texas Repository record for Efficient algorithms for scaling large language models (opens in a new tab)

  3. Quantized Lookup Table-Based Representation for Key-Value Cache

    … to enable cache reuse. As the demand for long-context inference grows, KV caches can become extremely large, making efficient compression essential to reduce communication costs. Interestingly, we observe that KV caches exhibit strong model-dependent structure, with layer-specific, non-uniform …

    tamu Repository record for Quantized Lookup Table-Based Representation for Key-Value Cache (opens in a new tab) Embargoed until 2028-05-01

  4. Quantized Lookup Table-Based Representation for Key-Value Cache

    … to enable cache reuse. As the demand for long-context inference grows, KV caches can become extremely large, making efficient compression essential to reduce communication costs. Interestingly, we observe that KV caches exhibit strong model-dependent structure, with layer-specific, non-uniform …

    tamu Repository record for Quantized Lookup Table-Based Representation for Key-Value Cache (opens in a new tab) Embargoed until 2028-05-01

  5. Quantized Lookup Table-Based Representation for Key-Value Cache

    … to enable cache reuse. As the demand for long-context inference grows, KV caches can become extremely large, making efficient compression essential to reduce communication costs. Interestingly, we observe that KV caches exhibit strong model-dependent structure, with layer-specific, non-uniform …

    tamu Repository record for Quantized Lookup Table-Based Representation for Key-Value Cache (opens in a new tab) Embargoed until 2028-05-01

  6. Non-linear dynamics identification using Gaussian process prior models within a Bayesian context.

    … It employs the methodology of Bayesian inference in using evidence or data to modify or refer some prior belief. Within the Bayesian context, inference can be used for several purposes, such as data analysis, filtering, data mining, signal processing, pattern recognition and statistics. …

    maynooth Download PDF for Non-linear dynamics identification using Gaussian process prior models within a Bayesian context. (opens in a new tab)

  7. Inferring Social and Internal Context Using a Mobile Phone

    … to three research areas including social context-aware computing, internal context-aware computing, and human behavioral data mining. In social context-aware computing, four studies are conducted. First, mobile phone user calling behavioral patterns are characterized in forms of randomness …

    unt Repository record for Inferring Social and Internal Context Using a Mobile Phone (opens in a new tab)

  8. Efficient Long-Context Retrieval Systems via Dynamic Sparse Attention

    … over whole collections of long documents. Context windows are finite, however, and so retrieval-augmented generation (RAG) closes that gap by indexing the corpus and retrieving the relevant evidence from it. While long-context RAG applications benefit from both corpus scale and context …

    ethz Repository record for Efficient Long-Context Retrieval Systems via Dynamic Sparse Attention (opens in a new tab)