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 “"Test-time Compute"”.

  1. 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 …

    nus Repository record for ADVANCING TEST-TIME COMPUTE SCALING IN LANGUAGE MODELS: FROM TRAINING TO INFERENCE (opens in a new tab) Download file for ADVANCING TEST-TIME COMPUTE SCALING IN LANGUAGE MODELS: FROM TRAINING TO INFERENCE (opens in a new tab)

  2. Systems and methods for improving large language models with increased inference compute

    Scaling the amount of compute used to train language models has led to massive increases in their capability. A relatively under-explored direction has been scaling the amount of compute used at inference time. This thesis explores the design space for test-time compute algorithms, focusing on the …

    oxford Repository record for Systems and methods for improving large language models with increased inference compute (opens in a new tab)

  3. MITIGATING REASONING-INDUCED HALLUCINATION IN LARGE REASONING MODELS VIA TRACE CONDENSATION

    … this work proves that actively managing test-time compute through structured, multi-agent trace condensation is an effective framework for ensuring robust intrinsic reasoning.

    maryland Repository record for MITIGATING REASONING-INDUCED HALLUCINATION IN LARGE REASONING MODELS VIA TRACE CONDENSATION (opens in a new tab)

  4. The Algorithm-Hardware Specialization Spectrum of Multi-Stage Intelligence Pipelines: From Dedicated Accelerators to Heterogeneous Systems

    … ORCHES (Q3): a GPU-PIM heterogeneous system for test-time-compute (TTC) LLM/VLM reasoning, combining adaptive workload assignment, branch-prediction-guided pipelining, and fragmentation-aware memory structuring. Achieves 4.16× / 3.10× end-to-end speedup on text / vision reasoning over SOTA GPU …

    gatech Repository record for The Algorithm-Hardware Specialization Spectrum of Multi-Stage Intelligence Pipelines: From Dedicated Accelerators to Heterogeneous Systems (opens in a new tab)

  5. Structure in Prediction: Mapping Large Language Model Prediction to Symbolic Structure

    … state-space complexity effectively predicts the test-time compute required for a reliably correct solution. This allows for principled compute budgeting, moving beyond heuristic prompting toward a rigorous theory of inference-time scaling. The third chapter investigates the scaling efficiency of …

    cornell Repository record for Structure in Prediction: Mapping Large Language Model Prediction to Symbolic Structure (opens in a new tab)

  6. Exploring the Capabilities and Limitations of Large Language Models in Financial Textual Analysis

    … achieving significant reductions in inference time compared to existing test-time search algorithms. The findings provide both diagnostic clarity for understanding LLM limitations in financial contexts and practical methodologies for enhancing their reliability in high-stakes analytical …

    queens Repository record for Exploring the Capabilities and Limitations of Large Language Models in Financial Textual Analysis (opens in a new tab)

  7. Unifying Foundation Models with Decision Making: A Path Towards Autonomous Self-Improving Agents beyond Rewards and Human Supervision

    … improvement of the video plans using inference-time compute, leading to more grounded and physically plausible plans in robotic manipulation tasks. Second, we develop a framework, Reg-ReBoot, to investigate efficient and scalable methods to improve base non-reasoning LLMs into better reasoners …

    waterloo Repository record for Unifying Foundation Models with Decision Making: A Path Towards Autonomous Self-Improving Agents beyond Rewards and Human Supervision (opens in a new tab)

  8. Efficient Inference-time Control and Alignment

    … enforcing behavioral objectives at inference time rather than modifying model parameters during post-training. In this approach, smaller modular control models are combined with a base model to shape predictions during the decision process. Our aim is to design alignment mechanisms that are …

    waterloo Repository record for Efficient Inference-time Control and Alignment (opens in a new tab)

  9. Interpretable and Trustworthy AI Systems for Healthcare

    … methods compare to complex AI models for EHR time series prediction, how to build inherently interpretable architectures for clinical text classification, and how to enable secure LLM agents for sensitive data analysis.</p><p>We examine whether, and under what conditions, transformer models …

    duke Repository record for Interpretable and Trustworthy AI Systems for Healthcare (opens in a new tab)