About 740 results
Open links in new tab
  1. 016 namely CLEVER, which is augmentation-free 017 and mitigates biases on the inference stage. 018 Specifically, we train a claim-evidence fusion 019 model and a claim-only model …

  2. Measuring Mathematical Problem Solving With the MATH Dataset

    Oct 18, 2021 · To find the limits of Transformers, we collected 12,500 math problems. While a three-time IMO gold medalist got 90%, GPT-3 models got ~5%, with accuracy increasing slowly.

  3. Alias-Free Mamba Neural Operator - OpenReview

    Sep 25, 2024 · Functionally, MambaNO achieves a clever balance between global integration, facilitated by state space model of Mamba that scans the entire function, and local integration, …

  4. Thieves on Sesame Street! Model Extraction of BERT-based APIs

    Dec 19, 2019 · Finally, we study two defense strategies against model extraction—membership classification and API watermarking—which while successful against some adversaries can …

  5. Weakly-Supervised Affordance Grounding Guided by Part-Level...

    Jan 22, 2025 · In this work, we focus on the task of weakly supervised affordance grounding, where a model is trained to identify affordance regions on objects using human-object …

  6. Reasoning of Large Language Models over Knowledge Graphs with...

    Jan 22, 2025 · While large language models (LLMs) have made significant progress in processing and reasoning over knowledge graphs, current methods suffer from a high non-retrieval rate.

  7. Training Large Language Model to Reason in a Continuous

    Sep 26, 2024 · Large language models are restricted to reason in the “language space”, where they typically express the reasoning process with a chain-of-thoughts (CoT) to solve a …

  8. Large Language Models are Human-Level Prompt Engineers

    Feb 1, 2023 · We propose an algorithm for automatic instruction generation and selection for large language models with human level performance.

  9. Eureka: Human-Level Reward Design via Coding Large Language …

    Jan 16, 2024 · Large Language Models (LLMs) have excelled as high-level semantic planners for sequential decision-making tasks. However, harnessing them to learn complex low-level …

  10. Probabilistic Learning to Defer: Handling Missing Expert...

    Jan 22, 2025 · Recent progress in machine learning research is gradually shifting its focus towards *human-AI cooperation* due to the advantages of exploiting the reliability of human …