HN Explorer

barthelomew

↗ HN profile [ 56.0 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Labeling Copilot: An agent for automated data curation in computer vision (github.com)
    5 points 0
  2. Toward Guarantees for Clinical Reasoning in Vision Language Models (arxiv.org)
    5 points 3
  3. SoTA LLM Guardrails by Trusting the Typical [ICLR 2026] (arxiv.org)
    1 points 0
  4. Predict your distributed LLM training time before you burn GPU hours (github.com)
    2 points 1
  5. Uncertainty Quantification for Auto Formalization [NeurIPS 2025] (github.com)
    1 points 0
  6. Race optimization algorithms with good initializations (beat them with bonuses) (debargha.com)
    8 points 6
  7. ProofOfThought: LLM-based reasoning using Z3 theorem proving (github.com)

    https://arxiv.org/abs/2409.17270

    326 points 28
  8. A Deep Research Agent for Curating Vision Datasets (arxiv.org)
    12 points 0
  9. Provably guarantee correctness of (some of) your LLM outputs (aws.amazon.com)
    3 points 0
  10. K^4: Online Log Anomaly Detection via Unsupervised Typicality Learning (arxiv.org)
    3 points 1
  11. Grammars of Formal Uncertainty (arxiv.org)
    34 points 6
  12. Show HN: Drop-In Out-of-Distribution Data Detector (github.com)

    Out-of-Distribution (OOD) detection is possibly the most important problem for safe and deployable ML, because it provides the first line of defense by preventing silent failures in critical ML systems; bounds AI…

    4 points 0
  13. Proof of Thought: Neurosymbolic Program Synthesis for Interpretable Reasoning (arxiv.org)
    4 points 1
  14. Pfizer vaccine adverse event reports [pdf] (phmpt.org)
    8 points 1