Y Hacker News new | ask | show | jobs

user: barthelomew created: 2019-08-19 karma: 229 ML research; debargha@case.edu submissions: Labeling Copilot: An agent for automated data curation in computer vision 5 points | 0 comments 0 points | 0 comments 0 points | 0 comments Toward Guarantees for Clinical Reasoning in Vision Language Models 5 points | 3 comments SoTA LLM Guardrails by Trusting the Typical [ICLR 2026] 1 points | 0 comments 0 points | 0 comments Predict your distributed LLM training time before you burn GPU hours 2 points | 1 comments Uncertainty Quantification for Auto Formalization [NeurIPS 2025] 1 points | 0 comments 0 points | 0 comments Race optimization algorithms with good initializations (beat them with bonuses) 8 points | 8 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments ProofOfThought: LLM-based reasoning using Z3 theorem proving 326 points | 175 comments A Deep Research Agent for Curating Vision Datasets 12 points | 0 comments Provably guarantee correctness of (some of) your LLM outputs 3 points | 0 comments K^4: Online Log Anomaly Detection via Unsupervised Typicality Learning 3 points | 1 comments Grammars of Formal Uncertainty 34 points | 5 comments Show HN: Drop-In Out-of-Distribution Data Detector 4 points | 0 comments 0 points | 0 comments Proof of Thought: Neurosymbolic Program Synthesis for Interpretable Reasoning 4 points | 1 comments 0 points | 0 comments 0 points | 0 comments