barthelomew's submissions

1.		Toward Guarantees for Clinical Reasoning in Vision Language Models (arxiv.org)
		5 points by barthelomew 20 days ago \| past \| 3 comments
2.		SoTA LLM Guardrails by Trusting the Typical [ICLR 2026] (arxiv.org)
		1 point by barthelomew 44 days ago \| past
3.		Predict your distributed LLM training time before you burn GPU hours (github.com/debarghag)
		2 points by barthelomew 57 days ago \| past \| 1 comment
4.		Uncertainty Quantification for Auto Formalization [NeurIPS 2025] (github.com/debarghag)
		1 point by barthelomew 3 months ago \| past
5.		Race optimization algorithms with good initializations (beat them with bonuses) (debargha.com)
		8 points by barthelomew 4 months ago \| past \| 8 comments
6.		ProofOfThought: LLM-based reasoning using Z3 theorem proving (github.com/debarghag)
		326 points by barthelomew 5 months ago \| past \| 175 comments
7.		A Deep Research Agent for Curating Vision Datasets (arxiv.org)
		12 points by barthelomew 5 months ago \| past
8.		Provably guarantee correctness of (some of) your LLM outputs (amazon.com)
		3 points by barthelomew 7 months ago \| past
9.		K^4: Online Log Anomaly Detection via Unsupervised Typicality Learning (arxiv.org)
		3 points by barthelomew 7 months ago \| past \| 1 comment
10.		Grammars of Formal Uncertainty (arxiv.org)
		34 points by barthelomew 9 months ago \| past \| 5 comments
11.		Show HN: Drop-In Out-of-Distribution Data Detector (github.com/debarghag)
		4 points by barthelomew on Jan 4, 2025 \| past
12.		Proof of Thought: Neurosymbolic Program Synthesis for Interpretable Reasoning (arxiv.org)
		4 points by barthelomew on Jan 4, 2025 \| past \| 1 comment
13.		Pfizer vaccine adverse event reports [pdf] (phmpt.org)
		8 points by barthelomew on March 2, 2022 \| past