barthelomew
- Karma
- 229
- Created
- 6 years ago
About
ML research; debargha@case.eduRecent Submissions
- 1. ▲ Toward Guarantees for Clinical Reasoning in Vision Language Models (arxiv.org)
- 2. ▲ SoTA LLM Guardrails by Trusting the Typical [ICLR 2026] (arxiv.org)
- 3. ▲ Predict your distributed LLM training time before you burn GPU hours (github.com)
- 4. ▲ Uncertainty Quantification for Auto Formalization [NeurIPS 2025] (github.com)
- 5. ▲ Race optimization algorithms with good initializations (beat them with bonuses) (debargha.com)
- 6. ▲ ProofOfThought: LLM-based reasoning using Z3 theorem proving (github.com)
- 7. ▲ A Deep Research Agent for Curating Vision Datasets (arxiv.org)
- 8. ▲ Provably guarantee correctness of (some of) your LLM outputs (aws.amazon.com)
- 9. ▲ K^4: Online Log Anomaly Detection via Unsupervised Typicality Learning (arxiv.org)
- 10. ▲ Grammars of Formal Uncertainty (arxiv.org)