AI safety researcher

Micah Goldblum

University of Maryland

Google Scholar dblp ORCID

Last 12 months4 papers

AI safety papers from the last year

On this site: 36 papers

October 2026

The Role of Quantization in Loss Spikes
Oct 28arXiv ↗

September 2026

TANGO: Watermarking Masked Diffusion Language Models in Token Pairs
Sep 28arXiv ↗

February 2026

Privacy-Preserving Mechanisms Enable Cheap Verifiable Inference of LLMs
Feb 19arXiv ↗

November 2025

Knowing What You Know Is Not Enough: Large Language Model Confidences Don't Align With Their Actions
Nov 17arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.