Excited to share my first PhD paper, “Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift” (accepted to #NeurIPS2026)! We frame AI detection as a continual learning problem, robustifying models to shifting human/AI writing. (1/N)

Show Post

Our experiments show TTA with semi/unsupervised learning helps detectors better classify shifting human/AI writing than pure supervised learning. On scientific abstracts, TTA detects 93.3% of AI text generated with an adversarial prompt; Pangram 3.3.2 detects only 27.0%! (6/N)

Show Post

New from @kevinren09.bsky.social @manishraghav.bsky.social @nkgarg.bsky.social: A crisp characterization of how (potentially adversarial) distribution shift is a major challenge for AI text detection, and how semi-supervised learning helps fix this.

Show Post

AI researchers warn technology 'months away' from being able to connect to wifi using eduroam

Show Post

I'm hiring a postdoc to start in summer/fall 2027! My lab uses computational social & cognitive science methods to explore how tech shapes knowledge & power: www.crockettlab.org You can submit an application here: apply.interfolio.com/195297. Review of apps starts Nov 20. Please share!

Show Post