Author

Yaniv Romano

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

When Metropolis and Hastings Meet Bradley and Terry: Exact MCMC From Preference Voting

This work introduces Pref-MH, a general exact MH sampler for judge-induced conditional distributions using only stochastic binary pairwise comparisons, and develops a valid accept/reject rule whose resulting Markov chain provably converges to the target distribution.

Ariel Smogorghevski, Nir Rosenfeld, Yaniv Romano · 0 citations

Preprint Aug 2026

Truncate Bad, Upweight Good: BoN-Style Distillation via Rank-Based Classification

This work proposes TUP: a Truncate-bad, Upweight-good Policy that removes low-ranked completions from the support and reweights only the retained upper tail with a tunable sharpness, and shows that TUP is competitive with strong offline alignment baselines.

Yarin Bar, Yaniv Romano · 0 citations