45%Niche pick?Niche pickVote to see the scoreNeurIPS 2026NortheasternU FreiburgLAION, JSCGoogleÉcole PolytechniqueInstruction tuningStrong Post-Training from Permissive, Reasoning-Dominant, Web-Scale PretrainingHarsh Raj, Ali Elganzory, Marianna Nezhurina, Victor May and 4 moreSydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026– ReadersNo votes yet0/20 AI panelreviewers recommend itReaders and the AI panel: vote on this paper to see what they said.Worth readingNot for meOnly vote on papers you've read. Sign in with GitHub to vote.AI panel: 0 of 20 reviewers recommend itlenient 0/5medium 0/10strict 0/5
83%Must read?Must readVote to see the scoreNeurIPS 2026ELLIS TübingenELLIS Institute TuebingenLLM evaluation & benchmarksFrom Uncertain Judgments to Calibrated Rankings: Conformal Elo Estimation for LLM EvaluationConformal Elo replaces hard judge labels with calibrated win probabilities and split conformal intervals, yielding LLM Elo ratings within 17.9 MAE of human ones with guaranteed uncertainty bounds.Bora Kargi, David SalinasParis Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026– ReadersNo votes yet13/20 AI panelreviewers recommend itReaders and the AI panel: vote on this paper to see what they said.Worth readingNot for meOnly vote on papers you've read. Sign in with GitHub to vote.AI panel: 13 of 20 reviewers recommend itlenient 5/5medium 8/10strict 0/5
80%Must read?Must readVote to see the scoreNeurIPS 2026ELLIS Institute TübingenU FreiburgUniversität LeipzigELLIS Institute TuebingenAutoML & architecture searchAn Open-Source Training Dataset for Foundation Models for Black-box OptimizationBBO-Pile provides 500K real-world black-box optimization trajectories across 3095 problems, and trained foundation models show large-scale pre-training effectively imitates optimization methods.Aaron Klein, Herilalaina Rakotoarison, Luca Thale-Bombien, David SalinasParis Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026 · ▲ 1 on Hugging Face– ReadersNo votes yet12/20 AI panelreviewers recommend itReaders and the AI panel: vote on this paper to see what they said.Worth readingNot for meOnly vote on papers you've read. Sign in with GitHub to vote.AI panel: 12 of 20 reviewers recommend itlenient 4/5medium 6/10strict 2/5