Mathematician releases AI-drafted papers combining OpenAI work with accelerated logconcave sampling research
michaelchchoi · x · 2026-10-09
Mathematician Jianfeng Lu published two preliminary research drafts on GitHub combining work OpenAI released this Tuesday with his ongoing research started in August at the Simons Institute, targeting accelerated logconcave sampling with subpolynomial dimension dependence. One draft gives an every-execution query bound of Cη·κ^(2/3)·d^η at total variation accuracy 1/10 for C² strongly convex potentials. The manuscripts are explicitly AI-generated and preliminary, with improved exposition forthcoming.
More from Research
- Could Looped Models Resist Distillation Attacks by Reasoning in Latent Space? — moyix · 2026-10-09
- LLM-as-a-Verifier: Weaker Model Verifies Stronger One, Hits 69.2% SOTA on Terminal-Bench 4 — Azaliamirh · 2026-10-09
- Salesforce's SRD distills hindsight into foresight, lifting 2B agent success from 0% to 60.6% — Salesforce · 2026-10-09
- Claude claims discovery of new binary red dwarf pair ~500 light-years away — nitarshan · 2026-10-09
- Prompt Tuning Is Forgotten Lore — Are We Massively Underusing Finetuned Tokens? — cephaloform · 2026-10-09
- Ricardo Baeza-Yates Lecture: When Will ML Evaluation Stop Fooling Itself? — PolarBearby · 2026-10-09