Talk at Geometry of ML 2026 shows AI finding and recommending resolutions to open math conjectures
wellecks · x · 2026-09-11
The author gave a talk at The Geometry of Machine Learning 2026 on their team's recent work in AI-assisted mathematical discovery.
The research focuses on systematically finding, attempting, and recommending resolutions to open mathematical conjectures using AI systems. The slides are publicly available for those who want to dig into the methodology.
Related event: CMU's FAR Framework Sifts 5,245 Papers for Conjectures Worth Solving(3 posts)→
More from Research
- In 2016 Robin Sloan already built an RNN-powered inline AI writing plugin — jackclarkSF · 2026-09-11
- SlopCodeBench: Measuring how sloppy LLM-generated code really is — mitsuhiko · 2026-09-11
- Microsoft paper: read-only verification tools lift agent memory pass rate from 39% to 73% — dair_ai · 2026-09-11
- Yale NLP Releases IdeaAMBIG Benchmark Targeting Underspecified Research Ideas for LLMs — yale-nlp · 2026-09-11
- SAM-H uses SAM 2 masks for training-free homography tracking, +18.4pp on PlanarTrack — ducha_aiki · 2026-09-11
- Autoregressive vs Diffusion Training: The Data-Efficiency Math Behind Non-Causal Architectures — mgostIH · 2026-09-11