Soheil Feizi to speak on the structure of reasoning in LLMs at Simons Institute workshop
SharonYixuanLi · x · 2026-10-07
University of Maryland's Soheil Feizi will speak at the Simons Institute workshop "Trustworthy AI: From Hallucinations to Reliable Autonomy" (Oct 7, 2:45–3:30pm PT) during COLM 2026 week.
His talk, "Understanding the Structure of Reasoning in Language Models," covers reasoning dynamics, reasoning under uncertainty, and mechanisms for controlling inference-time computation. The recurring theme: strong underlying capabilities do not always translate into reliable reasoning behavior — understanding that gap and the internal signals governing reasoning is becoming central to reliable autonomous AI.
More from Research
- 3DGS tracking upgraded: 120fps global-shutter camera doubles pose updates — Scobleizer · 2026-10-07
- New study argues life on Earth didn't have one origin, but two — skdh · 2026-10-07
- COLM paper: a few misaligned LLM agents can sway aligned majorities — AccBalanced · 2026-10-07
- Sharing one KV cache across recursions improves looped Transformers, preprint finds — yoavartzi · 2026-10-07
- Fourier transforms pushed to O(N log(N)^0.9999...), nearly closing the log gap — burny_tech · 2026-10-07
- Stanford OVAL brings two papers to COLM2026: SatIR and DataSTORM — stanfordnlp · 2026-10-07