Michael Hahn at BlackboxNLP: Turning Transformer Computations into Programs and Automata
hanjie_chen · x · 2026-10-29
At the BlackboxNLP 2026 workshop (EMNLP, Budapest), Saarland University professor Michael Hahn speaks at 14:00 on turning Transformer computations into explicit programs and automata, and what thinking traces do (and don't) reveal about how models reach their answers.
More from Research
- SARL trains search agents to recognize missing info without inference-time overhead — Taewhoo Lee · 2026-10-29
- CMU and Microsoft's AdaPRA uses adaptive rubrics to cut data science agent errors — CarnegieMellonU · 2026-10-29
- Ben Lorica: What If AI Engineers the Robot Itself, Not Just Drives It? — bigdata · 2026-10-29
- One neuron flips the persona: Tulu 3 8B's Layer 14 Neuron 3851 toggles helpful assistant to torture persona — menhguin · 2026-10-29
- Across 28 models, knowledge breadth tracks intelligence at Pearson r=0.86 — teortaxesTex · 2026-10-29
- Preprint finds AI-assisted peer review beats human-only review; HHMI embraces AI — anshulkundaje · 2026-10-29