AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

The Expressive Power of Low Precision Softmax Transformers with (Summarized) Chain-of-Thought

Moritz Brösamle, Stephan Eckstein

ICML 2026 · Architectures and efficiency › Attention and transformers · approach: Transformer expressivity and learnability · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase CoT model depth from 6 to 8 (ablation)CoT transformer on Sudoku · Sudoku-extreme, trained on CoT length up to 2^14accuracy at long contextImproved
raise activation precision from bfloat16 to fp32 (ablation)CoT transformer depth 6 · Sudoku-extreme, trained on CoT length up to 2^14accuracy at long contextNo clear effect
use summarized CoT instead of plain CoT at the same model sizedepth-6, dim-512 transformer · Sudoku-extreme long contextsaccuracyImproved
increase SCoT depth from 4 to 5 (ablation)SCoT transformer dim 512 · Sudoku-extremeaccuracy (%): 16.3 -> 97.2Improved
increase SCoT depth beyond 6 (ablation)SCoT transformer dim 512 · Sudoku-extremeaccuracy (%): 99.5 -> 99.7 -> 99.6No clear effect
longer training for N=2^14 CoT run (ablation)CoT depth 6 · Sudoku-extremeaccuracy at long contextMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy