AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Turbo Connection: Reasoning as Information Flow from Higher to Lower Layers

Tang Mohan, Sidi Lu

ICML 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Low-rank compression and merging · 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
add dense multi-layer downward connections (TurboConn)Llama 3.2 1B fine-tuned · Parityaccuracy (%): 92.87 -> 100.0Improved
add TurboConnQwen3 1.7B fine-tuned · Parityaccuracy (%): 53.78 -> 100.0Improved
add TurboConnLlama 3.1 8B fine-tuned · Multi-step Arithmeticaccuracy (%): 48.32 -> 51.86Improved
add TurboConnLlama 3.1 8B fine-tuned · GSM8K (No CoT)accuracy (%): 23.92 -> 24.82Improved
replace dense downward connections by single soft-token feedback (ablation)TurboConn on Llama 3.2 1B · Multi-step Arithmeticaccuracy (%): 42.66 -> 38.00Hurt
replace dense downward connections by single soft-token feedback (ablation)TurboConn on Llama 3.2 1B · Parityaccuracy (%): 100.0 -> 96.51Hurt
increase group size from 4 to 8 at alpha=100 (ablation)TurboConn on Llama 3.2 1B · Parityaccuracy (%): 100.00 -> 51.42Hurt
increase group size from 4 to 16 at alpha=100 (ablation)TurboConn on Llama 3.2 1B · GSM8K (No CoT)accuracy (%): 8.32 -> 6.94Hurt
use alpha=1 instead of alpha=100 at group size 16 (ablation)TurboConn on Llama 3.2 1B · Parityaccuracy (%): 51.40 -> 98.85Improved
use alpha=100 instead of alpha=1 at group size 4 (ablation)TurboConn on Llama 3.2 1B · Parityaccuracy (%): 98.94 -> 100.00Improved
use alpha=100 instead of alpha=1 at group size 4 (ablation)TurboConn on Llama 3.2 1B · Multi-step Arithmeticaccuracy (%): 40.13 -> 42.66Improved
add TurboConn to a CoT-conditioned answer modelLlama 3.2 1B · NuminaMath-CoTaccuracy (%): 30.96 -> 33.98Improved

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