AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models

Jiyeon Kim, Sungik Choi, Yongrae Jo, Moontae Lee, Minjoon Seo

ICML 2026 · Large language models › Language, safety and interpretability · approach: Parallel and early-exit decoding · 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 learned planner for first-step position selection (ablation)Top-1 Prob · GSM8K (T=32)accuracy: 46.6 -> 55.0Improved
add learned planner for first-step position selection (ablation)Top-1 Prob · Sudoku (T=32)accuracy: 71.2 -> 65.2Hurt
add EOS temperature annealing (ablation)Top-1 Prob · GSM8K (T=32)accuracy: 46.6 -> 50.9Improved
add EOS temperature annealing (ablation)Top-1 Prob · Countdown (T=32)accuracy: 42.2 -> 46.1Improved
add planner and EOS annealing togetherTop-1 Prob · Average of 4 tasks (T=32)accuracy: 44.8 -> 47.6Improved
add planner and EOS annealing togetherProb Margin · Average of 4 tasks (T=32)accuracy: 45.0 -> 49.1Improved
replace random initial position with learned planner (ablation)Init. Position · GSM8K (T=32)accuracy: 52.6 -> 55.0Improved
randomize initial position uniformly (ablation)Top-1 Prob · Sudoku (T=32)accuracy: 71.2 -> 48.3Hurt
randomize initial position uniformly (ablation)Top-1 Prob · GSM8K (T=32)accuracy: 46.6 -> 52.6Improved
increase diffusion steps in NAR confidence decoding (ablation)Top-1 Prob · Average of 4 tasksaccuracy: 44.8 -> 39.7 -> 37.7Hurt
add planner and EOS annealing at higher stepsTop-1 Prob · GSM8K (T=128)accuracy: 23.3 -> 61.0Improved
add planner and EOS annealing at higher stepsTop-1 Prob · Average of 4 tasks (T=128)accuracy: 37.7 -> 52.8Improved

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