AI Paper Atlas

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

Training Diffusion Language Models for Black-Box Optimization

Zipeng Sun, Can Chen, Ye Yuan, Haolun Wu, Jiayao Gu, Christopher Pal, Xue Liu

ICML 2026 · Large language models › Language, safety and interpretability · approach: LLM pruning and scaling data · 0 citations (OpenAlex)

Read the paper

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
use diffusion LLM (LLaDA) instead of autoregressive LLaMA backbone (ablation)DiBO · TF Bind 8normalized 100th percentile score: 0.915 -> 0.946Improved
use diffusion LLM instead of autoregressive backbone (ablation)DiBO · TF Bind 10normalized 100th percentile score: 0.682 -> 0.741Improved
use diffusion LLM instead of autoregressive backbone (ablation)DiBO · Ant Morphologynormalized 100th percentile score: 0.930 -> 0.932Improved
use diffusion LLM instead of autoregressive backbone (ablation)DiBO · D'Kitty Morphologynormalized 100th percentile score: 0.912 -> 0.912No clear effect
add delimiter tokens (ablation)DiBO · Ant Morphology (DA stage)normalized 100th percentile score: 0.693 -> 0.875Improved
add delimiter tokens (ablation)DiBO · TF Bind 8 (RL stage)normalized 100th percentile score: 0.943 -> 0.946Improved
add RL stage on top of DA+SFT (ablation)DiBO · TF Bind 8normalized 100th percentile score: 0.939 -> 0.946Improved
add SFT stage to DA+RL (ablation)DiBO · Ant Morphologynormalized 100th percentile score: 0.858 -> 0.932Improved
add domain adaptation stage to SFT+RL (ablation)DiBO · Ant Morphologynormalized 100th percentile score: 0.913 -> 0.932Improved
add DA and SFT before RL (ablation)DiBO · TF Bind 8normalized 100th percentile score: 0.437 -> 0.946Improved
add similarity-conditioned context (ablation)DiBO · TF Bind 8normalized 100th percentile score: 0.730 -> 0.946Improved
add similarity-conditioned context (ablation)DiBO · Ant Morphologynormalized 100th percentile score: 0.906 -> 0.932Improved

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