AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow Matching

Chenguang Wang, Zihan Zhou, LEI BAI, Tianshu Yu

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Flow matching generative modeling · 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 positional embedding (absolute PE) to RC-rooted ordering (ablation)RetroDiT-8M · USPTO-50kTop-1 (%): 50.4 -> 68.5Improved
use RoPE instead of absolute PE (ablation)RetroDiT-8M · USPTO-50kTop-1 (%): 68.5 -> 71.0Improved
use RoPE instead of absolute PE (ablation)RetroDiT-8M · USPTO-50kTop-10 (%): 94.8 -> 96.5Improved
use oracle reaction centers instead of predictedRetroDiT · USPTO-50kTop-1 (%): 61.2 -> 71.1Improved
use oracle reaction centers instead of predictedRetroDiT · USPTO-FullTop-1 (%): 51.3 -> 63.4Improved
add RC-rooted ordering instead of canonical ordering (ablation)RetroDiT 65M · USPTO-FullTop-1 (%): 50.4 -> 51.2Improved
add oracle RC ordering to a small model instead of scaling to 65M canonical (ablation)RetroDiT 280K · USPTO-FullTop-1 (%): 50.4 -> ~51Improved
use RC-rooted ordering at low RC accuracy (below 35-40%) (ablation)RetroDiT-8M · USPTO-50k and USPTO-FullTop-1 (%): 35--40%Hurt
use RC-rooted ordering at 70% RC accuracy (ablation)RetroDiT-8M · USPTO-50k and USPTO-FullTop-1 (%): over 10 pointsImproved
use structure-aware flow model instead of RetroBridge diffusionOurs (Pred. RC) · USPTO-50kTop-1 (%): 50.8 -> 61.2Improved
use structure-aware flow model instead of RetroSynFlowOurs (Pred. RC) · USPTO-50kTop-1 (%): 60.0 -> 61.2Improved
use DiT backbone instead of Graph Transformer (ablation)RetroDiT · USPTO-FullaccuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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