AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

RankFlow: Property-aware Transport for Protein Optimization

Lu Yu, Wei Xiang, Kang Han, Gaowen Liu, Ramana Rao Kompella

ICLR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Generative protein structure design · 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 rank-consistent loss LRFlow to energy-guided flow matching (ablation)RankFlow · ProteinGym FitnessSpearman: 0.702 -> 0.742Improved
add rank-consistent loss LRFlow to energy-guided flow matching (ablation)RankFlow · ProteinGym ActivitySpearman: 0.680 -> 0.722Improved
add flow-matching energy loss LPFM to rank loss (ablation)RankFlow · ProteinGym FitnessSpearman: 0.624 -> 0.742Improved
use rank-consistent loss instead of kinetic regularizer (ablation)RankFlow · ProteinGym FitnessSpearman: 0.714 -> 0.742Improved
use rank-consistent loss instead of pairwise hinge (ablation)RankFlow · ProteinGym FitnessSpearman: 0.709 -> 0.742Improved
use energy weight lambda=0.5 instead of 0 (ablation)RankFlow · ProteinGym FitnessSpearman: 0.718 -> 0.742Improved
use energy weight lambda=0.5 instead of 1 (ablation)RankFlow · ProteinGym FitnessSpearman: 0.738 -> 0.742Improved
use cosine schedule instead of linear (ablation)RankFlow · ProteinGym FitnessSpearman: 0.736 -> 0.742Improved
use combined rank-and-normalized energy instead of negative label energy (ablation)RankFlow · ProteinGym FitnessSpearman: 0.738 -> 0.742Improved
add structure information and fusion encoder (ablation)RankFlow · ProteinGym (Fitness, Activity)SpearmanImproved
add property-guided steering gate (ablation)RankFlow · ProteinGymSpearmanImproved
use RankFlow instead of Kermut on contiguous splitRankFlow · ProteinGym ContiguousSpearman: 0.591 -> 0.589Hurt

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