AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Spectral Flow Matching: Stabilizing Stochastic GFlowNets via Frequency-Domain Regularization

Nadhir Hassen, Johan W. Verjans

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Flow matching generative modeling

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
use spectral loss (ST-GFN) instead of trajectory balanceTB · Sample efficiencysteps to 90% performance: 10483 -> 5850Improved
use spectral loss (ST-GFN) instead of SubTBSubTB · Sample efficiencysteps to 90% performance: 7850 -> 5850Improved
use spectral loss (ST-GFN) instead of Stochastic-GFNStochastic-GFN · Sample efficiencysteps to 90% performance: 7680 -> 5850Improved
use spectral loss (ST-GFN) instead of TB+NoveltyTB+Novelty · Sample efficiencysteps to 90% performance: 8350 -> 5850Improved
use ST-GFN instead of TBTB · Total wall-clock timewall-clock time (s): 544s -> 404sImproved
use ST-GFN instead of TB+NoveltyTB+Novelty · Total wall-clock timewall-clock time (s): 548s -> 404sImproved
add spectral regularization and RFF policy embeddingTB · BitSequence (90% action failure)top-100 rewardImproved
add autocorrelated intrinsic rewardTB · HyperGrid 32x32 (64 modes)modes foundImproved
add adaptive spectral regularization (learnable lambda)ST-GFN · Training dynamicsoptimization rateMixed

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