AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Efficient Few-Step Solution Generation via Discrete Flow Matching for Combinatorial Optimization

Yuanshu Li, Di Wang, Wei Du, Xuan Wu, Peng Zhao, Yubin Xiao, You Zhou

AAAI 2026 · Image generation › Fast diffusion sampling · approach: Flow matching distillation · 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 velocity-based consistency loss (ablation)EFLOCO · TSP, 10-step inferenceoptimality gap (%): 0.14 -> 0.05Improved
add velocity-based consistency loss (ablation)EFLOCO · TSP, 2-step inferenceoptimality gap (%): 0.19 -> 0.07Improved
use ATSS in training and inference instead of uniform training + linear (ablation)DIFUSCO retrained · TSP, 10 stepsoptimality gap (%): 0.5868 -> 0.4352Improved
use ATSS in training and inference instead of uniform training + linear (ablation)DIFUSCO retrained · TSP, 20 stepsoptimality gap (%): 0.5370 -> 0.3616Improved
use ATSS inference only (uniform training) vs cosine inference (ablation)DIFUSCO retrained · TSP, 10 stepsoptimality gap (%): 0.5471 -> 0.4743Improved
use EFLOCO instead of DIFUSCO (greedy)NAR TSP solver · TSP-100optimality gap (%): 0.23 -> 0.38Hurt
use EFLOCO instead of MatNet (greedy)ATSP solver · ATSP-50optimality gap (%): 1.13 -> 0.22Improved
use EFLOCO instead of T2TCO (greedy)large TSP · TSP-500optimality gap (%): 0.91 -> 1.48Hurt
use EFLOCO instead of DIFUSCO (greedy)large TSP · TSP-500optimality gap (%): 1.75 -> 1.48Improved

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