cs.CVNov 4, 2026

Expanding the Quality-Coverage Frontier with Competitive Flow Matching

Authors: Wenxuan Peng, Richard Zhang, Haitian Zheng, Jaskirat Singh, Tsai-Shien Chen, Eli Shechtman, Bharath Hariharan, Hadar Averbuch-Elor, 

Organizations: Cornell University · Adobe Research

Abstract

Flow matching (FM) generators often face a quality-coverage tradeoff. Inference-time techniques such as classifier-free guidance raise quality, but at the cost of coverage. We hypothesize this limitation stems from a basic property of the objective: an intermediate noisy image could correspond to many clean images, yet the model can only predict a single velocity, at best averaging over the multiple possibilities. To mitigate this, we introduce competition among predictions during training. We achieve this by augmenting the predictor with a randomly drawn low-dimensional conditioning code zz. For each training example, we sample KK values of zz to produce KK candidate velocities that compete to explain the target, and apply the loss only to the best-matching candidate. This winner-take-all objective allows different modes to shape different predictions, rather than being averaged into a single compromise. Furthermore, this term naturally enables a new form of guidance, auxiliary conditioning scaling, which complements traditional guidance methods. Together, these two guidance mechanisms show that our method substantially improves the quality-coverage frontier. We validate on ImageNet-256, using two different testbeds, SiT and RAEv2. Given less than 3% of the original SiT pretraining compute for post-training, at the 67% Recall point, our method reduces FDr,6\mathrm{FD}_{r,6} from 19.22 to 5.91. On RAEv2, at the 70% Recall point, it reduces FDr,6\mathrm{FD}_{r,6} from 16.83 to 3.18.

Figures & tables

Appendix figures & tables19 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Posterior Augmented Flow Matching

    May 1, 2026George Stoica, Sayak Paul, Matthew Wallingford +6Flow MatchingConditional Image Generation

  2. The Velocity Deficit: Initial Energy Injection for Flow Matching

    May 14, 2026Linze Li, Zong-Wei Hong, Shen Zhang +4Flow MatchingImage Generation

  3. Energy-Guided Flow Matching

    Aug 6, 2026Haoyang Tong, Yu He, Fang Li +6Flow MatchingConditional Image Generation