4 papers · 1 filter
Unbalanced W-Flow: Unbalanced Wasserstein Drifting under Finite-Batch Marginal Fluctuations
Jongwook Jeon, Mingue Park, Jiwon Choi +3
Teacher-free one-step generative models such as W-Flow learn directly from distributional objectives, with the Sinkhorn divergence providing the strongest empirical performance amo…
NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment
Jisung Hwang, Yunhong Min, Jaihoon Kim +2
We introduce the Noise-Tilted Reverse Kernel (NTRK), a reward-guided diffusion sampler that injects reward gradients through the noise term, leaving the pretrained reverse kernel u…
Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion
Jaihoon Kim, Taehoon Yoon, Prin Phunyaphibarn +3
Discrete diffusion models have emerged as powerful frameworks for generating structured categorical data. However, efficiently sampling from reward-tilted distributions remains a f…
Demystifying Transition Matching: When and Why It Can Beat Flow Matching
Jaihoon Kim, Rajarshi Saha, Minhyuk Sung +1
Flow Matching (FM) underpins many state-of-the-art generative models, yet recent results indicate that Transition Matching (TM) can achieve higher quality with fewer sampling steps…