collaborators

8 papers

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.CV2026

Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models

Prin Phunyaphibarn, Phillip Y. Lee, Jaihoon Kim +1

Classifier-Free Guidance (CFG) is a fundamental technique in training conditional diffusion models. The common practice for CFG-based training is to use a single network to learn b…

cs.CV2025

MatLat: Material Latent Space for PBR Texture Generation

Kyeongmin Yeo, Yunhong Min, Jaihoon Kim +1

We propose a generative framework for producing high-quality PBR textures on a given 3D mesh. As large-scale PBR texture datasets are scarce, our approach focuses on effectively le…

cs.CV2025

Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing

Jaihoon Kim, Taehoon Yoon, Jisung Hwang +1

We propose an inference-time scaling approach for pretrained flow models. Recently, inference-time scaling has gained significant attention in LLMs and diffusion models, improving…