activity
20242026
collaborators

5 papers

cs.LG2026

Gradient Preconditioning for Efficient and Reliable Reward-Guided Generation

Jisung Hwang, Minhyuk Sung

We propose a gradient preconditioning method that makes reward-guided generation with one-step generative models both efficient and reliable. Test-time noise optimization can unloc…

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.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…

cs.CV2025

Moment- and Power-Spectrum-Based Gaussianity Regularization for Text-to-Image Models

Jisung Hwang, Jaihoon Kim, Minhyuk Sung

We propose a novel regularization loss that enforces standard Gaussianity, encouraging samples to align with a standard Gaussian distribution. This facilitates a range of downstrea…

cs.CV2024

MemBench: Memorized Image Trigger Prompt Dataset for Diffusion Models

Chunsan Hong, Tae-Hyun Oh, Minhyuk Sung

Diffusion models have achieved remarkable success in Text-to-Image generation tasks, leading to the development of many commercial models. However, recent studies have reported tha…