Showing 2025Show all
2 papers · 1 filter
cs.CV2025
Training-Free Reward-Guided Image Editing via Trajectory Optimal Control
Jinho Chang, Jaemin Kim, Jong Chul Ye
Recent advancements in diffusion and flow-matching models have demonstrated remarkable capabilities in high-fidelity image synthesis. A prominent line of research involves reward-g…
cs.AI2025
Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs
Jaemin Kim, Hangeol Chang, Hyunmin Hwang +2
Large Language Models (LLMs) have demonstrated remarkable general capabilities, but enhancing skills such as reasoning often demands substantial computational resources and may com…