Seminar Talks

Presented at MLVC Lab, Kyung Hee University Global Campus

Reasoning Models / Reasoning Image Restoration

Seminar covering the use of large language models and vision-language approaches in visual reasoning and restoration. We explored recent innovations in step-wise reasoning and multimodal agents for complex image tasks.

Referenced Papers

Multi-Task Learning Perspective for Diffusion Models

Presents a multi-task learning viewpoint on modern diffusion models. It discusses task transferability, negative transfer challenges, and the use of mixture-of-experts to solve denoising in a synergistic fashion.

Referenced Papers

Task-Oriented Diffusion for Image Restoration

A deep dive into diffusion-based models tailored for specific restoration tasks, including Ambient Diffusion, ResShift for super-resolution, and DiffBIR’s two-stage blind restoration pipeline.

Referenced Papers

Any-Size Diffusion & ResDiff (AAAI 2024)

Highlights from two AAAI-24 papers: Any-Size-Diffusion (ASD), a two-stage pipeline for text-to-image synthesis at arbitrary resolutions, and ResDiff, which unites CNN priors with diffusion guidance for efficient single-image super-resolution.

Referenced Papers

NeurIPS 2024 Paper Summaries

Summary session from NeurIPS 2024, with analyses of several key papers presented at the conference.