Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models

About this episode

This episode discusses a novel framework for image refinement in unified multimodal models, focusing on conditional image regeneration.

🤗 Upvotes: 22 | cs.CV Authors: Jiayi Guo, Linqing Wang, Jiangshan Wang, Yang Yue, Zeyu Liu, Zhiyuan Zhao, Qinglin Lu, Gao Huang, Chunyu Wang Title: Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models Arxiv: http://arxiv.org/abs/2604.25636v1 Abstract: Unified multimodal models (UMMs) integrate visual understanding and generation within a single framework. For text-to-image (T2I) tasks, this unified capability allows UMMs to refine outputs after their initial generation, potentially extending the performance upper bound. Current UMM-based refinement methods primarily follow a refinement-via-editing (RvE) paradigm, where UMMs produce editing instructions to modify misaligned regions while preserving aligned content. However, editing instructions often describe prompt-image misalignment only coarsely, leading to incomplete refinement. Moreover, pixel-level preservation, though necessary for editing, unnecessarily restricts the effective modification space for refinement. To address these limitations, we propose Refinement via Regeneration (RvR), a novel framework that reformulates refinement as conditional image regeneration…

People in this episode

Hosts: Jingwen Liang, Gengyu Wang

Topics covered

• image refinement
• unified multimodal models
• text-to-image tasks
• conditional image regeneration
• semantic alignment
• modification space

Keywords

• image refinement
• unified multimodal models
• text-to-image
• semantic tokens
• editing instructions
• modification space
• conditional regeneration

More episodes of Daily Paper Cast

• EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments · June 13, 2026 · 24 min
• MiniMax Sparse Attention · June 13, 2026 · 26 min
• SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning · June 13, 2026 · 23 min
• InterleaveThinker: Reinforcing Agentic Interleaved Generation · June 13, 2026 · 21 min
• FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents · June 13, 2026 · 23 min
• Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? · June 13, 2026 · 20 min