Episode
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
- Podcast
- Daily Paper Cast
- Published
- Jun 13, 2026
- Duration seconds
- 1228
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/8c03bbf5
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/robust-u1-can-mllms-self-recover-corrupted-visual-content-for-robust-understanding/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/robust-u1-can-mllms-self-recover-corrupted-visual-content-for-robust-understanding.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 71 | cs.CV, cs.AI, cs.CL Authors: Jiaqi Tang, Jianmin Chen, Youyang Zhai, Wei Wei, Runtao Liu, Mengjie Zhao, Xiangyu Wu, Qingfa Xiao, Qifeng Chen Title: Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Arxiv: http://arxiv.org/abs/2606.08063v1 Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in visual understanding, yet their performance degrades significantly under real-world visual corruptions. While existing robustness enhancement approaches exist, they are limited: black-box feature alignment lacks interpretability, and white-box text-based reasoning cannot restore lost pixel-level details. This work investigates a fundamental research question: Can MLLMs recover corrupted visual content by themselves? To address this, we propose Robust-U1, a novel framework that equips MLLMs with explicit visual self-recovery capability for robust understanding. The approach comprises three core stages: supervised fine-tuning for initial reconstruction, reinforcement learning with dual rewards (pixel-level SSIM and semantic-level CLIP similarity) for aligning high visual quality, and multimodal reasoning that jointly considers both the corrupted input and the recovered image. Extensive experiments demonstrate that Robust-U1 achieves state-of-the-art robustness on the real-world corruption benchmark and maintains superior performance under adversarial corruptions on general VQA benchmarks. Analysis confirms that high-quality visual recovery directly enhances reasoning performance, establishing self-recovery as a critical mechanism for robust visual understanding. The source code is available at https://github.com/jqtangust/Robust-U1.