PolyX-Research/Robust-U1
Official implementation of Robust-U1, a unified multimodal LLM that self-recovers corrupted visual content for robust understanding.
Collecting fresh signals — velocity needs a few days of history.
collecting data…
star history
Robust-U1 is an ICML 2026 paper implementation that extends multimodal large language models to handle degraded or corrupted images. The model performs self-recovery of visual content and reasons over the restored input to improve robustness under real-world image degradations. The repository provides code, pretrained models, and an online demo for reproducing the results.
Frequently asked
- What is PolyX-Research/Robust-U1?
- Official implementation of Robust-U1, a unified multimodal LLM that self-recovers corrupted visual content for robust understanding.
- Is Robust-U1 open source?
- Yes — PolyX-Research/Robust-U1 is an open-source project tracked on heatdrop.
- What language is Robust-U1 written in?
- PolyX-Research/Robust-U1 is primarily written in Python.
- How popular is Robust-U1?
- PolyX-Research/Robust-U1 has 502 stars on GitHub.
- Where can I find Robust-U1?
- PolyX-Research/Robust-U1 is on GitHub at https://github.com/PolyX-Research/Robust-U1.