Jiaqi-hkust/Robust-R1-SFT
4B
โข
Updated
โข
54
โข
4
Jiaqi Tang PRO
Jiaqi-hkust
AI & ML interests
Multi-modal Large Language Model
Recent Activity
authored
a paper
about 16 hours ago
LongVideoAgent: Multi-Agent Reasoning with Long Videos
replied to
their
post
1 day ago
We have open-sourced Robust-R1 (AAAI 2026 Oral), a new paradigm in the field of anti-degradation and robustness enhancement for multimodal large models.
Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that focuses solely on visual encoder generalization, suffering from limited interpretability and isolated optimization. To overcome these limitations, we propose Robust-R1, a novel framework that explicitly models visual degradations through structured reasoning chains. Our approach integrates: (i) supervised fine-tuning for degradation-aware reasoning foundations, (ii) reward-driven alignment for accurately perceiving degradation parameters, and (iii) dynamic reasoning depth scaling adapted to degradation intensity. To facilitate this approach, we introduce a specialized 11K dataset featuring realistic degradations synthesized across four critical real-world visual processing stages, each annotated with structured chains connecting degradation parameters, perceptual influence, pristine semantic reasoning chain, and conclusion. Comprehensive evaluations demonstrate state-of-the-art robustness: Robust-R1 outperforms all general and robust baselines on the real-world degradation benchmark R-Bench, while maintaining superior anti-degradation performance under multi-intensity adversarial degradations on MMMB, MMStar, and RealWorldQA.
We have made all of our papers, codes, data, model weights and demos fully open-source:
Paper: https://huggingface.co/papers/2512.17532 (help us to upvote)
GitHub code: https://github.com/jqtangust/Robust-R1 (help us to star)
HF model: https://huggingface.co/Jiaqi-hkust/Robust-R1
HF data: https://huggingface.co/datasets/Jiaqi-hkust/Robust-R1
HF Space: https://huggingface.co/spaces/Jiaqi-hkust/Robust-R1
We sincerely invite everyone to give it a try.
upvoted
a
paper
2 days ago
LongVideoAgent: Multi-Agent Reasoning with Long Videos
Organizations
None yet