Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Baiqi Wu

Baiqi Wu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Vision×2AI×2

Frequent co-authors

Yiming Wang1×
Qingming Li1×
Jiahao Chen1×
Tong Zhang1×
Shouling Ji1×
Xixiang He1×

Research Timeline

2026
StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning

The paper introduces StemBind, a diagnostic benchmark that separates perception, rule induction, and answer selection in abstract visual reasoning, revealing that the primary failure point for MLLMs is the mapping of the identified rule to the correct instance.

Order within Chaos: Capturing Intrinsic Energy Anomalies for AI-Manipulated Image Forgery Localization

The paper proposes FLAME, a novel framework that detects AI-generated image forgeries by identifying intrinsic energy anomalies caused by the diffusion process, achieving state-of-the-art localization.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIRecentJun 1, 2026

Order within Chaos: Capturing Intrinsic Energy Anomalies for AI-Manipulated Image Forgery Localization

Yiming Wang, Baiqi Wu, Qingming Li, Jiahao Chen +2 more

The paper proposes FLAME, a novel framework that detects AI-generated image forgeries by identifying intrinsic energy anomalies caused by the diffusion process, achieving state-of-the-art localization…

View →
cs.CVcs.AIRecentMay 29, 2026

StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning

Xixiang He, Baiqi Wu, Xingming Li, Ao Cheng +3 more

The paper introduces StemBind, a diagnostic benchmark that separates perception, rule induction, and answer selection in abstract visual reasoning, revealing that the primary failure point for MLLMs i…

View →