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

Shuai Li

8 indexed papers

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

Publications per year

8
26

Top categories

AI×5Vision×4Crypto×2Sound×1Distributed×1ML×1

Frequent co-authors

Garvin Guo2×
Yu Chen2×
Xiang Wang2×
Xinpei Zhao2×
Huaxing Liu2×
Aleksei Khalin1×

Research Timeline

2026
Can Drift-Adaptive Malware Detectors Be Made Robust? Attacks and Defenses Under White-Box and Black-Box Threats

The paper proposes a universal robustification framework to enhance drift-adaptive malware detectors against combined concept drift and adversarial attacks, significantly reducing attack success rates across various threat models.

VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models

VertMark introduces a novel, unified, and training-free framework to embed robust watermarks into vertical domain pre-trained language models (VPLMs) for copyright protection across multiple specialized domains.

CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations

The paper introduces CardioLens, a rigorous evaluation testbed for multi-sequence Cardiac MRI, which reveals that current Multimodal Large Language Models (MLLMs) exhibit a significant 'clinical reality gap' and perform poorly when simulating real-world cardiac interpretation workflows.

Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning

The paper deconstructs latent visual reasoning tokens into components and finds that the performance gains are primarily due to boundary markers and attention patterns, not the tokens' ability to encode visual evidence.

Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains

The paper argues that observed gains in multimodal agents using tools may be due to learning tool-calling patterns rather than genuine capability expansion, finding that tool access provides little consistent aggregate improvement.

Boosting Multimodal Federated Learning via Chained Modality Optimization

The paper proposes FedMChain, a novel federated learning framework that structures multimodal training into sequential phases to mitigate modality competition and improve model performance while reducing communication overhead.

Audio-Anchored Fusion of Multi-Ratio DiT Reconstruction Residuals for Cross-Domain Audio Deepfake Detection

This paper proposes using a Diffusion Transformer as a frozen reconstruction probe for audio deepfake detectors, achieving state-of-the-art performance on ASVspoof 5 Eval and ITW Full.

NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge

This paper reviews the NTIRE 2026 Low-light Enhancement competition, which merged misaligned smartphone images into a single, clean image in low-light conditions, achieving improvements of up to +6.49 dB in PSNR and +0.0101 in SSIM.

Highlighted terms show continued research focus across papers

Papers

cs.CVEmpiricalRecentAug 10, 2026

NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge

Aleksei Khalin, Egor Ershov, Artyom Panshin, Sergey Korchagin +45 more

This paper reviews the NTIRE 2026 Low-light Enhancement competition, which merged misaligned smartphone images into a single, clean image in low-light conditions, achieving improvements of up to +6.49…

View →
cs.SDcs.AIEmpirical
Recent
Jul 29, 2026

Audio-Anchored Fusion of Multi-Ratio DiT Reconstruction Residuals for Cross-Domain Audio Deepfake Detection

Haotian Mo, Jie Liu, Siqi Shen, Songzhu Mei +7 more

This paper proposes using a Diffusion Transformer as a frozen reconstruction probe for audio deepfake detectors, achieving state-of-the-art performance on ASVspoof 5 Eval and ITW Full.

View →
cs.CVcs.AIRecentJun 1, 2026

Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains

Garvin Guo, Donglei Yu, Yu Chen, Xiang Wang +5 more

The paper argues that observed gains in multimodal agents using tools may be due to learning tool-calling patterns rather than genuine capability expansion, finding that tool access provides little co…

View →
cs.DCcs.AIRecentJun 1, 2026

Boosting Multimodal Federated Learning via Chained Modality Optimization

Zixin Zhang, Fan Qi, Shuai Li, Xiaoshan Yang +1 more

The paper proposes FedMChain, a novel federated learning framework that structures multimodal training into sequential phases to mitigate modality competition and improve model performance while reduc…

View →
cs.CVcs.AIRecentMay 31, 2026

Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning

Garvin Guo, Yu Chen, Xiang Wang, Shuai Li +3 more

The paper deconstructs latent visual reasoning tokens into components and finds that the performance gains are primarily due to boundary markers and attention patterns, not the tokens' ability to enco…

View →
cs.CVcs.AIcs.LGRecentMay 28, 2026

CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations

Zixian Su, Hongkai Zhang, Fan Gao, Encheng Su +11 more

The paper introduces CardioLens, a rigorous evaluation testbed for multi-sequence Cardiac MRI, which reveals that current Multimodal Large Language Models (MLLMs) exhibit a significant 'clinical reali…

View →
cs.CRMay 4, 2026

VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models

Cong Kong, Xin Cheng, Zhaoxia Yin, Shuai Li +2 more

VertMark introduces a novel, unified, and training-free framework to embed robust watermarks into vertical domain pre-trained language models (VPLMs) for copyright protection across multiple specializ…

View →
cs.CRApr 8, 2026

Can Drift-Adaptive Malware Detectors Be Made Robust? Attacks and Defenses Under White-Box and Black-Box Threats

Adrian Shuai Li, Md Ajwad Akil, Elisa Bertino

The paper proposes a universal robustification framework to enhance drift-adaptive malware detectors against combined concept drift and adversarial attacks, significantly reducing attack success rates…

View →