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

Yang Wang

8 indexed papers

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

Publications per year

8
26

Top categories

AI×5Sound×2Crypto×2Info Retrieval×1Networking×1HCI×1

Frequent co-authors

Chen Yang2×
Chufan Yu2×
Hanfu Chen2×
Jie Zhu2×
Jingqi Chen2×
Ke Chen2×

Research Timeline

2026
ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety

The paper introduces ProjLens, an interpretability framework that reveals that backdoor vulnerabilities in Multimodal Large Language Models (MLLMs) are encoded within a low-rank subspace of the projector, causing a measurable semantic shift in poisoned inputs.

When Are LLM Inferences Acceptable? User Reactions and Control Preferences for Inferred Personal Information

This study investigated user reactions to inferred personal information from their own ChatGPT histories, finding that acceptability is governed by context-sensitive norms regarding generation, retention, and transmission, rather than just the inference content.

FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models

FedMPT introduces a novel federated learning framework for Multi-Label Recognition (MLR) using Vision-Language Models (VLMs) by leveraging generalizable conditions to mitigate label overfitting and improve robustness.

FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models

FedMPT introduces a novel federated learning framework for Multi-Label Recognition (MLR) using Vision-Language Models (VLMs) by leveraging generalizable conditions to mitigate label overfitting and improve robustness.

MOSS-Audio Technical Report

MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.

MOSS-Audio Technical Report

MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.

The Multipath Reliable Connection (MRC) Transport

This paper presents MRC, an open, production-grade transport designed for large-scale AI/ML training over best-effort Ethernet.

TSGR: Taobao Search Generative Retrieval

This paper proposes TSGR, a generative retrieval framework for industrial e-commerce search that incorporates value awareness into item representation and candidate ranking.

Highlighted terms show continued research focus across papers

Papers

cs.IREmpiricalRecentJul 21, 2026

TSGR: Taobao Search Generative Retrieval

Tianyu Zhan, Gui Ling, Tong Xiong, Kunhai Lin +8 more

This paper proposes TSGR, a generative retrieval framework for industrial e-commerce search that incorporates value awareness into item representation and candidate ranking.

View →
cs.NIEmpiricalRecent
Jun 16, 2026

The Multipath Reliable Connection (MRC) Transport

Rip Sohan, Eric Spada, Eric Davis, Mark Handley +35 more

This paper presents MRC, an open, production-grade transport designed for large-scale AI/ML training over best-effort Ethernet.

View →
cs.SDcs.AIRecentJun 1, 2026

MOSS-Audio Technical Report

Chen Yang, Chufan Yu, Hanfu Chen, Jie Zhu +21 more

MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.

View →
cs.SDcs.AIRecentJun 1, 2026

MOSS-Audio Technical Report

Chen Yang, Chufan Yu, Hanfu Chen, Jie Zhu +21 more

MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.

View →
cs.AIRecentMay 27, 2026

FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models

Xucong Wang, Pengkun Wang, Zhe Zhao, Liheng Yu +2 more

FedMPT introduces a novel federated learning framework for Multi-Label Recognition (MLR) using Vision-Language Models (VLMs) by leveraging generalizable conditions to mitigate label overfitting and im…

View →
cs.AIRecentMay 27, 2026

FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models

Xucong Wang, Pengkun Wang, Zhe Zhao, Liheng Yu +2 more

FedMPT introduces a novel federated learning framework for Multi-Label Recognition (MLR) using Vision-Language Models (VLMs) by leveraging generalizable conditions to mitigate label overfitting and im…

View →
cs.HCcs.CRMay 11, 2026

When Are LLM Inferences Acceptable? User Reactions and Control Preferences for Inferred Personal Information

Kyzyl Monteiro, Minjung Park, Alexander Ioffrida, Angelina Sanna +5 more

This study investigated user reactions to inferred personal information from their own ChatGPT histories, finding that acceptability is governed by context-sensitive norms regarding generation, retent…

View →
cs.CRcs.AIApr 21, 2026

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety

Kun Wang, Cheng Qian, Miao Yu, Lilan Peng +5 more

The paper introduces ProjLens, an interpretability framework that reveals that backdoor vulnerabilities in Multimodal Large Language Models (MLLMs) are encoded within a low-rank subspace of the projec…

View →