Yang Wang
8 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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.
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 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 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 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 is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.
This paper presents MRC, an open, production-grade transport designed for large-scale AI/ML training over best-effort Ethernet.
This paper proposes TSGR, a generative retrieval framework for industrial e-commerce search that incorporates value awareness into item representation and candidate ranking.
Papers
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.