558 citations
- Nanjing UniversityCN38 papers
- Shanghai Jiao Tong UniversityCN15 papers
- Stockholm UniversitySE14 papers
- University of Science and Technology of ChinaCN14 papers
- Centre National de la Recherche ScientifiqueFR13 papers
- Chinese Academy of SciencesCN13 papers
- Iowa State UniversityUS13 papers
- McGill UniversityCA13 papers
- University of WashingtonUS13 papers
- A. Alikhanyan National LaboratoryAM12 papers
- Boston UniversityUS12 papers
- Brandeis UniversityUS12 papers
99 papers
Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints
Zirui Huang, Yunlong Mao, Wei Tong +3
The proliferation of customized Large Language Models (LLMs) poses critical risks of Data Intellectual Property (Data IP) infringement via unauthorized fine-tuning on proprietary d…
A Token/KV-Cache Communication Media Selection and Resource Allocation Strategy for Multi-Agent Collaboration
Lipeng Dai, Luping Xiang, Kun Yang
The convergence of large language models (LLMs) with 6G networks is fostering a paradigm of autonomous multi-agent cooperation, which in turn is expected to substantially increase…
Study of Particle Fluence Effects on Collected Charge and Depletion Voltage of the ATLAS IBL Planar Pixel Sensors
ATLAS Collaboration
After ten years of operation at the LHC, the planar pixel sensors of the innermost barrel layer of the ATLAS Pixel detector have accumulated an average bulk damage fluence in exces…
Adversarial Batch Representation Augmentation for Batch Correction in High-Content Cellular Screening
Lei Tong, Xujing Yao, Adam Corrigan +6
High-Content Screening routinely generates massive volumes of cell painting images for phenotypic profiling. However, technical variations across experimental executions inevitably…
Optical signatures of -1/3 fractional quantum anomalous Hall state in twisted MoTe2
Haiyang Pan, Shunshun Yang, Yuzhu Wang +9
The discovery of fractional charge excitations in new platforms offers crucial insights into strongly correlated quantum phases. While a range of fractional quantum anomalous Hall…
AtPatch: Debugging Transformers via Hot-Fixing Over-Attention
Shihao Weng, Yang Feng, Jincheng Li +3
Transformer-based deep neural networks (DNNs) affected by backdoor attacks and unfairness typically exhibit anomalous attention patterns, leading to over-attend to backdoor trigger…