Yukun Cao - OpenReview
Yukun Cao Pronouns: he/him PhD student, University of Science and Technology of China Joined May 2022
Yukun Cao - OpenReview
Yukun Cao Associate Professor, College of Computer Science and Technology, Shanghai University of Electric Power Joined October 2023
Yuan Feng1;3;y , Yukun Cao1;3;y, Hairu Wang1;3, Xike Xie2;3; , and S. Kevin Zhou2;3 1School of Computer Science, University of Science and Technology of China (USTC), China 2School of Biomedical Engineering, USTC, China 3Data Darkness Lab, MIRACLE Center, Suzhou Institute for Advanced Research, USTC, China
Identify Critical KV Cache in LLM Inference from an Output...
2024年9月23日 · Large language models have driven numerous paradigm shifts in the field of natural language processing, achieving remarkable success in various real-world applications through scaling model size...
Mayfly: a Neural Data Structure for Graph Stream Summarization
2024年1月16日 · A graph is a structure made up of vertices and edges used to represent complex relationships between entities, while a graph stream is a continuous flow of graph updates that convey evolving...
Meta-sketch: A Neural Data Structure for Estimating Item...
2022年5月16日 · To estimate item frequencies of data streams with limited space, sketches are widely used in real applications, including real-time web analytics, network monitoring, and self-driving. Sketches can be viewed as a model which maps the identifier of a stream item to the corresponding frequency domain. Starting from the premise, we envision a neural data …
Prototype-based Optimal Transport for Out-of-Distribution …
Detecting Out-of-Distribution (OOD) inputs is crucial for improving the reliability of deep neural networks in the real-world deployment. In this paper, inspired by the inherent distribution shift between ID and OOD data, we propose a novel method that leverages optimal transport to measure the distribution discrepancy between test inputs and ID prototypes. The resulting …
Abstract To estimate item frequencies of data streams with limited space, sketches are widely used in real applications, including real-time web analytics, network monitoring, and self-driving. Sketches can be viewed as a model which maps the identifier of a stream item to the corresponding frequency domain. Starting from the premise, we envision a neural data …
ICLR 2025 Conference Submissions - OpenReview
22 Sep 2024 (modified: 12 Nov 2024) ICLR 2025 Conference Withdrawn Submission Readers: Everyone
Junlin Lv - OpenReview
Junlin Lv Pronouns: he/him MS student, University of Science and Technology of China Joined August 2024