Search Results for author: Jiaxin Yu

Found 6 papers, 2 papers with code

MetaBGM: Dynamic Soundtrack Transformation For Continuous Multi-Scene Experiences With Ambient Awareness And Personalization

no code implementations5 Sep 2024 Haoxuan Liu, ZiHao Wang, HaoRong Hong, Youwei Feng, Jiaxin Yu, Han Diao, Yunfei Xu, Kejun Zhang

This paper introduces MetaBGM, a groundbreaking framework for generating background music that adapts to dynamic scenes and real-time user interactions.

Security Code Review by Large Language Models

no code implementations29 Jan 2024 Jiaxin Yu, Peng Liang, Yujia Fu, Amjed Tahir, Mojtaba Shahin, Chong Wang, Yangxiao Cai

Specifically, we compared the performance of 6 LLMs under five different prompts with the state-of-the-art static analysis tools to detect and analyze security defects.

Defect Detection

MonoGAE: Roadside Monocular 3D Object Detection with Ground-Aware Embeddings

no code implementations30 Sep 2023 Lei Yang, Jiaxin Yu, Xinyu Zhang, Jun Li, Li Wang, Yi Huang, Chuang Zhang, Hong Wang, Yiming Li

We discover that most existing monocular 3D object detectors rely on the ego-vehicle prior assumption that the optical axis of the camera is parallel to the ground.

Autonomous Driving Monocular 3D Object Detection +1

Latent Dynamic Networked System Identification with High-Dimensional Networked Data

no code implementations29 Sep 2023 Jiaxin Yu, Yanfang Mo, S. Joe Qin

Networked dynamic systems are ubiquitous in various domains, such as industrial processes, social networks, and biological systems.

Dimensionality Reduction

Relation-Specific Attentions over Entity Mentions for Enhanced Document-Level Relation Extraction

1 code implementation NAACL 2022 Jiaxin Yu, Deqing Yang, Shuyu Tian

Compared with traditional sentence-level relation extraction, document-level relation extraction is a more challenging task where an entity in a document may be mentioned multiple times and associated with multiple relations.

Document-level Relation Extraction Relation +2

Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction

1 code implementation ACL 2021 Li Cui, Deqing Yang, Jiaxin Yu, Chengwei Hu, Jiayang Cheng, Jingjie Yi, Yanghua Xiao

As a typical task of continual learning, continual relation extraction (CRE) aims to extract relations between entities from texts, where the samples of different relations are delivered into the model continuously.

Continual Learning Continual Relation Extraction +1

Cannot find the paper you are looking for? You can Submit a new open access paper.