Search Results for author: Yilun Huang

Found 7 papers, 4 papers with code

Enhancing Multimodal Large Language Models with Vision Detection Models: An Empirical Study

no code implementations31 Jan 2024 Qirui Jiao, Daoyuan Chen, Yilun Huang, Yaliang Li, Ying Shen

Despite the impressive capabilities of Multimodal Large Language Models (MLLMs) in integrating text and image modalities, challenges remain in accurately interpreting detailed visual elements.

Hallucination object-detection +3

DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network

1 code implementation CVPR 2023 Xuan Shen, Yaohua Wang, Ming Lin, Yilun Huang, Hao Tang, Xiuyu Sun, Yanzhi Wang

To this end, a novel framework termed Mathematical Architecture Design for Deep CNN (DeepMAD) is proposed to design high-performance CNN models in a principled way.

Image Classification Neural Architecture Search

Enhancing Model Performance in Multilingual Information Retrieval with Comprehensive Data Engineering Techniques

no code implementations14 Feb 2023 Qi Zhang, Zijian Yang, Yilun Huang, Ze Chen, Zijian Cai, Kangxu Wang, Jiewen Zheng, Jiarong He, Jin Gao

In this paper, we present our solution to the Multilingual Information Retrieval Across a Continuum of Languages (MIRACL) challenge of WSDM CUP 2023\footnote{https://project-miracl. github. io/}.

Data Augmentation Information Retrieval +1

A Semantic Alignment System for Multilingual Query-Product Retrieval

no code implementations5 Aug 2022 Qi Zhang, Zijian Yang, Yilun Huang, Ze Chen, Zijian Cai, Kangxu Wang, Jiewen Zheng, Jiarong He, Jin Gao

Our models are all trained with cross-entropy loss to classify the query-product pairs into ESCI 4 categories at first, and then we use weighted sum with the 4-class probabilities to get the score for ranking.

Data Augmentation Retrieval +1

An Effective Way for Cross-Market Recommendation with Hybrid Pre-Ranking and Ranking Models

1 code implementation2 Mar 2022 Qi Zhang, Zijian Yang, Yilun Huang, Jiarong He, Lixiang Wang

The Cross-Market Recommendation task of WSDM CUP 2022 is about finding solutions to improve individual recommendation systems in resource-scarce target markets by leveraging data from similar high-resource source markets.

feature selection Recommendation Systems

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