no code implementations • 20 Feb 2025 • Dengjie Li, Tiancheng Shen, Yao Zhou, Baisong Yang, Zhongying Liu, Masheng Yang, Bernard Ghanem, Yibo Yang, Yujie Zhong, Ming-Hsuan Yang
In this work, we introduce SoCo (Singular spectrum optimization for large language model Compression), a novel compression framework that learns to rescale the decomposed components of SVD in a data-driven manner.
no code implementations • 31 Jan 2025 • Gyuseok Lee, Yaochen Zhu, Hwanjo Yu, Yao Zhou, Jundong Li
Diffusion-based recommender systems (DR) have gained increasing attention for their advanced generative and denoising capabilities.
no code implementations • 17 Jan 2025 • Xuange Zhang, Dengjie Li, Bo Liu, Zenghao Bao, Yao Zhou, Baisong Yang, Zhongying Liu, Yujie Zhong, Zheng Zhao, Tongtong Yuan
This is inspired by a reassessment of the efficiency of vision and language information transmission in the language decoder of LVLMs.
no code implementations • 26 Dec 2024 • Siyu Chen, Dengjie Li, Zenghao Bao, Yao Zhou, Lingfeng Tan, Yujie Zhong, Zheng Zhao
However, there are few studies on generating multi-panel Manga (Japanese comics) solely based on plain text.
no code implementations • 29 Sep 2024 • Yibo Zhong, Yao Zhou
Adapters have been widely explored to alleviate computational and storage costs when fine-tuning pretrained foundation models.
1 code implementation • 13 Jul 2024 • Yibo Zhong, Yao Zhou
Low-rank adaptation (LoRA) is a powerful parameter-efficient fine-tuning method that utilizes low-rank projectors $A$ and $B$ to learn weight updates $\Delta W$ for adaptation targets $W$.
no code implementations • 13 Apr 2024 • Yibo Zhong, Yao Zhou
Additionally, given the different responsiveness of heads to diverse visual tasks, our proposed method dynamically activates a subset of the approximated heads that are tailored to the current task.
no code implementations • 27 Feb 2024 • Xiaokun Zhang, Bo Xu, Chenliang Li, Yao Zhou, Liangyue Li, Hongfei Lin
Emerging efforts incorporate various kinds of side information into their methods for enhancing task performance.
no code implementations • 17 Oct 2023 • Xin Su, Yao Zhou, Zifei Shan, Qian Chen
Then we learn a semantic representation of MeKB for the cross-domain recommendation.
no code implementations • 27 Apr 2023 • Jiahua Rao, Zifei Shan, Longpo Liu, Yao Zhou, Yuedong Yang
With the recent progress in large-scale vision and language representation learning, Vision Language Pre-training (VLP) models have achieved promising improvements on various multi-modal downstream tasks.
1 code implementation • 9 Dec 2022 • Longfeng Wu, Yao Zhou, Dawei Zhou
Finally, we further propose a hybrid network that is jointly optimized for learning a more generic product representation.
no code implementations • 26 Mar 2022 • Yao Zhou, Changchun Bao
The packet loss problem seriously affects the quality of service in Voice over IP (VoIP) sceneries.
no code implementations • 28 Oct 2021 • Yao Zhou, Haonan Wang, Jingrui He, Haixun Wang
With the prevalence of deep learning based embedding approaches, recommender systems have become a proven and indispensable tool in various information filtering applications.
no code implementations • 1 Jan 2021 • Yao Zhou, Jun Wu, Jingrui He
In federated learning, data is distributed among local clients which collaboratively train a prediction model using secure aggregation.
no code implementations • 12 Dec 2020 • Yao Zhou, Jianpeng Xu, Jun Wu, Zeinab Taghavi Nasrabadi, Evren Korpeoglu, Kannan Achan, Jingrui He
Recommender systems are popular tools for information retrieval tasks on a large variety of web applications and personalized products.
no code implementations • 18 Sep 2020 • Yao Zhou, Jun Wu, Haixun Wang, Jingrui He
In this work, we show that this paradigm might inherit the adversarial vulnerability of the centralized neural network, i. e., it has deteriorated performance on adversarial examples when the model is deployed.
no code implementations • ECCV 2020 • Yao Zhou, Guowei Wan, Shenhua Hou, Li Yu, Gang Wang, Xiaofei Rui, Shiyu Song
We present a visual localization framework based on novel deep attention aware features for autonomous driving that achieves centimeter level localization accuracy.
no code implementations • 26 Nov 2019 • Pingchuan Ma, Yao Zhou, Yu Lu, Wei zhang
To this end, we propose the video shuffle, a parameter-free plug-in component that efficiently reallocates the inputs of 2D convolution so that its receptive field can be extended to the temporal dimension.
no code implementations • 10 May 2019 • Weixin Lu, Guowei Wan, Yao Zhou, Xiangyu Fu, Pengfei Yuan, Shiyu Song
We present DeepICP - a novel end-to-end learning-based 3D point cloud registration framework that achieves comparable registration accuracy to prior state-of-the-art geometric methods.
no code implementations • 23 Jun 2018 • Yao Zhou, Jingrui He
The unprecedented demand for large amount of data has catalyzed the trend of combining human insights with machine learning techniques, which facilitate the use of crowdsourcing to enlist label information both effectively and efficiently.
1 code implementation • 17 Apr 2018 • Yao Zhou, Arun Reddy Nelakurthi, Jingrui He
With the increasing demand for large amount of labeled data, crowdsourcing has been used in many large-scale data mining applications.
1 code implementation • COLING 2016 • Yao Zhou, Cong Liu, Yan Pan
We describe an attentive encoder that combines tree-structured recursive neural networks and sequential recurrent neural networks for modelling sentence pairs.