Search Results for author: Yao Zhou

Found 22 papers, 4 papers with code

Optimizing Singular Spectrum for Large Language Model Compression

no code implementations20 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.

Language Modeling Language Modelling +3

Collaborative Diffusion Model for Recommender System

no code implementations31 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.

Denoising model +1

HiMix: Reducing Computational Complexity in Large Vision-Language Models

no code implementations17 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.

Decoder

Manga Generation via Layout-controllable Diffusion

no code implementations26 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.

Semantic correspondence

Pear: Pruning and Sharing Adapters in Visual Parameter-Efficient Fine-Tuning

no code implementations29 Sep 2024 Yibo Zhong, Yao Zhou

Adapters have been widely explored to alleviate computational and storage costs when fine-tuning pretrained foundation models.

parameter-efficient fine-tuning

Low-Rank Interconnected Adaptation across Layers

1 code implementation13 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 $W$.

parameter-efficient fine-tuning

Rethinking Low-Rank Adaptation in Vision: Exploring Head-Level Responsiveness across Diverse Tasks

no code implementations13 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.

Transfer Learning

Side Information-Driven Session-based Recommendation: A Survey

no code implementations27 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.

Session-Based Recommendations Survey

Retrieval-based Knowledge Augmented Vision Language Pre-training

no code implementations27 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.

Entity Linking Knowledge Graphs +5

Towards High-Order Complementary Recommendation via Logical Reasoning Network

1 code implementation9 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.

Logical Reasoning Negation +2

A Neural Vocoder Based Packet Loss Concealment Algorithm

no code implementations26 Mar 2022 Yao Zhou, Changchun Bao

The packet loss problem seriously affects the quality of service in Voice over IP (VoIP) sceneries.

Packet Loss Concealment

From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systems

no code implementations28 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.

counterfactual Explainable Models +2

Robust Federated Learning for Neural Networks

no code implementations1 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.

Federated Learning

GAN-based Recommendation with Positive-Unlabeled Sampling

no code implementations12 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.

Generative Adversarial Network Information Retrieval +2

Adversarial Robustness through Bias Variance Decomposition: A New Perspective for Federated Learning

no code implementations18 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.

Adversarial Robustness Federated Learning +1

DA4AD: End-to-End Deep Attention-based Visual Localization for Autonomous Driving

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.

Autonomous Driving Deep Attention +1

Learning Efficient Video Representation with Video Shuffle Networks

no code implementations26 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.

Video Recognition

DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registration

no code implementations10 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.

Point Cloud Registration

Optimizing the Wisdom of the Crowd: Inference, Learning, and Teaching

no code implementations23 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.

Unlearn What You Have Learned: Adaptive Crowd Teaching with Exponentially Decayed Memory Learners

1 code implementation17 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.

Diversity

Modelling Sentence Pairs with Tree-structured Attentive Encoder

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.

Paraphrase Identification Question Selection +2

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