Search Results for author: Yunxiao Shi

Found 14 papers, 4 papers with code

A Learnable Agent Collaboration Network Framework for Personalized Multimodal AI Search Engine

no code implementations1 Sep 2024 Yunxiao Shi, Min Xu, Haimin Zhang, Xing Zi, Qiang Wu

This paper proposes a novel AI Search Engine framework called the Agent Collaboration Network (ACN).

AI Agent RAG

CTR-KAN: KAN for Adaptive High-Order Feature Interaction Modeling

1 code implementation16 Aug 2024 Yunxiao Shi, Wujiang Xu, Haimin Zhang, Qiang Wu, Yongfeng Zhang, Min Xu

Modeling high-order feature interactions is critical for click-through rate (CTR) prediction, yet traditional approaches often face challenges in balancing predictive accuracy and computational efficiency.

Click-Through Rate Prediction Computational Efficiency +2

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer

no code implementations16 Jul 2024 Pierre-David Letourneau, Manish Kumar Singh, Hsin-Pai Cheng, Shizhong Han, Yunxiao Shi, Dalton Jones, Matthew Harper Langston, Hong Cai, Fatih Porikli

We present Polynomial Attention Drop-in Replacement (PADRe), a novel and unifying framework designed to replace the conventional self-attention mechanism in transformer models.

Computational Efficiency Image Classification +3

SLMRec: Distilling Large Language Models into Small for Sequential Recommendation

1 code implementation28 May 2024 Wujiang Xu, Qitian Wu, Zujie Liang, Jiaojiao Han, Xuying Ning, Yunxiao Shi, Wenfang Lin, Yongfeng Zhang

Motivated by this insight, we empower small language models for SR, namely SLMRec, which adopt a simple yet effective knowledge distillation method.

Knowledge Distillation Language Modeling +4

ERAGent: Enhancing Retrieval-Augmented Language Models with Improved Accuracy, Efficiency, and Personalization

1 code implementation6 May 2024 Yunxiao Shi, Xing Zi, Zijing Shi, Haimin Zhang, Qiang Wu, Min Xu

The efficiency and personalization characteristics of ERAGent are supported by the Experiential Learner module which makes the AI assistant being capable of expanding its knowledge and modeling user profile incrementally.

Question Answering RAG +2

Parameter Hierarchical Optimization for Visible-Infrared Person Re-Identification

no code implementations11 Apr 2024 Zeng Yu, Yunxiao Shi

Importantly, in the alignment process of SAS and AAL, all the parameters are immediately optimized with optimization principles rather than training the whole network, which yields a better parameter training manner.

Person Re-Identification

FutureDepth: Learning to Predict the Future Improves Video Depth Estimation

no code implementations19 Mar 2024 Rajeev Yasarla, Manish Kumar Singh, Hong Cai, Yunxiao Shi, Jisoo Jeong, Yinhao Zhu, Shizhong Han, Risheek Garrepalli, Fatih Porikli

In this paper, we propose a novel video depth estimation approach, FutureDepth, which enables the model to implicitly leverage multi-frame and motion cues to improve depth estimation by making it learn to predict the future at training.

Decoder Future prediction +1

DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions

no code implementations CVPR 2024 Yunxiao Shi, Manish Kumar Singh, Hong Cai, Fatih Porikli

Leveraging the initial depths and features from this network, we uplift the 2D features to form a 3D point cloud and construct a 3D point transformer to process it, allowing the model to explicitly learn and exploit 3D geometric features.

Depth Completion

Causal Disentanglement for Regulating Social Influence Bias in Social Recommendation

no code implementations6 Mar 2024 Li Wang, Min Xu, Quangui Zhang, Yunxiao Shi, Qiang Wu

Building upon this insight, we propose a disentangled encoder that focuses on disentangling user and item embeddings into interest and social influence embeddings.

Causal Inference Disentanglement +1

Structure-Attentioned Memory Network for Monocular Depth Estimation

no code implementations10 Sep 2019 Jing Zhu, Yunxiao Shi, Mengwei Ren, Yi Fang, Kuo-Chin Lien, Junli Gu

To this end, we introduce a new Structure-Oriented Memory (SOM) module to learn and memorize the structure-specific information between RGB image domain and the depth domain.

Domain Adaptation Monocular Depth Estimation

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