Search Results for author: Yujie Chen

Found 16 papers, 8 papers with code

Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration

no code implementations27 Mar 2025 Yujie Chen, Haotong Qin, Zhang Zhang, Michelo Magno, Luca Benini, Yawei Li

While low-bit quantization is an efficient model compression strategy for reducing size and accelerating IR tasks, SSM suffers substantial performance drops at ultra-low bit-widths (2-4 bits), primarily due to outliers that exacerbate quantization error.

Computational Efficiency Image Restoration +4

S$^2$DN: Learning to Denoise Unconvincing Knowledge for Inductive Knowledge Graph Completion

1 code implementation20 Dec 2024 Tengfei Ma, Yujie Chen, Liang Wang, Xuan Lin, Bosheng Song, Xiangxiang Zeng

These results demonstrate the effectiveness of S$^2$DN in preserving semantic consistency and enhancing the robustness of filtering out unreliable interactions in contaminated KGs.

Denoising Inductive knowledge graph completion

Reject Threshold Adaptation for Open-Set Model Attribution of Deepfake Audio

no code implementations2 Dec 2024 Xinrui Yan, Jiangyan Yi, JianHua Tao, Yujie Chen, Hao Gu, Guanjun Li, Junzuo Zhou, Yong Ren, Tao Xu

To address the issues, we propose a novel framework for open set model attribution of deepfake audio with rejection threshold adaptation (ReTA).

Face Swapping

A Time Series is Worth Five Experts: Heterogeneous Mixture of Experts for Traffic Flow Prediction

1 code implementation26 Sep 2024 Guangyu Wang, Yujie Chen, Ming Gao, Zhiqiao Wu, Jiafu Tang, Jiabi Zhao

Accurate traffic prediction faces significant challenges, necessitating a deep understanding of both temporal and spatial cues and their complex interactions across multiple variables.

Mixture-of-Experts Prediction +2

Likelihood Based Inference in Fully and Partially Observed Exponential Family Graphical Models with Intractable Normalizing Constants

1 code implementation27 Apr 2024 Yujie Chen, Anindya Bhadra, Antik Chakraborty

These models have been successfully applied in many fields, such as the Ising model in statistical physics and count graphical models in genomics.

Bayesian Inference

Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion

1 code implementation19 Jan 2024 Cunhang Fan, Yujie Chen, Jun Xue, Yonghui Kong, JianHua Tao, Zhao Lv

This paper proposes a progressive distillation method based on masked generation features for KGC task, aiming to significantly reduce the complexity of pre-trained models.

Knowledge Graph Completion Language Modelling +1

Enhancing Low-Precision Sampling via Stochastic Gradient Hamiltonian Monte Carlo

1 code implementation25 Oct 2023 Ziyi Wang, Yujie Chen, Qifan Song, Ruqi Zhang

This paper investigates low-precision sampling via Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) with low-precision and full-precision gradient accumulators for both strongly log-concave and non-log-concave distributions.

Quantization Uncertainty Quantification

Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection

no code implementations27 Jun 2023 Shunbo Dong, Jun Xue, Cunhang Fan, Kang Zhu, Yujie Chen, Zhao Lv

The main purpose of this system is to improve the model's ability to learn precise forgery information for FSD task in low-quality scenarios.

Data Augmentation

An Online Algorithm for Chance Constrained Resource Allocation

no code implementations6 Mar 2023 Yuwei Chen, Zengde Deng, Yinzhi Zhou, Zaiyi Chen, Yujie Chen, Haoyuan Hu

This paper studies the online stochastic resource allocation problem (RAP) with chance constraints.

Bio-Inspired Adversarial Attack Against Deep Neural Networks

no code implementations30 Jun 2021 Bowei Xi, Yujie Chen, Fan Fei, Zhan Tu, Xinyan Deng

Hence in a successful physical attack against DNN, targeted motion against the system should also be considered.

Adversarial Attack Object

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