1 code implementation • 6 Feb 2025 • Yuan Feng, Junlin Lv, Yukun Cao, Xike Xie, S Kevin Zhou
This paper presents a formal study on identifying critical KV cache entries by analyzing attention output perturbation.
no code implementations • 5 Feb 2025 • Jixun Yao, Yuguang Yang, Yu Pan, Yuan Feng, Ziqian Ning, Jianhao Ye, Hongbin Zhou, Lei Xie
In this study, we propose a fine-grained preference optimization approach (FPO) to enhance the robustness of TTS systems.
no code implementations • 17 Jan 2025 • Zengyi Gao, Yukun Cao, Hairu Wang, Ao Ke, Yuan Feng, Xike Xie, S Kevin Zhou
By using the query text instead of the KG to infer the structural information of reasoning paths and employing adaptable retrieval strategies, FRAG improves retrieval quality while maintaining flexibility.
no code implementations • 17 Jan 2025 • Benjamin Kiefer, Lojze Žust, Jon Muhovič, Matej Kristan, Janez Perš, Matija Teršek, Uma Mudenagudi Chaitra Desai, Arnold Wiliem, Marten Kreis, Nikhil Akalwadi, Yitong Quan, Zhiqiang Zhong, Zhe Zhang, Sujie Liu, Xuran Chen, Yang Yang, Matej Fabijanić, Fausto Ferreira, Seongju Lee, Junseok Lee, Kyoobin Lee, Shanliang Yao, Runwei Guan, Xiaoyu Huang, Yi Ni, Himanshu Kumar, Yuan Feng, Yi-Ching Cheng, Chia-Ming Lee, Jannik Sheikh, Andreas Michel, Wolfgang Gross, Martin Weinmann, Josip Šarić, Yipeng Lin, Xiang Yang, Nan Jiang, Yutang Lu, Fei Feng, Ali Awad, Evan Lucas, Ashraf Saleem, Ching-Heng Cheng, Yu-Fan Lin, Tzu-Yu Lin, Chih-Chung Hsu
The 3rd Workshop on Maritime Computer Vision (MaCVi) 2025 addresses maritime computer vision for Unmanned Surface Vehicles (USV) and underwater.
no code implementations • 28 Nov 2024 • Guangshun Wei, Yuan Feng, Long Ma, Chen Wang, Yuanfeng Zhou, Changjian Li
To fully exploit the priors, we have designed a shape fusion module for producing an initial complete shape from multi-modality input (\ie, images and point clouds), and a follow-up shape consolidation module to obtain the final complete shape by discarding unreliable points introduced by the inconsistency from diffusion priors.
1 code implementation • 19 Sep 2024 • Junlin Lv, Yuan Feng, Xike Xie, Xin Jia, Qirong Peng, Guiming Xie
In this paper, we observe a locality in query criticality during the prefilling phase of long-context processing: adjacent query tokens tend to focus on similar subsets of the past Key-Value (KV) cache.
no code implementations • 18 Sep 2024 • Sijing Chen, Yuan Feng, Laipeng He, Tianwei He, Wendi He, Yanni Hu, Bin Lin, Yiting Lin, Yu Pan, Pengfei Tan, Chengwei Tian, Chen Wang, Zhicheng Wang, Ruoye Xie, Jixun Yao, Quanlei Yan, Yuguang Yang, Jianhao Ye, JingJing Yin, Yanzhen Yu, Huimin Zhang, Xiang Zhang, Guangcheng Zhao, Hongbin Zhou, Pengpeng Zou
In this report, we introduce Takin AudioLLM, a series of techniques and models, mainly including Takin TTS, Takin VC, and Takin Morphing, specifically designed for audiobook production.
no code implementations • 28 Jul 2024 • Yufei Zhao, Yuan Feng, Afkar Mohamed Ismail, Ziyue Wang, Yong Liang Guan, Yongxin Guo, Chau Yuen
Owing to the capability of each unit cell on the metasurface to independently switch states, the entire RIS is not limited to controlling general beams with specific directional patterns, but also generates beams with more complex structures, including multi-focus 3D spot beams and vortex beams.
2 code implementations • 16 Jul 2024 • Yuan Feng, Junlin Lv, Yukun Cao, Xike Xie, S. Kevin Zhou
In this paper, we establish a theoretical loss upper bound between pre- and post-eviction attention output, explaining the optimization target of prior cache eviction methods, while guiding the optimization of adaptive budget allocation.
no code implementations • 24 May 2024 • Yuan Feng, Chuanbing Zhao, Feifei Gao, Yong Zhang, Shaodan Ma
Therefore, we next design a transfer learning strategy that fine-tunes the pre-trained model by limited labeled data of the new environment.
no code implementations • 26 Mar 2024 • Hanzhe Li, Xiangxiang Wang, Yuan Feng, Yaqian Qi, Jingxiao Tian
This article explores how to drive intelligent iot monitoring and control through cloud computing and machine learning.
no code implementations • 5 Mar 2024 • Yaqian Qi, Yuan Feng, Xiangxiang Wang, Hanzhe Li, Jingxiao Tian
To enable large-scale and efficient deployment of artificial intelligence (AI), the combination of AI and edge computing has spawned Edge Intelligence, which leverages the computing and communication capabilities of end devices and edge servers to process data closer to where it is generated.
no code implementations • 23 Nov 2023 • Benjamin Kiefer, Lojze Žust, Matej Kristan, Janez Perš, Matija Teršek, Arnold Wiliem, Martin Messmer, Cheng-Yen Yang, Hsiang-Wei Huang, Zhongyu Jiang, Heng-Cheng Kuo, Jie Mei, Jenq-Neng Hwang, Daniel Stadler, Lars Sommer, Kaer Huang, Aiguo Zheng, Weitu Chong, Kanokphan Lertniphonphan, Jun Xie, Feng Chen, Jian Li, Zhepeng Wang, Luca Zedda, Andrea Loddo, Cecilia Di Ruberto, Tuan-Anh Vu, Hai Nguyen-Truong, Tan-Sang Ha, Quan-Dung Pham, Sai-Kit Yeung, Yuan Feng, Nguyen Thanh Thien, Lixin Tian, Sheng-Yao Kuan, Yuan-Hao Ho, Angel Bueno Rodriguez, Borja Carrillo-Perez, Alexander Klein, Antje Alex, Yannik Steiniger, Felix Sattler, Edgardo Solano-Carrillo, Matej Fabijanić, Magdalena Šumunec, Nadir Kapetanović, Andreas Michel, Wolfgang Gross, Martin Weinmann
The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024 addresses maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicles (USV).
Ranked #1 on
Semantic Segmentation
on LaRS
1 code implementation • CVPR 2023 • Yong Yang, Qiong Chen, Yuan Feng, Tianlin Huang
Existing few-shot segmentation methods are based on the meta-learning strategy and extract instance knowledge from a support set and then apply the knowledge to segment target objects in a query set.
Ranked #17 on
Few-Shot Semantic Segmentation
on PASCAL-5i (1-Shot)
no code implementations • 1 Mar 2023 • Likang Liu, Keke Sun, Chunlai Zhou, Yuan Feng
Within the framework established in this paper, constrained DP algorithms in the literature can be classified either as belief revision or belief update.
no code implementations • 23 Jan 2023 • Yuan Feng, Hyeran Jeon, Filip Blagojevic, Cyril Guyot, Qing Li, Dong Li
Transformer models gain popularity because of their superior inference accuracy and inference throughput.
no code implementations • 6 Jan 2023 • Shengyuan Ma, Runke Wang, Suhao Qiu, Ruokun Li, Qi Yue, Qingfang Sun, Liang Chen, Fuhua Yan, Guang-Zhong Yang, Yuan Feng
Here we propose a pipeline for processing MRE images using optimization-based displacement extraction and Traveling Wave Expansion-based Neural Network (TWENN) modulus estimation.
no code implementations • 19 Jul 2022 • Mujahid Al Rafi, Yuan Feng, Hyeran Jeon
In this paper, we show a new observation that pre-trained models and fine-tuned models have significantly high similarities in weight values.
1 code implementation • 14 Jun 2022 • Yuan Feng, Yaojun Hu, Pengfei Fang, Yanhong Yang, Sheng Liu, ShengYong Chen
However, jointly removing the rain and haze in scene images is ill-posed and challenging, where the existence of haze and rain and the change of atmosphere light, can both degrade the scene information.
no code implementations • 28 Mar 2022 • Ruiyang Zhao, Zhao He, Tao Wang, Suhao Qiu, Pawel Herman, Yanle Hu, Chencheng Zhang, Dinggang Shen, Bomin Sun, Guang-Zhong Yang, Yuan Feng
Here we proposed a convolutional long short-term memory (Conv-LSTM) based recurrent neural network (RNN), or ConvLR, to reconstruct interventional images with golden-angle radial sampling.
no code implementations • 7 May 2021 • Mingyuan Mao, Baochang Zhang, David Doermann, Jie Guo, Shumin Han, Yuan Feng, Xiaodi Wang, Errui Ding
This leads to a new problem of confidence discrepancy for the detector ensembles.
1 code implementation • 28 Apr 2021 • Ying Xin, Guanzhong Wang, Mingyuan Mao, Yuan Feng, Qingqing Dang, Yanjun Ma, Errui Ding, Shumin Han
Therefore, a trade-off between effectiveness and efficiency is necessary in practical scenarios.
Ranked #1 on
Object Detection
on COCO test-dev
(Hardware Burden metric)
no code implementations • 16 Dec 2020 • Yuan Feng, Hexiang Wang, Han Yang, Fangbo Wang
Although the basic neural network provides an alternative approach for structural dynamics analysis, the lack of physics law inside the neural network limits the model accuracy and fidelity.
1 code implementation • 16 Sep 2020 • Xuehui Yu, Zhenjun Han, Yuqi Gong, Nan Jiang, Jian Zhao, Qixiang Ye, Jie Chen, Yuan Feng, Bin Zhang, Xiaodi Wang, Ying Xin, Jingwei Liu, Mingyuan Mao, Sheng Xu, Baochang Zhang, Shumin Han, Cheng Gao, Wei Tang, Lizuo Jin, Mingbo Hong, Yuchao Yang, Shuiwang Li, Huan Luo, Qijun Zhao, Humphrey Shi
The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection.
no code implementations • 6 Sep 2020 • Xin Hong, Xiangzhen Zhou, Sanjiang Li, Yuan Feng, Mingsheng Ying
Tensor networks have been successfully applied in simulation of quantum physical systems for decades.
Quantum Physics Data Structures and Algorithms
2 code implementations • 15 Apr 2020 • Sanjiang Li, Xiangzhen Zhou, Yuan Feng
Mapping logical quantum circuits to Noisy Intermediate-Scale Quantum (NISQ) devices is a challenging problem which has attracted rapidly increasing interests from both quantum and classical computing communities.
Quantum Physics
no code implementations • 17 Nov 2019 • Ruoyu Guo, Cheng Cui, Yuning Du, Xianglong Meng, Xiaodi Wang, Jingwei Liu, Jianfeng Zhu, Yuan Feng, Shumin Han
We present an object detection framework based on PaddlePaddle.
1 code implementation • 23 Aug 2019 • Xiangzhen Zhou, Sanjiang Li, Yuan Feng
Our algorithm runs in time polynomial in all parameters including the size and the qubit number of the input circuit, and the qubit number in the QPU.
Quantum Physics
no code implementations • 16 Jul 2019 • Guangxi Li, Youle Wang, Yu Luo, Yuan Feng
We propose a quantum data fitting algorithm for non-sparse matrices, which is based on the Quantum Singular Value Estimation (QSVE) subroutine and a novel efficient method for recovering the signs of eigenvalues.
no code implementations • 31 Jul 2017 • Shenggang Ying, Mingsheng Ying, Yuan Feng
Secondly when updating the current classifier, private random noise is used to protect the original data.
no code implementations • 13 Dec 2015 • Shenggang Ying, Mingsheng Ying, Yuan Feng
Data mining is a key technology in big data analytics and it can discover understandable knowledge (patterns) hidden in large data sets.