no code implementations • EMNLP 2021 • Yangyang Zhao, Zhenyu Wang, Changxi Zhu, Shihan Wang
Most of the existing dialogue policy methods rely on a single learning system, while the human brain has two specialized learning and memory systems, supporting to find good solutions without requiring copious examples.
no code implementations • 10 Apr 2024 • Gaole Dai, Zhenyu Wang, Qinwen Xu, Ming Lu, Wen Chen, Boxin Shi, Shanghang Zhang, Tiejun Huang
Since the spike camera relies on temporal integration instead of temporal differentiation used by event cameras, our proposed TfS loss maintains manageable training costs.
no code implementations • 28 Mar 2024 • Zhenyu Wang, YaLi Li, Taichi Liu, Hengshuang Zhao, Shengjin Wang
Specifically, we propose the cycle-modality propagation, aimed at propagating knowledge bridging 2D and 3D modalities, to support the aforementioned functionalities.
1 code implementation • 26 Mar 2024 • Chenhongyi Yang, Zehui Chen, Miguel Espinosa, Linus Ericsson, Zhenyu Wang, Jiaming Liu, Elliot J. Crowley
In this paper, we further adapt the selective scanning process of Mamba to the visual domain, enhancing its ability to learn features from two-dimensional images by (i) a continuous 2D scanning process that improves spatial continuity by ensuring adjacency of tokens in the scanning sequence, and (ii) direction-aware updating which enables the model to discern the spatial relations of tokens by encoding directional information.
no code implementations • 28 Jan 2024 • Zhenyu Wang, Enze Xie, Aoxue Li, Zhongdao Wang, Xihui Liu, Zhenguo Li
Given a complex text prompt containing multiple concepts including objects, attributes, and relationships, the LLM agent initially decomposes it, which entails the extraction of individual objects, their associated attributes, and the prediction of a coherent scene layout.
2 code implementations • 6 Dec 2023 • Jiayi Pan, Chengcan Wang, Kaifu Zheng, Yangguang Li, Zhenyu Wang, Bin Feng
Our results show that, with SmoothQuant+, the Code Llama-34B model can be quantized and deployed on a A100 40GB GPU, achieving lossless accuracy and a throughput increase of 1. 9 to 4. 0 times compared to the FP16 model deployed on two A100 40GB GPUs.
no code implementations • 1 Nov 2023 • YiRong Chen, Xiaofen Xing, Jingkai Lin, huimin zheng, Zhenyu Wang, Qi Liu, Xiangmin Xu
Large language models (LLMs) have been widely applied in various fields due to their excellent capability for memorizing knowledge and chain of thought (CoT).
1 code implementation • 24 Oct 2023 • YiRong Chen, Zhenyu Wang, Xiaofen Xing, huimin zheng, Zhipei Xu, Kai Fang, Junhong Wang, Sihang Li, Jieling Wu, Qi Liu, Xiangmin Xu
Large language models (LLMs) have performed well in providing general and extensive health suggestions in single-turn conversations, exemplified by systems such as ChatGPT, ChatGLM, ChatDoctor, DoctorGLM, and etc.
1 code implementation • NeurIPS 2023 • Zhenyu Wang, YaLi Li, Xi Chen, Hengshuang Zhao, Shengjin Wang
In this paper, we propose Uni3DETR, a unified 3D detector that addresses indoor and outdoor 3D detection within the same framework.
no code implementations • 5 Sep 2023 • Zhenyu Wang, Peter Bühlmann, Zijian Guo
Classical machine learning methods may lead to poor prediction performance when the target distribution differs from the source populations.
no code implementations • 7 Aug 2023 • Taichi Liu, Chen Gao, Zhenyu Wang, Dong Li, Jianye Hao, Depeng Jin, Yong Li
Graph Neural Network (GNN)-based models have become the mainstream approach for recommender systems.
no code implementations • 5 May 2023 • Yangyang Zhao, Zhenyu Wang, Mehdi Dastani, Shihan Wang
When a conversation enters a dead-end state, regardless of the actions taken afterward, it will continue in a dead-end trajectory until the agent reaches a termination state or maximum turn.
1 code implementation • CVPR 2023 • Zhenyu Wang, YaLi Li, Xi Chen, Ser-Nam Lim, Antonio Torralba, Hengshuang Zhao, Shengjin Wang
In this paper, we formally address universal object detection, which aims to detect every scene and predict every category.
1 code implementation • 3 Mar 2023 • You Shen, Yunzhou Zhang, Yanmin Wu, Zhenyu Wang, Linghao Yang, Sonya Coleman, Dermot Kerr
Specifically, we design the Pillar-based Shape Completion (PSC) module to predict the probability of occupancy whether a pillar contains object shapes.
no code implementations • 17 Nov 2022 • Zhenyu Wang, John H. L. Hansen
Automatic speaker verification systems are vulnerable to a variety of access threats, prompting research into the formulation of effective spoofing detection systems to act as a gate to filter out such spoofing attacks.
no code implementations • 17 Nov 2022 • Zhenyu Wang, John H. L. Hansen
A comprehensive set of experiments are conducted to demonstrate that: 1) diverse acoustic environments do impact speaker recognition performance, which could advance research in audio forensics, 2) domain adversarial training learns the discriminative features which are also invariant to shifts between domains, 3) discrepancy-minimizing adaptation achieves effective performance simultaneously across multiple acoustic domains, and 4) moment-matching adaptation along with dynamic distribution alignment also significantly promotes speaker recognition performance on each domain, especially for the LENA-field domain with noise compared to all other systems.
1 code implementation • NIPS 2022 • Zhenyu Wang, Hao Luo, Pichao Wang, Feng Ding, Fan Wang, Hao Li
Although Vision transformers (ViTs) have recently dominated many vision tasks, deploying ViT models on resource-limited devices remains a challenging problem.
1 code implementation • 22 Jun 2022 • Yuhao Lu, Beixing Deng, Zhenyu Wang, Peiyuan Zhi, YaLi Li, Shengjin Wang
6-DoF grasp pose detection of multi-grasp and multi-object is a challenge task in the field of intelligent robot.
no code implementations • 14 Apr 2022 • Yu Wu, Jianle Wei, Weiqin Ying, Yanqi Lan, Zhen Cui, Zhenyu Wang
On the other hand, the parallel reference lines of the parallel decomposition methods including the normal boundary intersection (NBI) might result in poor diversity because of under-sampling near the boundaries for MaOPs with concave frontiers.
1 code implementation • CVPR 2022 • Zhenyu Wang, YaLi Li, Shengjin Wang
We construct a framework for semi-supervised instance segmentation by assigning pixel-level pseudo labels.
no code implementations • 28 Jan 2022 • Zhenyu Wang, John H. L. Hansen
Audio analysis for forensic speaker verification offers unique challenges in system performance due in part to data collected in naturalistic field acoustic environments where location/scenario uncertainty is common in the forensic data collection process.
1 code implementation • CVPR 2022 • Rui Peng, Rongjie Wang, Zhenyu Wang, Yawen Lai, Ronggang Wang
Depth estimation is solved as a regression or classification problem in existing learning-based multi-view stereo methods.
Ranked #9 on 3D Reconstruction on DTU
no code implementations • NeurIPS 2021 • Zhenyu Wang, YaLi Li, Ye Guo, Shengjin Wang
To combat the noisy labeling, we propose noise-resistant semi-supervised learning by quantifying the region uncertainty.
no code implementations • 28 Oct 2021 • Zhenyu Wang, XiaoYu Zhang, Hao Wang
In smart grids, distributed energy resources (DERs) have penetrated residential zones to provide a new form of electricity supply, mainly from renewable energy.
no code implementations • CVPR 2021 • Zhenyu Wang, YaLi Li, Ye Guo, Lu Fang, Shengjin Wang
In this paper, we delve into semi-supervised object detection where unlabeled images are leveraged to break through the upper bound of fully-supervised object detection models.
no code implementations • 8 Mar 2021 • Zuowei Liang, Xingyuan Hou, Wanru Ma, Fan Zhang, Ping Wu, Zongyuan Zhang, Fanghang Yu, J. -J. Ying, Kun Jiang, Lei Shan, Zhenyu Wang, X. -H. Chen
The transition-metal-based kagome metals provide a versatile platform for correlated topological phases hosting various electronic instabilities.
Superconductivity Strongly Correlated Electrons
no code implementations • 4 Feb 2021 • Zhenyu Wang, H. Y. Yuan, Yunshan Cao, Z. -X. Li, Rembert A. Duine, Peng Yan
An optical frequency comb consists of a set of discrete and equally spaced frequencies and has found wide applications in the synthesis over broad spectral frequencies of electromagnetic wave and precise optical frequency metrology.
Mesoscale and Nanoscale Physics Optics
no code implementations • 28 Dec 2020 • Yangyang Zhao, Zhenyu Wang, Zhenhua Huang
We propose a novel framework, Automatic Curriculum Learning-based Deep Q-Network (ACL-DQN), which replaces the traditional random sampling method with a teacher policy model to realize the dialogue policy for automatic curriculum learning.
no code implementations • 15 Dec 2020 • Zhenyu Wang, Hong Qin, Benjamin Sturdevant, Choong-Seock Chang
We compare the energy conservation property of the geometric PIC algorithm derived from the discrete variational principle with that of previous PIC methods on unstructured meshes.
Plasma Physics
no code implementations • 17 Sep 2020 • Zhenyu Wang, Z. -X. Li, Ruifang Wang, Bo Liu, Hao Meng, Yunshan Cao, Peng Yan
We propose a new method to generate magnetic skyrmions through spin-wave focusing in chiral ferromagnets. A lens is constructed to focus spin waves by a curved interface between two ferromagnetic thin films with different perpendicular magnetic anisotropies.
Mesoscale and Nanoscale Physics
no code implementations • 5 Sep 2020 • Zhenyu Wang, Wei Xia, John H. L. Hansen
Forensic audio analysis for speaker verification offers unique challenges due to location/scenario uncertainty and diversity mismatch between reference and naturalistic field recordings.
no code implementations • 30 Apr 2020 • Fei Tang, Wanling Gao, Jianfeng Zhan, Chuanxin Lan, Xu Wen, Lei Wang, Chunjie Luo, Jiahui Dai, Zheng Cao, Xingwang Xiong, Zihan Jiang, Tianshu Hao, Fanda Fan, Fan Zhang, Yunyou Huang, Jianan Chen, Mengjia Du, Rui Ren, Chen Zheng, Daoyi Zheng, Haoning Tang, Kunlin Zhan, Biao Wang, Defei Kong, Minghe Yu, Chongkang Tan, Huan Li, Xinhui Tian, Yatao Li, Junchao Shao, Zhenyu Wang, Xiaoyu Wang, Hainan Ye
We use real-world benchmarks to cover the factors space that impacts the learning dynamics to the most considerable extent.
no code implementations • 17 Feb 2020 • Wanling Gao, Fei Tang, Jianfeng Zhan, Chuanxin Lan, Chunjie Luo, Lei Wang, Jiahui Dai, Zheng Cao, Xiongwang Xiong, Zihan Jiang, Tianshu Hao, Fanda Fan, Xu Wen, Fan Zhang, Yunyou Huang, Jianan Chen, Mengjia Du, Rui Ren, Chen Zheng, Daoyi Zheng, Haoning Tang, Kunlin Zhan, Biao Wang, Defei Kong, Minghe Yu, Chongkang Tan, Huan Li, Xinhui Tian, Yatao Li, Gang Lu, Junchao Shao, Zhenyu Wang, Xiaoyu Wang, Hainan Ye
An end-to-end benchmark is a distillation of the essential attributes of an industry-scale application.
no code implementations • 13 Aug 2019 • Wanling Gao, Fei Tang, Lei Wang, Jianfeng Zhan, Chunxin Lan, Chunjie Luo, Yunyou Huang, Chen Zheng, Jiahui Dai, Zheng Cao, Daoyi Zheng, Haoning Tang, Kunlin Zhan, Biao Wang, Defei Kong, Tong Wu, Minghe Yu, Chongkang Tan, Huan Li, Xinhui Tian, Yatao Li, Junchao Shao, Zhenyu Wang, Xiaoyu Wang, Hainan Ye
On the basis of the AIBench framework, abstracting the real-world data sets and workloads from one of the top e-commerce providers, we design and implement the first end-to-end Internet service AI benchmark, which contains the primary modules in the critical paths of an industry scale application and is scalable to deploy on different cluster scales.
no code implementations • 19 Feb 2019 • Zhenyu Wang, Wei Zheng, Chunfeng Song
In this paper, we propose a method for air quality measurement based on double-channel convolutional neural network ensemble learning to solve the problem of feature extraction for different parts of environmental images.
no code implementations • 13 Sep 2018 • Haichao Shi, Peng Li, Bo wang, Zhenyu Wang
However, in this paper, we propose a novel architecture for image captioning with deep reinforcement learning to optimize image captioning tasks.
1 code implementation • 4 Oct 2017 • Ilai Schwartz, Jochen Scheuer, Benedikt Tratzmiller, Samuel Mueller, Qiong Chen, Ish Dhand, Zhenyu Wang, Christoph Mueller, Boris Naydenov, Fedor Jelezko, Martin B. Plenio
We derive sequences theoretically and demonstrate experimentally that they are capable of efficient polarisation transfer from an optically polarised nitrogen-vacancy centre in diamond to the surrounding $^{13}$C nuclear spin bath even in the presence of control errors, making it an ideal tool for the realisation of the above NV centre based applications.
Quantum Physics