1 code implementation • ACL 2022 • Guanhua Chen, Shuming Ma, Yun Chen, Dongdong Zhang, Jia Pan, Wenping Wang, Furu Wei
When applied to zero-shot cross-lingual abstractive summarization, it produces an average performance gain of 12. 3 ROUGE-L over mBART-ft. We conduct detailed analyses to understand the key ingredients of SixT+, including multilinguality of the auxiliary parallel data, positional disentangled encoder, and the cross-lingual transferability of its encoder.
Abstractive Text Summarization Cross-Lingual Abstractive Summarization +6
no code implementations • 10 May 2024 • Rongyu Zhang, Yun Chen, Chenrui Wu, Fangxin Wang, Bo Li
Federated learning (FL) offers a privacy-centric distributed learning framework, enabling model training on individual clients and central aggregation without necessitating data exchange.
no code implementations • 2 Apr 2024 • Xu Li, Ruiqi Sun, Jiameng Lv, Peng Jia, Nan Li, Chengliang Wei, Zou Hu, Xinzhong Er, Yun Chen, Zhang Ban, Yuedong Fang, Qi Guo, Dezi Liu, Guoliang Li, Lin Lin, Ming Li, Ran Li, Xiaobo Li, Yu Luo, Xianmin Meng, Jundan Nie, Zhaoxiang Qi, Yisheng Qiu, Li Shao, Hao Tian, Lei Wang, Wei Wang, Jingtian Xian, Youhua Xu, Tianmeng Zhang, Xin Zhang, Zhimin Zhou
To overcome these challenges, we have developed a framework based on a hierarchical visual Transformer with a sliding window technique to search for strong lensing systems within entire images.
no code implementations • 13 Mar 2024 • Zeguan Xiao, Yan Yang, Guanhua Chen, Yun Chen
In this work, we propose Tastle, a novel black-box jailbreak framework for automated red teaming of LLMs.
1 code implementation • 21 Feb 2024 • Meng Xu, Shuo Wang, Liner Yang, Haoyu Wang, Zhenghao Liu, Cunliang Kong, Yun Chen, Yang Liu, Maosong Sun, Erhong Yang
We evaluate several representative multilingual LLMs on the proposed OMGEval, which we believe will provide a valuable reference for the community to further understand and improve the multilingual capability of LLMs.
no code implementations • 18 Feb 2024 • Hanqing Wang, Bowen Ping, Shuo Wang, Xu Han, Yun Chen, Zhiyuan Liu, Maosong Sun
Most prior works on LoRA combination primarily rely on task-level weights for each involved LoRA, making different examples and tokens share the same LoRA weights.
no code implementations • 29 Dec 2023 • Yun Chen, Lingxiao Yang, Qi Chen, Jian-Huang Lai, Xiaohua Xie
We introduce a two-stage pipeline to effectively train our network: Stage I utilizes inter-speech contrastive learning to model fine-grained emotion and intra-speech disentanglement learning to better separate emotion and content.
no code implementations • 11 Dec 2023 • Ava Pun, Gary Sun, Jingkang Wang, Yun Chen, Ze Yang, Sivabalan Manivasagam, Wei-Chiu Ma, Raquel Urtasun
Different outdoor illumination conditions drastically alter the appearance of urban scenes, and they can harm the performance of image-based robot perception systems if not seen during training.
no code implementations • 9 Nov 2023 • Ze Yang, Sivabalan Manivasagam, Yun Chen, Jingkang Wang, Rui Hu, Raquel Urtasun
In this work, we present NeuSim, a novel approach that estimates accurate geometry and realistic appearance from sparse in-the-wild data captured at distance and at limited viewpoints.
no code implementations • ICCV 2023 • Jeffrey Yunfan Liu, Yun Chen, Ze Yang, Jingkang Wang, Sivabalan Manivasagam, Raquel Urtasun
We propose a new method for realistic real-time novel-view synthesis (NVS) of large scenes.
no code implementations • 2 Nov 2023 • Jingkang Wang, Sivabalan Manivasagam, Yun Chen, Ze Yang, Ioan Andrei Bârsan, Anqi Joyce Yang, Wei-Chiu Ma, Raquel Urtasun
To tackle these issues, we present CADSim, which combines part-aware object-class priors via a small set of CAD models with differentiable rendering to automatically reconstruct vehicle geometry, including articulated wheels, with high-quality appearance.
no code implementations • 26 Oct 2023 • Hanqing Wang, Yajing Luo, Boya Xiong, Guanhua Chen, Yun Chen
Stylistic headline generation is the task to generate a headline that not only summarizes the content of an article, but also reflects a desired style that attracts users.
no code implementations • 2 Oct 2023 • Tianci Xue, Ziqi Wang, Yixia Li, Yun Chen, Guanhua Chen
To alleviate the illusion of competence of models, we first ask the model to verify the correctness of shown examples.
no code implementations • 26 Aug 2023 • Yun Chen, Nuria González-Prelcic, Takayuki Shimizu, Hongshen Lu, Chinmay Mahabal
In this paper, we propose first a mmWave channel tracking algorithm based on multidimensional orthogonal matching pursuit algorithm (MOMP) using reduced sparsifying dictionaries, which exploits information from channel estimates in previous frames.
1 code implementation • 19 Aug 2023 • Liwen Zhang, Weige Cai, Zhaowei Liu, Zhi Yang, Wei Dai, Yujie Liao, Qianru Qin, Yifei Li, Xingyu Liu, Zhiqiang Liu, Zhoufan Zhu, Anbo Wu, Xin Guo, Yun Chen
Our work offers a more comprehensive financial knowledge evaluation benchmark, utilizing data of mock exams and covering a wide range of evaluated LLMs.
2 code implementations • CVPR 2023 • Ze Yang, Yun Chen, Jingkang Wang, Sivabalan Manivasagam, Wei-Chiu Ma, Anqi Joyce Yang, Raquel Urtasun
Previously recorded driving logs provide a rich resource to build these new scenarios from, but for closed loop evaluation, we need to modify the sensor data based on the new scene configuration and the SDV's decisions, as actors might be added or removed and the trajectories of existing actors and the SDV will differ from the original log.
no code implementations • 1 Aug 2023 • Yun Chen, Jiaping Xiao
Collaborative heterogeneous robot systems can greatly improve the efficiency of target search and navigation tasks.
1 code implementation • ACL 2023 • Guanhua Chen, Lu Hou, Yun Chen, Wenliang Dai, Lifeng Shang, Xin Jiang, Qun Liu, Jia Pan, Wenping Wang
Furthermore, to enhance the token- and sentence-level multilingual representation of the MTE, we propose to train it with machine translation and contrastive learning jointly before the TriKD to provide a better initialization.
no code implementations • 30 Jun 2023 • Yun Chen, Nuria González-Prelcic, Takayuki Shimizu, HongSheng Lu
One strategy to obtain user location information in a wireless network operating at millimeter wave (mmWave) is based on the exploitation of the geometric relationships between the channel parameters and the user position.
1 code implementation • 28 Jan 2023 • Weikang Wang, Guanhua Chen, Hanqing Wang, Yue Han, Yun Chen
In this paper, we investigate whether multilingual sentence Transformer LaBSE is a strong multilingual word aligner.
no code implementations • 26 Nov 2022 • Jinran Nie, Liner Yang, Yun Chen, Cunliang Kong, Junhui Zhu, Erhong Yang
Compared with potential solutions, our approach fuses the representations of the word complexity levels into the model to get better control of lexical complexity.
1 code implementation • 25 May 2022 • Peng Chen, Zhimin Chen, Pu Miao, Yun Chen
This letter addresses the passive sensing issue utilizing wireless communication signals and RIS amidst interference from wireless access points (APs).
1 code implementation • 23 Apr 2022 • Cunliang Kong, Xuezhi Fang, Liner Yang, Yun Chen, Erhong Yang
Since traditional dictionaries present word senses as discrete items in predefined inventories, they fall short of flexibility, which is required in providing specific meanings of words in particular contexts.
no code implementations • 18 Apr 2022 • Ruixuan Liu, Yanlin Wang, Yang Cao, Lingjuan Lyu, Weike Pan, Yun Chen, Hong Chen
Collecting and training over sensitive personal data raise severe privacy concerns in personalized recommendation systems, and federated learning can potentially alleviate the problem by training models over decentralized user data. However, a theoretically private solution in both the training and serving stages of federated recommendation is essential but still lacking. Furthermore, naively applying differential privacy (DP) to the two stages in federated recommendation would fail to achieve a satisfactory trade-off between privacy and utility due to the high-dimensional characteristics of model gradients and hidden representations. In this work, we propose a federated news recommendation method for achieving a better utility in model training and online serving under a DP guarantee. We first clarify the DP definition over behavior data for each round in the life-circle of federated recommendation systems. Next, we propose a privacy-preserving online serving mechanism under this definition based on the idea of decomposing user embeddings with public basic vectors and perturbing the lower-dimensional combination coefficients.
no code implementations • 4 Apr 2022 • Yun Chen, Joan Palacios, Nuria González-Prelcic, Takayuki Shimizu, HongSheng Lu
High resolution compressive channel estimation provides information for vehicle localization when a hybrid mmWave MIMO system is considered.
2 code implementations • ACL 2022 • Cunliang Kong, Yun Chen, Hengyuan Zhang, Liner Yang, Erhong Yang
We demonstrate that the framework can generate relevant, simple definitions for the target words through automatic and manual evaluations on English and Chinese datasets.
2 code implementations • 19 Mar 2022 • Peng Chen, Zhimin Chen, Liang Liu, Yun Chen, Xianbin Wang
The estimation of direction of arrival (DOA) is a crucial issue in conventional radar, wireless communication, and integrated sensing and communication (ISAC) systems.
no code implementations • 12 Jan 2022 • Andrew Graff, Yun Chen, Nuria González-Prelcic, Takayuki Shimizu
Then, a deep network is used to translate features of these radar spatial covariances into features of the communication spatial covariances, by learning the intricate mapping between radar and communication channels, in both line-of-sight and non-line-of-sight settings.
1 code implementation • 30 Dec 2021 • Yingying Wang, Cunliang Kong, Liner Yang, Yijun Wang, Xiaorong Lu, Renfen Hu, Shan He, Zhenghao Liu, Yun Chen, Erhong Yang, Maosong Sun
This resource is of great relevance for second language acquisition research, foreign-language teaching, and automatic grammatical error correction.
no code implementations • 16 Nov 2021 • Yun Chen, Andrew Graff, Nuria González-Prelcic, Takayuki Shimizu
In this paper, we obtain prior information to speed up the beam training process by implementing two deep neural networks (DNNs) that realize radar-to-communication (R2C) channel information translation in a vehicle-to-infrastructure (V2I) system.
1 code implementation • 16 Oct 2021 • Guanhua Chen, Shuming Ma, Yun Chen, Dongdong Zhang, Jia Pan, Wenping Wang, Furu Wei
When applied to zero-shot cross-lingual abstractive summarization, it produces an average performance gain of 12. 3 ROUGE-L over mBART-ft. We conduct detailed analyses to understand the key ingredients of SixT+, including multilinguality of the auxiliary parallel data, positional disentangled encoder, and the cross-lingual transferability of its encoder.
Abstractive Text Summarization Cross-Lingual Abstractive Summarization +6
1 code implementation • EMNLP 2021 • Guanhua Chen, Shuming Ma, Yun Chen, Li Dong, Dongdong Zhang, Jia Pan, Wenping Wang, Furu Wei
In this paper, we focus on a zero-shot cross-lingual transfer task in NMT.
no code implementations • Sensors 2021 • Xiaotao Shao, Qing Wang, Wei Yang, Yun Chen, Yi Xie, Yan Shen, Zhongli Wang
MFPN includes two modules, namely double feature pyramid network (FPN) integrated with ResNet (DFR) and repulsion loss of minimum (RLM).
no code implementations • 29 Jan 2021 • Shengsheng Zhang, Yaping Huang, Yun Chen, Liner Yang, Chencheng Wang, Erhong Yang
We exploit a set of data-rich source domains to learn the initialization of model parameters that facilitates fast adaptation on new resource-poor target domains.
no code implementations • 17 Jan 2021 • James Tu, Huichen Li, Xinchen Yan, Mengye Ren, Yun Chen, Ming Liang, Eilyan Bitar, Ersin Yumer, Raquel Urtasun
Yet, there have been limited studies on the adversarial robustness of multi-modal models that fuse LiDAR features with image features.
no code implementations • CVPR 2021 • Yun Chen, Frieda Rong, Shivam Duggal, Shenlong Wang, Xinchen Yan, Sivabalan Manivasagam, Shangjie Xue, Ersin Yumer, Raquel Urtasun
Scalable sensor simulation is an important yet challenging open problem for safety-critical domains such as self-driving.
no code implementations • CVPR 2019 • Ming Liang, Bin Yang, Yun Chen, Rui Hu, Raquel Urtasun
In this paper we propose to exploit multiple related tasks for accurate multi-sensor 3D object detection.
Ranked #13 on 3D Object Detection on KITTI Cars Easy
no code implementations • ICCV 2019 • Yun Chen, Bin Yang, Ming Liang, Raquel Urtasun
In this paper, we tackle the problem of depth completion from RGBD data.
no code implementations • 12 Oct 2020 • Cunliang Kong, Liner Yang, Tianzuo Zhang, Qinan Fan, Zhenghao Liu, Yun Chen, Erhong Yang
We demonstrate the effectiveness of this approach on zero-shot definition generation.
no code implementations • ECCV 2020 • Wenyuan Zeng, Shenlong Wang, Renjie Liao, Yun Chen, Bin Yang, Raquel Urtasun
In this paper, we propose the Deep Structured self-Driving Network (DSDNet), which performs object detection, motion prediction, and motion planning with a single neural network.
1 code implementation • ECCV 2020 • Ming Liang, Bin Yang, Rui Hu, Yun Chen, Renjie Liao, Song Feng, Raquel Urtasun
We propose a motion forecasting model that exploits a novel structured map representation as well as actor-map interactions.
no code implementations • CVPR 2020 • Ming Liang, Bin Yang, Wenyuan Zeng, Yun Chen, Rui Hu, Sergio Casas, Raquel Urtasun
We tackle the problem of joint perception and motion forecasting in the context of self-driving vehicles.
no code implementations • 11 May 2020 • Yun Chen, Xingqin Lin, Talha Ahmed Khan, Mohammad Mozaffari
In this paper, we propose a novel handover framework for providing efficient mobility support and reliable wireless connectivity to drones served by a terrestrial cellular network.
1 code implementation • EMNLP 2020 • Yun Chen, Yang Liu, Guanhua Chen, Xin Jiang, Qun Liu
Shift-Att is an interpretation method that induces alignments from the attention weights of Transformer and does not require parameter update or architecture change.
1 code implementation • ACL 2020 • Zhiyong Wu, Yun Chen, Ben Kao, Qun Liu
However, this approach of evaluating a language model is undermined by the uncertainty of the amount of knowledge that is learned by the probe itself.
no code implementations • 6 Apr 2020 • Wei Peng, Chongxuan Huang, Tian-Hao Li, Yun Chen, Qun Liu
Existing data augmentation approaches for neural machine translation (NMT) have predominantly relied on back-translating in-domain (IND) monolingual corpora.
no code implementations • 21 Nov 2019 • Yun Chen, Xingqin Lin, Talha Khan, Mohammad Mozaffari
Flying drones can be used in a wide range of applications and services from surveillance to package delivery.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Yun Chen, Liangyou Li, Xin Jiang, Xiao Chen, Qun Liu
Despite the success of neural machine translation (NMT), simultaneous neural machine translation (SNMT), the task of translating in real time before a full sentence has been observed, remains challenging due to the syntactic structure difference and simultaneity requirements.
no code implementations • 30 Oct 2019 • Yun Chen, Yiyue Chen, Zhengzhong Tu
Finally, key values for key features of the two poses are computed correspondingly in the pose error detection part, which helps give correction advice.
no code implementations • 29 Sep 2019 • Liner Yang, Chencheng Wang, Yun Chen, Yongping Du, Erhong Yang
We propose two data synthesis methods which can control the error rate and the ratio of error types on synthetic data.
1 code implementation • 16 May 2019 • Liner Yang, Cunliang Kong, Yun Chen, Yang Liu, Qinan Fan, Erhong Yang
To accomplish this task, we construct the Chinese Definition Modeling Corpus (CDM), which contains triples of word, sememes and the corresponding definition.
no code implementations • EMNLP 2018 • Jiatao Gu, Yong Wang, Yun Chen, Kyunghyun Cho, Victor O. K. Li
We frame low-resource translation as a meta-learning problem, and we learn to adapt to low-resource languages based on multilingual high-resource language tasks.
1 code implementation • EMNLP 2018 • Yun Chen, Victor O. K. Li, Kyunghyun Cho, Samuel R. Bowman
Beam search is a widely used approximate search strategy for neural network decoders, and it generally outperforms simple greedy decoding on tasks like machine translation.
no code implementations • 9 Feb 2018 • Yun Chen, Yang Liu, Victor O. K. Li
While end-to-end neural machine translation (NMT) has achieved notable success in the past years in translating a handful of resource-rich language pairs, it still suffers from the data scarcity problem for low-resource language pairs and domains.
no code implementations • ACL 2017 • Yun Chen, Yang Liu, Yong Cheng, Victor O. K. Li
While end-to-end neural machine translation (NMT) has made remarkable progress recently, it still suffers from the data scarcity problem for low-resource language pairs and domains.