1 code implementation • NAACL 2022 • Pei Chen, Haotian Xu, Cheng Zhang, Ruihong Huang
General domain Named Entity Recognition (NER) datasets like CoNLL-2003 mostly annotate coarse-grained location entities such as a country or a city.
no code implementations • EMNLP 2020 • Hui Su, Xiaoyu Shen, Zhou Xiao, Zheng Zhang, Ernie Chang, Cheng Zhang, Cheng Niu, Jie zhou
In this work, we take a close look at the movie domain and present a large-scale high-quality corpus with fine-grained annotations in hope of pushing the limit of movie-domain chatbots.
no code implementations • COLING 2022 • Xiaofeng Qi, Chao Li, Zhongping Liang, Jigang Liu, Cheng Zhang, Yuanxin Wei, Lin Yuan, Guang Yang, Lanxiao Huang, Min Li
This paper introduces a generative system for in-battle real-time commentary in mobile MOBA games.
no code implementations • 24 Nov 2024 • Arthur Azevedo de Amorim, Cheng Zhang, Marco Gaboardi
We prove that the equational theory of Kleene algebra with commutativity conditions on primitives (or atomic terms) is undecidable, thereby settling a longstanding open question in the theory of Kleene algebra.
1 code implementation • 22 Nov 2024 • Zizhao Wu, Jian Shi, Xuan Deng, Cheng Zhang, Genfu Yang, Ming Zeng, Yunhai Wang
Point cloud completion aims to infer a complete shape from its partial observation.
no code implementations • 13 Nov 2024 • Chris Jennings-Shaffer, David H Rich, Matthew Macaulay, Michael D Karcher, Tanvi Ganapathy, Shosuke Kiami, Anna Kooperberg, Cheng Zhang, Marc A Suchard, Frederick A Matsen IV
This structure can represent many trees at once, and local rearrangements of trees translate to methods of enlarging the sDAG.
no code implementations • 7 Nov 2024 • Cheng Zhang, Hanna Foerster, Robert D. Mullins, Yiren Zhao, Ilia Shumailov
We evaluate HSPI against models served on different real hardware and find that in a white-box setting we can distinguish between different \GPU{}s with between $83. 9\%$ and $100\%$ accuracy.
1 code implementation • 30 Oct 2024 • Shiyue Zhang, Longlin Yu, Ziheng Cheng, Cheng Zhang
Recently, through a unified gradient flow perspective of Markov chain Monte Carlo (MCMC) and variational inference (VI), particle-based variational inference methods (ParVIs) have been proposed that tend to combine the best of both worlds.
no code implementations • 23 Oct 2024 • Shiyue Zhang, Ziheng Cheng, Cheng Zhang
Particle-based variational inference methods (ParVIs) use non-parametric variational families represented by particles to approximate the target distribution according to the kernelized Wasserstein gradient flow for the Kullback-Leibler (KL) divergence.
no code implementations • 20 Oct 2024 • Zhekun Shi, Longlin Yu, Tianyu Xie, Cheng Zhang
Recent success of diffusion models has inspired a surge of interest in developing sampling techniques using reverse diffusion processes.
no code implementations • 18 Oct 2024 • Pengguang Du, Cheng Zhang, Yindi Jing, Chao Fang, Zhilei Zhang, Yongming Huang
For the detected jammer along with users, we propose a two-step minimum mean square error (MMSE) channel estimation using the projected observation vectors.
no code implementations • 9 Oct 2024 • Zeyu Cao, Cheng Zhang, Pedro Gimenes, Jianqiao Lu, Jianyi Cheng, Yiren Zhao
Post-training quantization of Large Language Models (LLMs) has proven effective in reducing the computational requirements for running inference on these models.
no code implementations • 8 Oct 2024 • Divyat Mahajan, Jannes Gladrow, Agrin Hilmkil, Cheng Zhang, Meyer Scetbon
In this work, we propose to learn a \emph{single} model capable of inferring in a zero-shot manner the causal generative processes of datasets.
no code implementations • 8 Oct 2024 • Cheng Zhang, Jeffrey T. H. Wong, Can Xiao, George A. Constantinides, Yiren Zhao
However, these heuristic methods lack an analytical solution to guide the design of quantization error reconstruction terms.
no code implementations • 7 Oct 2024 • Yifan Wang, Cheng Zhang, Yuanndon Zhuang, Mingzeng Dai, Haiming Wang, Yongming Huang
Wireless networks supporting artificial intelligence have gained significant attention, with Over-the-Air Federated Learning emerging as a key application due to its unique transmission and distributed computing characteristics.
no code implementations • 2 Oct 2024 • Cheng Zhang, Yuanhao Wang, Francisco Vicente Carrasco, Chenglei Wu, Jinlong Yang, Thabo Beeler, Fernando de la Torre
We introduce FabricDiffusion, a method for transferring fabric textures from a single clothing image to 3D garments of arbitrary shapes.
1 code implementation • 30 Sep 2024 • Cheng Zhang, Dong Gong, Jiumei He, Yu Zhu, Jinqiu Sun, Yanning Zhang
Inspired by the success of deep generative models and fine-tuning techniques, we proposed a universal image restoration framework based on multiple low-rank adapters (LoRA) from multi-domain transfer learning.
1 code implementation • 26 Sep 2024 • Rwiddhi Chakraborty, Yinong Wang, Jialu Gao, Runkai Zheng, Cheng Zhang, Fernando de la Torre
The widespread success of deep learning models today is owed to the curation of extensive datasets significant in size and complexity.
no code implementations • 20 Sep 2024 • Zilong Wang, Cheng Zhang, Changwei Zhang, Yongming Huang
In this letter, the maximization of resistible jamming power is studied for multi-user downlink millimeter-wave cell-free multiple-input-multiple-output (CF-MIMO) systems.
1 code implementation • 9 Sep 2024 • Tianyu Xie, Musu Yuan, Minghua Deng, Cheng Zhang
Probability estimation of tree topologies is one of the fundamental tasks in phylogenetic inference.
1 code implementation • 1 Sep 2024 • Dingyuan Zhang, Dingkang Liang, Zichang Tan, Xiaoqing Ye, Cheng Zhang, Jingdong Wang, Xiang Bai
Slow inference speed is one of the most crucial concerns for deploying multi-view 3D detectors to tasks with high real-time requirements like autonomous driving.
1 code implementation • 9 Aug 2024 • Tianyu Xie, Frederick A. Matsen IV, Marc A. Suchard, Cheng Zhang
Reconstructing the evolutionary history relating a collection of molecular sequences is the main subject of modern Bayesian phylogenetic inference.
no code implementations • 4 Aug 2024 • Tian Zhan, Chunfeng Xu, Cheng Zhang, Ke Zhu
The Perspective-n-Point (PnP) problem has been widely studied in the literature and applied in various vision-based pose estimation scenarios.
1 code implementation • 17 Jul 2024 • Youngjoong Kwon, Baole Fang, Yixing Lu, Haoye Dong, Cheng Zhang, Francisco Vicente Carrasco, Albert Mosella-Montoro, Jianjin Xu, Shingo Takagi, Daeil Kim, Aayush Prakash, Fernando de la Torre
To tackle this challenge, this paper leverages recent advancements in Gaussian Splatting and introduces a new method to learn generalizable human Gaussians that allows photorealistic and accurate view-rendering of a new human subject from a limited set of sparse views in a feed-forward manner.
1 code implementation • 24 Jun 2024 • Zhiyu Tan, Xiaomeng Yang, Luozheng Qin, Mengping Yang, Cheng Zhang, Hao Li
Our evaluation across 24 text-to-image generation models demonstrate that EvalAlign not only provides superior metric stability but also aligns more closely with human preferences than existing metrics, confirming its effectiveness and utility in model assessment.
no code implementations • 21 Jun 2024 • Yuang Chen, Cheng Zhang, Xitong Gao, Robert D. Mullins, George A. Constantinides, Yiren Zhao
In this work, we propose AsymGQA, an activation-informed approach to asymmetrically grouping an MHA to a GQA for better model performance.
no code implementations • 21 Jun 2024 • Zixi Zhang, Cheng Zhang, Xitong Gao, Robert D. Mullins, George A. Constantinides, Yiren Zhao
We present HeteroLoRA, a light-weight search algorithm that leverages zero-cost proxies to allocate the limited LoRA trainable parameters across the model for better fine-tuned performance.
no code implementations • 20 Jun 2024 • Cheng Zhang
Many attempts at this task often fail to surpass the na\"ive baseline because of the randomness of the data and the improper utilization of exogenous variables as features.
no code implementations • 17 Jun 2024 • Tianhong Catherine Yu, Manru Mary Zhang, Peter He, Chi-Jung Lee, Cassidy Cheesman, Saif Mahmud, Ruidong Zhang, François Guimbretière, Cheng Zhang
In SeamPose, we repurposed seams as capacitive sensors in a shirt for continuous upper-body pose estimation.
1 code implementation • 12 Jun 2024 • Ruibo Tu, Zineb Senane, Lele Cao, Cheng Zhang, Hedvig Kjellström, Gustav Eje Henter
In this paper, we introduce high-order structural causal information as natural prior knowledge and provide a benchmark framework for the evaluation of tabular synthesis models.
1 code implementation • 5 Jun 2024 • Zhewen Yu, Sudarshan Sreeram, Krish Agrawal, Junyi Wu, Alexander Montgomerie-Corcoran, Cheng Zhang, Jianyi Cheng, Christos-Savvas Bouganis, Yiren Zhao
We propose a Hardware-Aware Sparsity Search (HASS) to systematically determine an efficient sparsity solution for dataflow accelerators.
no code implementations • 5 Jun 2024 • Ali Momeni, Babak Rahmani, Benjamin Scellier, Logan G. Wright, Peter L. McMahon, Clara C. Wanjura, Yuhang Li, Anas Skalli, Natalia G. Berloff, Tatsuhiro Onodera, Ilker Oguz, Francesco Morichetti, Philipp del Hougne, Manuel Le Gallo, Abu Sebastian, Azalia Mirhoseini, Cheng Zhang, Danijela Marković, Daniel Brunner, Christophe Moser, Sylvain Gigan, Florian Marquardt, Aydogan Ozcan, Julie Grollier, Andrea J. Liu, Demetri Psaltis, Andrea Alù, Romain Fleury
Research over the past few years has shown that the answer to all these questions is likely "yes, with enough research": PNNs could one day radically change what is possible and practical for AI systems.
1 code implementation • 3 Jun 2024 • Kunpeng Wang, Zhengzheng Tu, Chenglong Li, Cheng Zhang, Bin Luo
To adaptively select the appropriate fusion scheme for multi-modal input, we introduce an adaptive ensemble module that forms the adaptive fusion bank, which is embedded into hierarchical layers for sufficient fusion of different source data.
no code implementations • 31 May 2024 • Eleanor Clifford, Adhithya Saravanan, Harry Langford, Cheng Zhang, Yiren Zhao, Robert Mullins, Ilia Shumailov, Jamie Hayes
We demonstrate that locking mechanisms are feasible by either targeting efficiency of model representations, such making models incompatible with quantisation, or tie the model's operation on specific characteristics of hardware, such as number of cycles for arithmetic operations.
2 code implementations • 29 May 2024 • Ziheng Cheng, Longlin Yu, Tianyu Xie, Shiyue Zhang, Cheng Zhang
This way, the upper-level objective becomes the kernel Stein discrepancy (KSD), which is readily computable for stochastic gradient descent due to the hierarchical structure of semi-implicit variational distributions.
1 code implementation • 26 May 2024 • Tianyu Xie, Yu Zhu, Longlin Yu, Tong Yang, Ziheng Cheng, Shiyue Zhang, Xiangyu Zhang, Cheng Zhang
We propose reflected flow matching (RFM) to train the velocity model in reflected CNFs by matching the conditional velocity fields in a simulation-free manner, similar to the vanilla FM.
1 code implementation • 21 May 2024 • Zhiyu Tan, Mengping Yang, Luozheng Qin, Hao Yang, Ye Qian, Qiang Zhou, Cheng Zhang, Hao Li
Moreover, the model capacity of the text encoder from CLIP is relatively limited compared to Large Language Models (LLMs), which offer multilingual input, accommodate longer context, and achieve superior text representation.
no code implementations • 2 May 2024 • Chong Zheng, Yongming Huang, Cheng Zhang, Tony Q. S. Quek
To this end, we abstract the system into a weighted undirected topology graph and, then propose a recurrent graph reinforcement learning (RGRL) algorithm to intelligently learn the optimal hybrid RA policy.
1 code implementation • 11 Apr 2024 • Cheng Zhang, Qianyi Wu, Camilo Cruz Gambardella, Xiaoshui Huang, Dinh Phung, Wanli Ouyang, Jianfei Cai
Generative models, e. g., Stable Diffusion, have enabled the creation of photorealistic images from text prompts.
no code implementations • 10 Apr 2024 • Meyer Scetbon, Joel Jennings, Agrin Hilmkil, Cheng Zhang, Chao Ma
Based on this, we design a two-stage causal generative model that first infers the causal order from observations in a zero-shot manner, thus by-passing the search, and then learns the generative fixed-point SCM on the ordered variables.
no code implementations • 8 Mar 2024 • Ceyao Zhang, Renjie Li, Cheng Zhang, Zhaoyu Zhang, Feng Yin
By modeling the inverse design of PCSEL as a sequential decision-making problem, RL approaches can construct a satisfactory PCSEL structure from scratch.
no code implementations • CVPR 2024 • Junyan Wang, Zhenhong Sun, Zhiyu Tan, Xuanbai Chen, Weihua Chen, Hao Li, Cheng Zhang, Yang song
Vanilla text-to-image diffusion models struggle with generating accurate human images, commonly resulting in imperfect anatomies such as unnatural postures or disproportionate limbs. Existing methods address this issue mostly by fine-tuning the model with extra images or adding additional controls -- human-centric priors such as pose or depth maps -- during the image generation phase.
no code implementations • 1 Mar 2024 • Jinyang Jiang, Xiaotian Liu, Tao Ren, Qinghao Wang, Yi Zheng, Yufu Du, Yijie Peng, Cheng Zhang
We introduce a deep reinforcement learning (DRL) approach for solving management problems including inventory management, dynamic pricing, and recommendation.
no code implementations • 29 Feb 2024 • Yang Xu, Yunlin Tan, Cheng Zhang, Kai Chi, Peng Sun, Wenyuan Yang, Ju Ren, Hongbo Jiang, Yaoxue Zhang
This paper presents a robust watermark embedding scheme, named RobWE, to protect the ownership of personalized models in PFL.
1 code implementation • 8 Feb 2024 • Qingsen Yan, Yixu Feng, Cheng Zhang, Pei Wang, Peng Wu, Wei Dong, Jinqiu Sun, Yanning Zhang
Further, we design a novel Color and Intensity Decoupling Network (CIDNet) with two branches dedicated to processing the decoupled image brightness and color in the HVI space.
Ranked #1 on Low-Light Image Enhancement on LOL-v2
Low-light Image Deblurring and Enhancement Low-Light Image Enhancement
no code implementations • 6 Feb 2024 • Tarun Gupta, Wenbo Gong, Chao Ma, Nick Pawlowski, Agrin Hilmkil, Meyer Scetbon, Marc Rigter, Ade Famoti, Ashley Juan Llorens, Jianfeng Gao, Stefan Bauer, Danica Kragic, Bernhard Schölkopf, Cheng Zhang
The study of causality lends itself to the construction of veridical world models, which are crucial for accurately predicting the outcomes of possible interactions.
1 code implementation • 4 Feb 2024 • Cheng Zhang, Jianyi Cheng, George A. Constantinides, Yiren Zhao
Post-training quantization of Large Language Models (LLMs) is challenging.
no code implementations • 23 Jan 2024 • Shih-Han Chou, Matthew Kowal, Yasmin Niknam, Diana Moyano, Shayaan Mehdi, Richard Pito, Cheng Zhang, Ian Knopke, Sedef Akinli Kocak, Leonid Sigal, Yalda Mohsenzadeh
Towards a solution for designing this ability in algorithms, we present a large-scale analysis on an in-house dataset collected by the Reuters News Agency, called Reuters Video-Language News (ReutersViLNews) dataset which focuses on high-level video-language understanding with an emphasis on long-form news.
no code implementations • CVPR 2024 • Yu-Ying Yeh, Jia-Bin Huang, Changil Kim, Lei Xiao, Thu Nguyen-Phuoc, Numair Khan, Cheng Zhang, Manmohan Chandraker, Carl S Marshall, Zhao Dong, Zhengqin Li
In contrast, TextureDreamer can transfer highly detailed, intricate textures from real-world environments to arbitrary objects with only a few casually captured images, potentially significantly democratizing texture creation.
2 code implementations • 17 Dec 2023 • Xiao Wang, Jiandong Jin, Chenglong Li, Jin Tang, Cheng Zhang, Wei Wang
In this paper, we formulate PAR as a vision-language fusion problem and fully exploit the relations between pedestrian images and attribute labels.
no code implementations • 28 Nov 2023 • Zhengming Zhang, Yongming Huang, Cheng Zhang, Qingbi Zheng, Luxi Yang, Xiaohu You
In this paper, a framework consisting of a digital twin and reinforcement learning agents is present to handle the issue.
no code implementations • 7 Nov 2023 • Shantanu Gupta, Cheng Zhang, Agrin Hilmkil
In this work, we propose CAusal Method Predictor (CAMP), a framework for predicting the best method for a given dataset.
1 code implementation • NeurIPS 2023 • Longlin Yu, Tianyu Xie, Yu Zhu, Tong Yang, Xiangyu Zhang, Cheng Zhang
Semi-implicit variational inference (SIVI) has been introduced to expand the analytical variational families by defining expressive semi-implicit distributions in a hierarchical manner.
1 code implementation • NeurIPS 2023 • Tianyu Xie, Cheng Zhang
Designing flexible probabilistic models over tree topologies is important for developing efficient phylogenetic inference methods.
1 code implementation • 8 Oct 2023 • Cheng Zhang, Jianyi Cheng, Ilia Shumailov, George A. Constantinides, Yiren Zhao
In this work, we explore the statistical and learning properties of the LLM layer and attribute the bottleneck of LLM quantisation to numerical scaling offsets.
no code implementations • 3 Oct 2023 • Cheng Zhang, Nilam Nur Amir Sjarif, Roslina Ibrahim
Given the superiority of capsule network (CapsNet) over CNN in various forecasting and classification tasks, this study investigates the potential of integrating a 1D CapsNet with an LSTM network for multi-step stock index forecasting.
1 code implementation • 1 Oct 2023 • JiaQi Zhang, Joel Jennings, Agrin Hilmkil, Nick Pawlowski, Cheng Zhang, Chao Ma
These results provide compelling evidence that our method has the potential to serve as a stepping stone for the development of causal foundation models.
1 code implementation • ICCV 2023 • Cheng Zhang, Xuanbai Chen, Siqi Chai, Chen Henry Wu, Dmitry Lagun, Thabo Beeler, Fernando de la Torre
We show that, for some attributes, images can represent concepts more expressively than text.
no code implementations • 22 Aug 2023 • Ceyao Zhang, Kaijie Yang, Siyi Hu, ZiHao Wang, Guanghe Li, Yihang Sun, Cheng Zhang, Zhaowei Zhang, Anji Liu, Song-Chun Zhu, Xiaojun Chang, Junge Zhang, Feng Yin, Yitao Liang, Yaodong Yang
Building agents with adaptive behavior in cooperative tasks stands as a paramount goal in the realm of multi-agent systems.
1 code implementation • 19 Aug 2023 • Longlin Yu, Cheng Zhang
Semi-implicit variational inference (SIVI) greatly enriches the expressiveness of variational families by considering implicit variational distributions defined in a hierarchical manner.
no code implementations • 6 Aug 2023 • Cheng Zhang, Yu Zhu, Qingsen Yan, Jinqiu Sun, Yanning Zhang
To address this issue, we propose a novel All-in-one Multi-degradation Image Restoration Network (AMIRNet) that can effectively capture and utilize accurate degradation representation for image restoration.
1 code implementation • NeurIPS 2023 • Yashas Annadani, Nick Pawlowski, Joel Jennings, Stefan Bauer, Cheng Zhang, Wenbo Gong
Bayesian causal discovery aims to infer the posterior distribution over causal models from observed data, quantifying epistemic uncertainty and benefiting downstream tasks.
1 code implementation • 2 Jun 2023 • Shaoyuan Huang, Zheng Wang, Heng Zhang, Xiaofei Wang, Cheng Zhang, Wenyu Wang
In this paper, we propose an end-to-end framework with global pooling and static content awareness, DynEformer, to provide a unified workload prediction scheme for dynamic MT-ECP.
1 code implementation • 25 May 2023 • Zhiyu Tan, ZiChao Dong, Cheng Zhang, Weikun Zhang, Hang Ji, Hao Li
Semantic occupancy prediction aims to infer dense geometry and semantics of surroundings for an autonomous agent to operate safely in the 3D environment.
no code implementations • ICCV 2023 • Cheng Sun, Guangyan Cai, Zhengqin Li, Kai Yan, Cheng Zhang, Carl Marshall, Jia-Bin Huang, Shuang Zhao, Zhao Dong
In the last stage, initialized by the neural predictions, we perform PBIR to refine the initial results and obtain the final high-quality reconstruction of object shape, material, and illumination.
Ranked #1 on Depth Prediction on Stanford-ORB
no code implementations • 21 Apr 2023 • Cheng Zhang, Nilam Nur Amir Sjarif, Roslina Ibrahim
Accurately predicting the prices of financial time series is essential and challenging for the financial sector.
no code implementations • 11 Apr 2023 • Cheng Zhang, Stefan Bauer, Paul Bennett, Jiangfeng Gao, Wenbo Gong, Agrin Hilmkil, Joel Jennings, Chao Ma, Tom Minka, Nick Pawlowski, James Vaughan
We assess the ability of large language models (LLMs) to answer causal questions by analyzing their strengths and weaknesses against three types of causal question.
no code implementations • 25 Mar 2023 • Cheng Zhang
Moreover, we present a novel approach to automatically generate adequate distractors for a given QAP.
1 code implementation • 22 Mar 2023 • Matthew Ashman, Chao Ma, Agrin Hilmkil, Joel Jennings, Cheng Zhang
In this work, we further extend the existing body of work and develop a novel gradient-based approach to learning an ADMG with non-linear functional relations from observational data.
1 code implementation • 27 Feb 2023 • Desi R. Ivanova, Joel Jennings, Tom Rainforth, Cheng Zhang, Adam Foster
We formalize the problem of contextual optimization through the lens of Bayesian experimental design and propose CO-BED -- a general, model-agnostic framework for designing contextual experiments using information-theoretic principles.
2 code implementations • 17 Feb 2023 • Cheng Zhang
Structural information of phylogenetic tree topologies plays an important role in phylogenetic inference.
no code implementations • 24 Jan 2023 • Ruibo Tu, Chao Ma, Cheng Zhang
ChatGPT has demonstrated exceptional proficiency in natural language conversation, e. g., it can answer a wide range of questions while no previous large language models can.
1 code implementation • CVPR 2023 • Cheng Zhang, Hai Liu, Yongjian Deng, Bochen Xie, Youfu Li
To leverage the observed findings, we propose a novel critical minority relationship-aware method based on the Transformer architecture in which the facial part relationships can be learned.
no code implementations • TIP 2022 • Hai Liu, Cheng Zhang, Yongjian Deng, Bochen Xie, Tingting Liu, Zhaoli Zhang, You-Fu Li
To this end, two novel modules are proposed to leverage the characteristics of bird images, namely, the hierarchy stage feature aggregation (HSFA) module and the feature in feature abstraction (FFA) module.
Ranked #10 on Fine-Grained Image Classification on NABirds
no code implementations • 14 Nov 2022 • Xin Hua, Zhijiang Du, Hongjian Yu, Jixin Ma, Fanjun Zheng, Cheng Zhang, Qiaohui Lu, Hui Zhao
Cochlear implantation is currently the most effective treatment for patients with severe deafness, but mastering cochlear implantation is extremely challenging because the temporal bone has extremely complex and small three-dimensional anatomical structures, and it is important to avoid damaging the corresponding structures when performing surgery.
no code implementations • 27 Oct 2022 • Jun Lv, Yunhai Feng, Cheng Zhang, Shuang Zhao, Lin Shao, Cewu Lu
Model-based reinforcement learning (MBRL) is recognized with the potential to be significantly more sample-efficient than model-free RL.
Deformable Object Manipulation Model-based Reinforcement Learning +3
no code implementations • 26 Oct 2022 • Wenbo Gong, Joel Jennings, Cheng Zhang, Nick Pawlowski
Given the complexity of real-world relationships and the nature of observations in discrete time, causal discovery methods need to consider non-linear relations between variables, instantaneous effects and history-dependent noise (the change of noise distribution due to past actions).
no code implementations • 20 Oct 2022 • Cheng Zhang, Jie Wang
Transformer-based QG models can generate question-answer pairs (QAPs) with high qualities, but may also generate silly questions for certain texts.
1 code implementation • 18 Sep 2022 • Marcus Klasson, Hedvig Kjellström, Cheng Zhang
In such settings, we propose that continual learning systems should learn the time to learn and schedule which tasks to replay at different time steps.
no code implementations • 2 Sep 2022 • Julia Grosse, Cheng Zhang, Philipp Hennig
Bayesian optimization is a popular formalism for global optimization, but its computational costs limit it to expensive-to-evaluate functions.
no code implementations • 17 Aug 2022 • Wenbo Gong, Digory Smith, Zichao Wang, Craig Barton, Simon Woodhead, Nick Pawlowski, Joel Jennings, Cheng Zhang
In this competition, participants will address two fundamental causal challenges in machine learning in the context of education using time-series data.
no code implementations • 12 Jul 2022 • Desi R. Ivanova, Joel Jennings, Cheng Zhang, Adam Foster
In this paper we introduce a model-agnostic framework for gathering data to evaluate and improve contextual decision making through Bayesian Experimental Design.
1 code implementation • 15 May 2022 • Cheng Zhang, Hao Zhang, Jie Wang
We present a system called TP3 to perform a downstream task of transformers on generating question-answer pairs (QAPs) from a given article.
1 code implementation • 16 Apr 2022 • Cheng Zhang, Frederick A. Matsen IV
Bayesian phylogenetic inference is currently done via Markov chain Monte Carlo (MCMC) with simple proposal mechanisms.
1 code implementation • CVPR 2022 • Cheng Zhang, Shaolin Su, Yu Zhu, Qingsen Yan, Jinqiu Sun, Yanning Zhang
In this paper, to better study an image's potential value that can be explored for restoration, we propose a novel concept, referring to image restoration potential (IRP).
no code implementations • 21 Mar 2022 • Cheng Zhang, Jian Shi, Xuan Deng, Zizhao Wu
In computer-aided design (CAD) community, the point cloud data is pervasively applied in reverse engineering, where the point cloud analysis plays an important role.
1 code implementation • 3 Mar 2022 • Philip Versteeg, Cheng Zhang, Joris M. Mooij
We consider the problem of discovering causal relations from independence constraints selection bias in addition to confounding is present.
no code implementations • 22 Feb 2022 • Cheng Zhang, Tai-Yu Pan, Tianle Chen, Jike Zhong, WenJin Fu, Wei-Lun Chao
One fundamental challenge in building an instance segmentation model for a large number of classes in complex scenes is the lack of training examples, especially for rare objects.
no code implementations • CVPR 2022 • Zirui Peng, Shaofeng Li, Guoxing Chen, Cheng Zhang, Haojin Zhu, Minhui Xue
In this paper, we propose a novel and practical mechanism which enables the service provider to verify whether a suspect model is stolen from the victim model via model extraction attacks.
no code implementations • 10 Feb 2022 • Soheil Sadeghi Eshkevari, Xiaocheng Tang, Zhiwei Qin, Jinhan Mei, Cheng Zhang, Qianying Meng, Jia Xu
In this study, a real-time dispatching algorithm based on reinforcement learning is proposed and for the first time, is deployed in large scale.
1 code implementation • 4 Feb 2022 • Tomas Geffner, Javier Antoran, Adam Foster, Wenbo Gong, Chao Ma, Emre Kiciman, Amit Sharma, Angus Lamb, Martin Kukla, Nick Pawlowski, Miltiadis Allamanis, Cheng Zhang
Causal inference is essential for data-driven decision making across domains such as business engagement, medical treatment and policy making.
no code implementations • ICLR 2022 • Ruibo Tu, Kun Zhang, Hedvig Kjellström, Cheng Zhang
With this criterion, we propose a novel optimal transport-based algorithm for ANMs which is robust to the choice of models and extend it to post-nonlinear models.
1 code implementation • NeurIPS 2021 • Chao Ma, Cheng Zhang
In this work, we fill in this gap by systematically analyzing the identifiability of generative models under MNAR.
1 code implementation • 15 Oct 2021 • Pablo Morales-Alvarez, Wenbo Gong, Angus Lamb, Simon Woodhead, Simon Peyton Jones, Nick Pawlowski, Miltiadis Allamanis, Cheng Zhang
Learning structures between groups of variables from data with missing values is an important task in the real world, yet difficult to solve.
no code implementations • 29 Sep 2021 • Zhixuan Chu, Tan Yan, Yue Wu, Yi Xu, Cheng Zhang, Yulin kang
Time series forecasting has historically been a key area of academic research and industrial applications.
no code implementations • 29 Sep 2021 • Marcus Klasson, Hedvig Kjellstrom, Cheng Zhang
Inspired by human learning, we illustrate that scheduling over which tasks to revisit is critical to the final performance with finite memory resources.
no code implementations • 29 Sep 2021 • Tomas Geffner, Emre Kiciman, Angus Lamb, Martin Kukla, Miltiadis Allamanis, Cheng Zhang
Current causal discovery methods either fail to scale, model only limited forms of functional relationships, or cannot handle missing values.
no code implementations • 29 Sep 2021 • Yang Hu, Cheng Zhang
In this paper we propose a new method to stabilize the training process of the latent variables of adversarial auto-encoders, which we name Intervention Adversarial auto-encoder (IVAAE).
1 code implementation • EMNLP 2021 • Jihyung Kil, Cheng Zhang, Dong Xuan, Wei-Lun Chao
We found that many of the "unknowns" to the learned VQA model are indeed "known" in the dataset implicitly.
1 code implementation • 27 Aug 2021 • Amit Sharma, Vasilis Syrgkanis, Cheng Zhang, Emre Kiciman
Estimation of causal effects involves crucial assumptions about the data-generating process, such as directionality of effect, presence of instrumental variables or mediators, and whether all relevant confounders are observed.
1 code implementation • ICCV 2021 • Cheng Zhang, Zhaopeng Cui, Cai Chen, Shuaicheng Liu, Bing Zeng, Hujun Bao, yinda zhang
Panorama images have a much larger field-of-view thus naturally encode enriched scene context information compared to standard perspective images, which however is not well exploited in the previous scene understanding methods.
no code implementations • 17 Aug 2021 • Cheng Zhang, Arthur Azevedo de Amorim, Marco Gaboardi
In his seminal work, Kozen proved that KAT subsumes propositional Hoare logic, showing that one can reason about the (partial) correctness of while programs by means of the equational theory of KAT.
2 code implementations • 13 Aug 2021 • Cheng Zhang, Haocheng Wan, Xinyi Shen, Zizhao Wu
The recently developed pure Transformer architectures have attained promising accuracy on point cloud learning benchmarks compared to convolutional neural networks.
Ranked #19 on 3D Part Segmentation on ShapeNet-Part
no code implementations • 28 Jul 2021 • Cheng Zhang, Jinwoo Kim, JungHo Jeon, Jinding Xing, Changbum Ahn, Pingbo Tang, Hubo Cai
This paper will lay the foundation for identifying relevant studies to form a research roadmap to address the four knowledge gaps identified.
1 code implementation • NeurIPS 2021 • Tai-Yu Pan, Cheng Zhang, Yandong Li, Hexiang Hu, Dong Xuan, Soravit Changpinyo, Boqing Gong, Wei-Lun Chao
We propose NorCal, Normalized Calibration for long-tailed object detection and instance segmentation, a simple and straightforward recipe that reweighs the predicted scores of each class by its training sample size.
no code implementations • 25 Jun 2021 • Cheng Zhang, Pan Gao
Prior work has shown that JPEG compression can combat the drop in classification accuracy on adversarial examples to some extent.
no code implementations • ICML Workshop AML 2021 • Cheng Zhang, Pan Gao
We propose a modified VAE (variational autoencoder) as a denoiser to remove adversarial perturbations for image classification.
no code implementations • 16 Jun 2021 • Julia Grosse, Cheng Zhang, Philipp Hennig
Exciting contemporary machine learning problems have recently been phrased in the classic formalism of tree search -- most famously, the game of Go.
no code implementations • NeurIPS 2021 • Hippolyt Ritter, Martin Kukla, Cheng Zhang, Yingzhen Li
Bayesian neural networks and deep ensembles represent two modern paradigms of uncertainty quantification in deep learning.
no code implementations • 27 May 2021 • Varun Chandrasekaran, Darren Edge, Somesh Jha, Amit Sharma, Cheng Zhang, Shruti Tople
However for real-world applications, the privacy of data is critical.
no code implementations • 22 Apr 2021 • Michael Karcher, Cheng Zhang, Frederick A Matsen IV
Given overlapping subsets of a set of taxa (e. g. species), and posterior distributions on phylogenetic tree topologies for each of these taxon sets, how can we infer a posterior distribution on phylogenetic tree topologies for the entire taxon set?
no code implementations • 12 Apr 2021 • Angus Lamb, Evgeny Saveliev, Yingzhen Li, Sebastian Tschiatschek, Camilla Longden, Simon Woodhead, José Miguel Hernández-Lobato, Richard E. Turner, Pashmina Cameron, Cheng Zhang
While deep learning has obtained state-of-the-art results in many applications, the adaptation of neural network architectures to incorporate new output features remains a challenge, as neural networks are commonly trained to produce a fixed output dimension.
1 code implementation • CVPR 2021 • Cheng Zhang, Zhaopeng Cui, yinda zhang, Bing Zeng, Marc Pollefeys, Shuaicheng Liu
We not only propose an image-based local structured implicit network to improve the object shape estimation, but also refine the 3D object pose and scene layout via a novel implicit scene graph neural network that exploits the implicit local object features.
Ranked #1 on Monocular 3D Object Detection on SUN RGB-D (using extra training data)
no code implementations • 9 Mar 2021 • Xiaoqi Huang, Cheng Zhang
We consider the Schr\"odinger operators $H_V=-\Delta_g+V$ with singular potentials $V$ on general $n$-dimensional Riemannian manifolds and study whether various forms of pointwise Weyl law remain valid under this pertubation.
Analysis of PDEs Mathematical Physics Classical Analysis and ODEs Functional Analysis Mathematical Physics Spectral Theory 58J50, 35P15
no code implementations • 22 Feb 2021 • Cheng Zhang, Yunze Pan, Yunqi Zhang, Adam C. Champion, Zhaohui Shen, Dong Xuan, Zhiqiang Lin, Ness B. Shroff
Further, the evaluation shows no consistent differences among three vertex centrality measures for long-term (i. e., weekly) contact graphs, which necessitates the inclusion of SEIR simulation in our framework.
Social and Information Networks Computers and Society
1 code implementation • ICCV 2021 • Cheng Zhang, Tai-Yu Pan, Yandong Li, Hexiang Hu, Dong Xuan, Soravit Changpinyo, Boqing Gong, Wei-Lun Chao
Many objects do not appear frequently enough in complex scenes (e. g., certain handbags in living rooms) for training an accurate object detector, but are often found frequently by themselves (e. g., in product images).
1 code implementation • 22 Jan 2021 • Tabish Rashid, Cheng Zhang, Kamil Ciosek
We show the benefits of using information gain as compared to the confidence interval criterion of ResponseGraphUCB (Rowland et al. 2019), and provide theoretical results justifying our method.
no code implementations • 1 Jan 2021 • Jiadong Liang, Liangyu Zhang, Cheng Zhang, Zhihua Zhang
In this paper we propose a novel approach for stabilizing the training process of Generative Adversarial Networks as well as alleviating the mode collapse problem.
no code implementations • SEMEVAL 2020 • Cheng Zhang, Hayato Yamana
For subtask B, we simply use a sequence-pair BERT model, the official accuracy of which is 0. 53196 and ranks 25th out of 32.
1 code implementation • NeurIPS 2020 • Cheng Zhang
By handling the non-Euclidean branch length space of phylogenetic models with carefully designed permutation equivariant transformations, VBPI-NF uses normalizing flows to provide a rich family of flexible branch length distributions that generalize across different tree topologies.
no code implementations • 26 Nov 2020 • Yongming Huang, Shengheng Liu, Cheng Zhang, Xiaohu You, Hequan Wu
Future beyond fifth-generation (B5G) and sixth-generation (6G) mobile communications will shift from facilitating interpersonal communications to supporting Internet of Everything (IoE), where intelligent communications with full integration of big data and artificial intelligence (AI) will play an important role in improving network efficiency and providing high-quality service.
no code implementations • NeurIPS Workshop LMCA 2020 • Haiyan Yin, Yingzhen Li, Sinno Jialin Pan, Cheng Zhang, Sebastian Tschiatschek
Solving real-life sequential decision making problems under partial observability involves an exploration-exploitation problem.
no code implementations • 28 Oct 2020 • Philip J. Ball, Yingzhen Li, Angus Lamb, Cheng Zhang
We study a setting where the pruning phase is given a time budget, and identify connections between iterative pruning and multiple sleep cycles in humans.
no code implementations • 23 Oct 2020 • Cheng Zhang, Yicheng Sun, Hejia Chen, Jie Wang
This paper presents a novel approach to automatic generation of adequate distractors for a given question-answer pair (QAP) generated from a given article to form an adequate multiple-choice question (MCQ).
no code implementations • 23 Oct 2020 • Changfeng Yu, Cheng Zhang, Jie Wang
Accurate extraction of body text from PDF-formatted academic documents is essential in text-mining applications for deeper semantic understandings.
1 code implementation • NeurIPS 2020 • Xueru Zhang, Ruibo Tu, Yang Liu, Mingyan Liu, Hedvig Kjellström, Kun Zhang, Cheng Zhang
Our results show that static fairness constraints can either promote equality or exacerbate disparity depending on the driving factor of qualification transitions and the effect of sensitive attributes on feature distributions.
no code implementations • 15 Oct 2020 • Ling Wang, Cheng Zhang, Zejian Luo, ChenGuang Liu, Jie Liu, Xi Zheng, Athanasios Vasilakos
To reduce the computational cost without loss of generality, we present a defense strategy called a progressive defense against adversarial attacks (PDAAA) for efficiently and effectively filtering out the adversarial pixel mutations, which could mislead the neural network towards erroneous outputs, without a-priori knowledge about the attack type.
no code implementations • 4 Oct 2020 • Cheng Zhang, Jie Wang
Creating multiple-choice questions to assess reading comprehension of a given article involves generating question-answer pairs (QAPs) on the main points of the document.
1 code implementation • 4 Oct 2020 • Wenlin Yao, Cheng Zhang, Shiva Saravanan, Ruihong Huang, Ali Mostafavi
People increasingly use social media to report emergencies, seek help or share information during disasters, which makes social networks an important tool for disaster management.
no code implementations • 4 Sep 2020 • Chang Liu, Jiahui Sun, Haiming Jin, Meng Ai, Qun Li, Cheng Zhang, Kehua Sheng, Guobin Wu, XiaoHu Qie, Xinbing Wang
Thus, in this paper, we exploit adaptive dispatching intervals to boost the platform's profit under a guarantee of the maximum passenger waiting time.
no code implementations • 9 Aug 2020 • Jiadong Liang, Liangyu Zhang, Cheng Zhang, Zhihua Zhang
In this paper we propose a novel approach for stabilizing the training process of Generative Adversarial Networks as well as alleviating the mode collapse problem.
no code implementations • 23 Jul 2020 • Zichao Wang, Angus Lamb, Evgeny Saveliev, Pashmina Cameron, Yordan Zaykov, José Miguel Hernández-Lobato, Richard E. Turner, Richard G. Baraniuk, Craig Barton, Simon Peyton Jones, Simon Woodhead, Cheng Zhang
In this competition, participants will focus on the students' answer records to these multiple-choice diagnostic questions, with the aim of 1) accurately predicting which answers the students provide; 2) accurately predicting which questions have high quality; and 3) determining a personalized sequence of questions for each student that best predicts the student's answers.
1 code implementation • 23 Jul 2020 • James Jordon, Daniel Jarrett, Jinsung Yoon, Tavian Barnes, Paul Elbers, Patrick Thoral, Ari Ercole, Cheng Zhang, Danielle Belgrave, Mihaela van der Schaar
The clinical time-series setting poses a unique combination of challenges to data modeling and sharing.
no code implementations • 16 Jul 2020 • Luke Harries, Rebekah Storan Clarke, Timothy Chapman, Swamy V. P. L. N. Nallamalli, Levent Ozgur, Shuktika Jain, Alex Leung, Steve Lim, Aaron Dietrich, José Miguel Hernández-Lobato, Tom Ellis, Cheng Zhang, Kamil Ciosek
Efficient software testing is essential for productive software development and reliable user experiences.
no code implementations • 6 Jul 2020 • Ruqi Zhang, Yingzhen Li, Christopher De Sa, Sam Devlin, Cheng Zhang
Variational inference (VI) plays an essential role in approximate Bayesian inference due to its computational efficiency and broad applicability.
2 code implementations • NeurIPS 2020 • Chao Ma, Sebastian Tschiatschek, José Miguel Hernández-Lobato, Richard Turner, Cheng Zhang
Deep generative models often perform poorly in real-world applications due to the heterogeneity of natural data sets.
no code implementations • 13 Jun 2020 • Cheng Zhang
The number of static human poses is limited, it is hard to retrieve the exact videos using one single pose as the clue.
no code implementations • 7 Jun 2020 • Cheng Zhang, Francine Chen, Yan-Ying Chen
In this paper, we propose an alternative approach that learns discriminative features among triplets of images and cyclically trains on region features to verify whether attentive regions contain information indicative of a disease.
no code implementations • 20 May 2020 • Cheng Zhang, Qingsen Yan, Yu Zhu, Xianjun Li, Jinqiu Sun, Yanning Zhang
Extensive experiments demonstrate the superiority of the proposed network in terms of suppressing the chromatic aberration and noise artifacts in enhancement, especially when the low-light image has severe noise.
no code implementations • 3 May 2020 • Cheng Zhang, Kun Zhang, Yingzhen Li
We present a causal view on the robustness of neural networks against input manipulations, which applies not only to traditional classification tasks but also to general measurement data.
no code implementations • ICLR 2020 • Jacob Beck, Kamil Ciosek, Sam Devlin, Sebastian Tschiatschek, Cheng Zhang, Katja Hofmann
In many partially observable scenarios, Reinforcement Learning (RL) agents must rely on long-term memory in order to learn an optimal policy.
no code implementations • ACL 2020 • Hengyi Cai, Hongshen Chen, Yonghao Song, Cheng Zhang, Xiaofang Zhao, Dawei Yin
In this paper, we propose a data manipulation framework to proactively reshape the data distribution towards reliable samples by augmenting and highlighting effective learning samples as well as reducing the effect of inefficient samples simultaneously.
no code implementations • 12 Mar 2020 • Zichao Wang, Sebastian Tschiatschek, Simon Woodhead, Jose Miguel Hernandez-Lobato, Simon Peyton Jones, Richard G. Baraniuk, Cheng Zhang
Online education platforms enable teachers to share a large number of educational resources such as questions to form exercises and quizzes for students.
1 code implementation • 2 Mar 2020 • Hengyi Cai, Hongshen Chen, Cheng Zhang, Yonghao Song, Xiaofang Zhao, Yangxi Li, Dongsheng Duan, Dawei Yin
Current state-of-the-art neural dialogue systems are mainly data-driven and are trained on human-generated responses.
no code implementations • 18 Feb 2020 • Cheng Zhang, Qiuchi Li, Lingyu Hua, Dawei Song
To tackle the problem, in this paper, we identify and analyze the internal and external factors that affect the memory ability of RNNs, and propose a Semantic Euclidean Space to represent the semantics expressed by a sequence.
1 code implementation • IJCNLP 2019 • Hengyi Cai, Hongshen Chen, Cheng Zhang, Yonghao Song, Xiaofang Zhao, Dawei Yin
For each conversation, the model generates parameters of the encoder-decoder by referring to the input context.