1 code implementation • 22 Jan 2025 • Kun Fang, Ziyu Wang, Gus Xia, Ichiro Fujinaga
We convert the music data to symbolic inputs and evaluate LLMs' ability in detecting annotation errors in three key MIR tasks: beat tracking, chord extraction, and key estimation.
no code implementations • 20 Dec 2024 • Xingchen Song, Chengdong Liang, BinBin Zhang, Pengshen Zhang, Ziyu Wang, Youcheng Ma, Menglong Xu, Lin Wang, Di wu, Fuping Pan, Dinghao Zhou, Zhendong Peng
We refer to this as Automatic Speech Perception (ASP), and the perception results are presented in the experimental section.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
no code implementations • 8 Nov 2024 • Sreyas Venkataraman, YuFei Wang, Ziyu Wang, Zackory Erickson, David Held
Our method then learns a policy using offline RL with the reward-labeled dataset.
no code implementations • 11 Oct 2024 • Tingyu Zhu, Haoyu Liu, Ziyu Wang, Zhimin Jiang, Zeyu Zheng
Developing generative models to create or conditionally create symbolic music presents unique challenges due to the combination of limited data availability and the need for high precision in note pitch.
no code implementations • 4 Oct 2024 • Ziyu Wang, Shuangpeng Han, Mike Zheng Shou, Mengmi Zhang
PPL uses a hierarchical memory to store compositional parts of prototypical poses, from which we distill a general pose prior.
no code implementations • 28 Sep 2024 • Ziyu Wang, Hao Li, Di Huang, Amir M. Rahmani
In digital healthcare, large language models (LLMs) have primarily been utilized to enhance question-answering capabilities and improve patient interactions.
no code implementations • 27 Aug 2024 • Longshen Ou, Jingwei Zhao, Ziyu Wang, Gus Xia, Ye Wang
Large language models have shown significant capabilities across various domains, including symbolic music generation.
1 code implementation • 26 Aug 2024 • Yinghao Ma, Anders Øland, Anton Ragni, Bleiz MacSen Del Sette, Charalampos Saitis, Chris Donahue, Chenghua Lin, Christos Plachouras, Emmanouil Benetos, Elona Shatri, Fabio Morreale, Ge Zhang, György Fazekas, Gus Xia, huan zhang, Ilaria Manco, Jiawen Huang, Julien Guinot, Liwei Lin, Luca Marinelli, Max W. Y. Lam, Megha Sharma, Qiuqiang Kong, Roger B. Dannenberg, Ruibin Yuan, Shangda Wu, Shih-Lun Wu, Shuqi Dai, Shun Lei, Shiyin Kang, Simon Dixon, Wenhu Chen, Wenhao Huang, Xingjian Du, Xingwei Qu, Xu Tan, Yizhi Li, Zeyue Tian, Zhiyong Wu, Zhizheng Wu, Ziyang Ma, Ziyu Wang
In recent years, foundation models (FMs) such as large language models (LLMs) and latent diffusion models (LDMs) have profoundly impacted diverse sectors, including music.
no code implementations • 11 Jul 2024 • Seyed Amir Hossein Aqajari, Ziyu Wang, Ali Tazarv, Sina Labbaf, Salar Jafarlou, Brenda Nguyen, Nikil Dutt, Marco Levorato, Amir M. Rahmani
The challenge is to timely send EMAs, especially during stress, balancing monitoring efficiency and user convenience.
no code implementations • 4 Jul 2024 • Yuxuan Wu, Ziyu Wang, Bhiksha Raj, Gus Xia
We contribute an unsupervised method that effectively learns from raw observation and disentangles its latent space into content and style representations.
1 code implementation • 7 Jun 2024 • Ziyu Wang, Chris Holmes
Our experiments provide a principled evaluation of task-specific calibration, and demonstrate that epistemic uncertainty offers a promising deferral strategy for efficient data acquisition in in-context learning.
1 code implementation • 2 Jun 2024 • Fabian Falck, Ziyu Wang, Chris Holmes
In-context learning (ICL) has emerged as a particularly remarkable characteristic of Large Language Models (LLM): given a pretrained LLM and an observed dataset, LLMs can make predictions for new data points from the same distribution without fine-tuning.
no code implementations • 30 May 2024 • Longwen Zhang, Ziyu Wang, Qixuan Zhang, QIwei Qiu, Anqi Pang, Haoran Jiang, Wei Yang, Lan Xu, Jingyi Yu
To narrow this disparity, we introduce CLAY, a 3D geometry and material generator designed to effortlessly transform human imagination into intricate 3D digital structures.
1 code implementation • Biomedical Signal Processing and Control 2024 • Yuzhu Cao, Weiwei Cao, Ziyu Wang, Gang Yuan, Zeyi Li, Xinye Ni, Jian Zheng
The RD-LKA layer utilizes anisotropic depth-wise large kernel convolutions to capture large receptive fields with an extremely low parameter count while modeling long-range spatial relationships.
Ranked #1 on
Medical Image Registration
on IXI
1 code implementation • 26 May 2024 • Shuangpeng Han, Ziyu Wang, Mengmi Zhang
Biological motion perception (BMP) refers to humans' ability to perceive and recognize the actions of living beings solely from their motion patterns, sometimes as minimal as those depicted on point-light displays.
no code implementations • 22 May 2024 • Hongkai Chen, Zixin Luo, Yurun Tian, Xuyang Bai, Ziyu Wang, Lei Zhou, Mingmin Zhen, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan
Identifying robust and accurate correspondences across images is a fundamental problem in computer vision that enables various downstream tasks.
2 code implementations • 16 May 2024 • Ziyu Wang, Lejun Min, Gus Xia
A cascaded diffusion model is trained to model the hierarchical language, where each level is conditioned on its upper levels.
no code implementations • 11 Apr 2024 • Ming Cheng, BoWen Zhang, Ziyu Wang, Ziyi Zhou, Weiqi Feng, Yi Lyu, Xingjian Diao
Trajectory similarity search plays an essential role in autonomous driving, as it enables vehicles to analyze the information and characteristics of different trajectories to make informed decisions and navigate safely in dynamic environments.
1 code implementation • 28 Mar 2024 • Ziyu Wang, Chris Holmes
Bayesian modelling allows for the quantification of predictive uncertainty which is crucial in safety-critical applications.
no code implementations • 29 Feb 2024 • Tianyi Zhang, Li Zhang, Zhaoyi Hou, Ziyu Wang, Yuling Gu, Peter Clark, Chris Callison-Burch, Niket Tandon
Planning in a text-based environment continues to be a major challenge for AI systems.
1 code implementation • 25 Feb 2024 • Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Ziyang Ma, Liumeng Xue, Ziyu Wang, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Pengfei Li, Jingcheng Wu, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Emmanouil Benetos, Jie Fu, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo
It is based on continual pre-training and finetuning LLaMA2 on a text-compatible music representation, ABC notation, and the music is treated as a second language.
no code implementations • 16 Feb 2024 • Ziyu Wang, Zhongqi Yang, Iman Azimi, Amir M. Rahmani
Mental health conditions, prevalent across various demographics, necessitate efficient monitoring to mitigate their adverse impacts on life quality.
no code implementations • 8 Feb 2024 • Weikang Wan, Ziyu Wang, YuFei Wang, Zackory Erickson, David Held
The key to our approach is to leverage the recent progress in differentiable trajectory optimization, which enables computing the gradients of the loss with respect to the parameters of trajectory optimization.
1 code implementation • 28 Dec 2023 • Ziyu Wang, Yanjie Ze, Yifei Sun, Zhecheng Yuan, Huazhe Xu
Learning policies that can generalize to unseen environments is a fundamental challenge in visual reinforcement learning (RL).
no code implementations • 15 Dec 2023 • Suyi Jiang, Haimin Luo, Haoran Jiang, Ziyu Wang, Jingyi Yu, Lan Xu
Recent months have witnessed rapid progress in 3D generation based on diffusion models.
1 code implementation • CVPR 2024 • Ziyu Wang, Yue Xu, Cewu Lu, Yong-Lu Li
It first distills the videos into still images as static memory and then compensates the dynamic and motion information with a learnable dynamic memory block.
no code implementations • 3 Nov 2023 • Ziyu Wang, Wenhao Jiang, Zixuan Zhang, Wei Tang, Junchi Yan
Sequential processes in real-world often carry a combination of simple subsystems that interact with each other in certain forms.
1 code implementation • 25 Oct 2023 • Jingwei Zhao, Gus Xia, Ziyu Wang, Ye Wang
In the realm of music AI, arranging rich and structured multi-track accompaniments from a simple lead sheet presents significant challenges.
2 code implementations • 28 May 2023 • Yue Xu, Yong-Lu Li, Kaitong Cui, Ziyu Wang, Cewu Lu, Yu-Wing Tai, Chi-Keung Tang
We believe this paradigm will open up new avenues in the dynamics of distillation and pave the way for efficient dataset distillation.
no code implementations • 26 May 2023 • Gaole Dai, Wei Wu, Ziyu Wang, Jie Fu, Shanghang Zhang, Tiejun Huang
By incorporating hand-designed optimizers as the second component in our hybrid approach, we are able to retain the benefits of learned optimizers while stabilizing the training process and, more importantly, improving testing performance.
no code implementations • 23 May 2023 • Yuting Wu, Qiwen Wang, Ziyu Wang, Xinxin Wang, Buvna Ayyagari, Siddarth Krishnan, Michael Chudzik, Wei D. Lu
The efficacy of training larger models is evaluated using realistic hardware parameters and shows that that analog CIM modules can enable efficient mix-precision DNN training with accuracy comparable to full-precision software trained models.
no code implementations • 13 Apr 2023 • Ziyu Wang, Yuting Wu, Yongmo Park, Sangmin Yoo, Xinxin Wang, Jason K. Eshraghian, Wei D. Lu
Analog compute-in-memory (CIM) systems are promising for deep neural network (DNN) inference acceleration due to their energy efficiency and high throughput.
no code implementations • CVPR 2023 • Liao Wang, Qiang Hu, Qihan He, Ziyu Wang, Jingyi Yu, Tinne Tuytelaars, Lan Xu, Minye Wu
The success of the Neural Radiance Fields (NeRFs) for modeling and free-view rendering static objects has inspired numerous attempts on dynamic scenes.
no code implementations • 19 Mar 2023 • Sangmin Yoo, Eric Yeu-Jer Lee, Ziyu Wang, Xinxin Wang, Wei D. Lu
Event-based cameras are inspired by the sparse and asynchronous spike representation of the biological visual system.
no code implementations • 9 Mar 2023 • Wenkai Tan, Justus Renkhoff, Alvaro Velasquez, Ziyu Wang, Lusi Li, Jian Wang, Shuteng Niu, Fan Yang, Yongxin Liu, Houbing Song
Our work could provide a useful tool to defend against certain adversarial attacks on deep neural networks.
1 code implementation • NeurIPS 2023 • Ziyu Wang, Mike Zheng Shou, Mengmi Zhang
To capture compositional entities of the scene, we proposed cyclic walks between perceptual features extracted from vision transformers and object entities.
no code implementations • CVPR 2023 • Suyi Jiang, Haoran Jiang, Ziyu Wang, Haimin Luo, Wenzheng Chen, Lan Xu
With the aid of the anchor image, we adapt a 3D reconstructor for fine-grained details synthesis and propose a two-stage blending scheme to boost appearance generation.
no code implementations • 29 Oct 2022 • Ziyu Wang, Yucen Luo, Yueru Li, Jun Zhu, Bernhard Schölkopf
For nonparametric conditional moment models, efficient estimation often relies on preimposed conditions on various measures of ill-posedness of the hypothesis space, which are hard to validate when flexible models are used.
no code implementations • 30 Sep 2022 • Zheng Cao, Raymond Guo, Caesar M. Tuguinay, Mark Pock, Jiayi Gao, Ziyu Wang
This paper presents a methodology for combining programming and mathematics to optimize elevator wait times.
1 code implementation • 21 Sep 2022 • Yang Qu, Yutian Qin, Lecheng Chao, Hangkai Qian, Ziyu Wang, Gus Xia
The relationship between perceptual loudness and physical attributes of sound is an important subject in both computer music and psychoacoustics.
no code implementations • 9 Sep 2022 • Ziyu Wang, Yu Deng, Jiaolong Yang, Jingyi Yu, Xin Tong
Experiments show that our method can successfully learn the generative model from unstructured monocular images and well disentangle the shape and appearance for objects (e. g., chairs) with large topological variance.
1 code implementation • CVPR 2022 • Zhihui Lin, Tianyu Yang, Maomao Li, Ziyu Wang, Chun Yuan, Wenhao Jiang, Wei Liu
Matching-based methods, especially those based on space-time memory, are significantly ahead of other solutions in semi-supervised video object segmentation (VOS).
Semantic Segmentation
Semi-Supervised Video Object Segmentation
+1
1 code implementation • 22 May 2022 • Ziyu Wang, Yuhao Zhou, Jun Zhu
We investigate nonlinear instrumental variable (IV) regression given high-dimensional instruments.
no code implementations • 8 Mar 2022 • Ziyu Wang, Wei Yang, Junming Cao, Lan Xu, Junqing Yu, Jingyi Yu
We present a novel neural refractive field(NeReF) to recover wavefront of transparent fluids by simultaneously estimating the surface position and normal of the fluid front.
1 code implementation • CVPR 2022 • Klaus Greff, Francois Belletti, Lucas Beyer, Carl Doersch, Yilun Du, Daniel Duckworth, David J. Fleet, Dan Gnanapragasam, Florian Golemo, Charles Herrmann, Thomas Kipf, Abhijit Kundu, Dmitry Lagun, Issam Laradji, Hsueh-Ti, Liu, Henning Meyer, Yishu Miao, Derek Nowrouzezahrai, Cengiz Oztireli, Etienne Pot, Noha Radwan, Daniel Rebain, Sara Sabour, Mehdi S. M. Sajjadi, Matan Sela, Vincent Sitzmann, Austin Stone, Deqing Sun, Suhani Vora, Ziyu Wang, Tianhao Wu, Kwang Moo Yi, Fangcheng Zhong, Andrea Tagliasacchi
Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details.
2 code implementations • 28 Jan 2022 • Ziyu Wang, Wenhao Jiang, Yiming Zhu, Li Yuan, Yibing Song, Wei Liu
In contrast with vision transformers and CNNs, the success of MLP-like models shows that simple information fusion operations among tokens and channels can yield a good representation power for deep recognition models.
1 code implementation • 30 Dec 2021 • Ziyu Wang, Dejing Xu, Gus Xia, Ying Shan
This is the audio-to-symbolic arrangement problem we tackle in this paper.
no code implementations • 26 Oct 2021 • Di wu, Yi Shi, Ziyu Wang, Jie Yang, Mohamad Sawan
Although compressive sensing (CS) can be adopted to compress the signals to reduce communication bandwidth requirement, it needs a complex reconstruction procedure before the signal can be used for seizure prediction.
no code implementations • 12 Aug 2021 • Liao Wang, Ziyu Wang, Pei Lin, Yuheng Jiang, Xin Suo, Minye Wu, Lan Xu, Jingyi Yu
To fill this gap, in this paper we propose a neural interactive bullet-time generator (iButter) for photo-realistic human free-viewpoint rendering from dense RGB streams, which enables flexible and interactive design for human bullet-time visual effects.
1 code implementation • NeurIPS 2021 • Ziyu Wang, Yuhao Zhou, Tongzheng Ren, Jun Zhu
Recent years have witnessed an upsurge of interest in employing flexible machine learning models for instrumental variable (IV) regression, but the development of uncertainty quantification methodology is still lacking.
no code implementations • NeurIPS 2021 • Ziyu Wang, Yuhao Zhou, Tongzheng Ren, Jun Zhu
Recent years have witnessed an upsurge of interest in employing flexible machine learning models for instrumental variable (IV) regression, but the development of uncertainty quantification methodology is still lacking.
no code implementations • 5 May 2021 • Ziyu Wang, Jie Yang, Mohamad Sawan
Accurate prediction of epileptic seizures allows patients to take preventive measures in advance to avoid possible injuries.
no code implementations • ICLR 2021 • Michael R. Zhang, Tom Le Paine, Ofir Nachum, Cosmin Paduraru, George Tucker, Ziyu Wang, Mohammad Norouzi
This modeling choice assumes that different dimensions of the next state and reward are conditionally independent given the current state and action and may be driven by the fact that fully observable physics-based simulation environments entail deterministic transition dynamics.
no code implementations • 6 Apr 2021 • Ziyu Wang, Liao Wang, Fuqiang Zhao, Minye Wu, Lan Xu, Jingyi Yu
In this paper, we propose MirrorNeRF - a one-shot neural portrait free-viewpoint rendering approach using a catadioptric imaging system with multiple sphere mirrors and a single high-resolution digital camera, which is the first to combine neural radiance field with catadioptric imaging so as to enable one-shot photo-realistic human portrait reconstruction and rendering, in a low-cost and casual capture setting.
3 code implementations • ICLR 2021 • Justin Fu, Mohammad Norouzi, Ofir Nachum, George Tucker, Ziyu Wang, Alexander Novikov, Mengjiao Yang, Michael R. Zhang, Yutian Chen, Aviral Kumar, Cosmin Paduraru, Sergey Levine, Tom Le Paine
Off-policy evaluation (OPE) holds the promise of being able to leverage large, offline datasets for both evaluating and selecting complex policies for decision making.
no code implementations • 17 Mar 2021 • Caglar Gulcehre, Sergio Gómez Colmenarejo, Ziyu Wang, Jakub Sygnowski, Thomas Paine, Konrad Zolna, Yutian Chen, Matthew Hoffman, Razvan Pascanu, Nando de Freitas
Due to bootstrapping, these errors get amplified during training and can lead to divergence, thereby crippling learning.
no code implementations • 1 Jan 2021 • Caglar Gulcehre, Sergio Gómez Colmenarejo, Ziyu Wang, Jakub Sygnowski, Thomas Paine, Konrad Zolna, Yutian Chen, Matthew Hoffman, Razvan Pascanu, Nando de Freitas
These errors can be compounded by bootstrapping when the function approximator overestimates, leading the value function to *grow unbounded*, thereby crippling learning.
1 code implementation • 14 Dec 2020 • Qipeng Guo, Zhijing Jin, Ziyu Wang, Xipeng Qiu, Weinan Zhang, Jun Zhu, Zheng Zhang, David Wipf
Cycle-consistent training is widely used for jointly learning a forward and inverse mapping between two domains of interest without the cumbersome requirement of collecting matched pairs within each domain.
1 code implementation • NeurIPS 2020 • Caglar Gulcehre, Ziyu Wang, Alexander Novikov, Thomas Paine, Sergio Gómez, Konrad Zolna, Rishabh Agarwal, Josh S. Merel, Daniel J. Mankowitz, Cosmin Paduraru, Gabriel Dulac-Arnold, Jerry Li, Mohammad Norouzi, Matthew Hoffman, Nicolas Heess, Nando de Freitas
We hope that our suite of benchmarks will increase the reproducibility of experiments and make it possible to study challenging tasks with a limited computational budget, thus making RL research both more systematic and more accessible across the community.
no code implementations • 27 Nov 2020 • Konrad Zolna, Alexander Novikov, Ksenia Konyushkova, Caglar Gulcehre, Ziyu Wang, Yusuf Aytar, Misha Denil, Nando de Freitas, Scott Reed
Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations.
1 code implementation • NeurIPS 2020 • Ziyu Wang, Bin Dai, David Wipf, Jun Zhu
The recent, counter-intuitive discovery that deep generative models (DGMs) can frequently assign a higher likelihood to outliers has implications for both outlier detection applications as well as our overall understanding of generative modeling.
2 code implementations • 17 Aug 2020 • Ziyu Wang, Yiyi Zhang, Yixiao Zhang, Junyan Jiang, Ruihan Yang, Junbo Zhao, Gus Xia
The dominant approach for music representation learning involves the deep unsupervised model family variational autoencoder (VAE).
1 code implementation • 17 Aug 2020 • Ziyu Wang, Ke Chen, Junyan Jiang, Yiyi Zhang, Maoran Xu, Shuqi Dai, Xianbin Gu, Gus Xia
The main body of the dataset contains the vocal melody, the lead instrument melody, and the piano accompaniment for each song in MIDI format, which are aligned to the original audio files.
2 code implementations • 17 Aug 2020 • Ziyu Wang, Dingsu Wang, Yixiao Zhang, Gus Xia
While deep generative models have become the leading methods for algorithmic composition, it remains a challenging problem to control the generation process because the latent variables of most deep-learning models lack good interpretability.
no code implementations • 17 Jul 2020 • Tom Le Paine, Cosmin Paduraru, Andrea Michi, Caglar Gulcehre, Konrad Zolna, Alexander Novikov, Ziyu Wang, Nando de Freitas
Therefore, in this work, we focus on \textit{offline hyperparameter selection}, i. e. methods for choosing the best policy from a set of many policies trained using different hyperparameters, given only logged data.
5 code implementations • NeurIPS 2020 • Ziyu Wang, Alexander Novikov, Konrad Zolna, Jost Tobias Springenberg, Scott Reed, Bobak Shahriari, Noah Siegel, Josh Merel, Caglar Gulcehre, Nicolas Heess, Nando de Freitas
Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction.
2 code implementations • 24 Jun 2020 • Caglar Gulcehre, Ziyu Wang, Alexander Novikov, Tom Le Paine, Sergio Gomez Colmenarejo, Konrad Zolna, Rishabh Agarwal, Josh Merel, Daniel Mankowitz, Cosmin Paduraru, Gabriel Dulac-Arnold, Jerry Li, Mohammad Norouzi, Matt Hoffman, Ofir Nachum, George Tucker, Nicolas Heess, Nando de Freitas
We hope that our suite of benchmarks will increase the reproducibility of experiments and make it possible to study challenging tasks with a limited computational budget, thus making RL research both more systematic and more accessible across the community.
5 code implementations • 1 Jun 2020 • Matthew W. Hoffman, Bobak Shahriari, John Aslanides, Gabriel Barth-Maron, Nikola Momchev, Danila Sinopalnikov, Piotr Stańczyk, Sabela Ramos, Anton Raichuk, Damien Vincent, Léonard Hussenot, Robert Dadashi, Gabriel Dulac-Arnold, Manu Orsini, Alexis Jacq, Johan Ferret, Nino Vieillard, Seyed Kamyar Seyed Ghasemipour, Sertan Girgin, Olivier Pietquin, Feryal Behbahani, Tamara Norman, Abbas Abdolmaleki, Albin Cassirer, Fan Yang, Kate Baumli, Sarah Henderson, Abe Friesen, Ruba Haroun, Alex Novikov, Sergio Gómez Colmenarejo, Serkan Cabi, Caglar Gulcehre, Tom Le Paine, Srivatsan Srinivasan, Andrew Cowie, Ziyu Wang, Bilal Piot, Nando de Freitas
These implementations serve both as a validation of our design decisions as well as an important contribution to reproducibility in RL research.
1 code implementation • pproximateinference AABI Symposium 2019 • Ziyu Wang, Shuyu Cheng, Yueru Li, Jun Zhu, Bo Zhang
Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative.
no code implementations • 14 Jan 2020 • Jianyu Niu, Ziyu Wang, Fangyu Gai, Chen Feng
First, we propose a new incentive analysis that takes the network capacity into account, showing that Bitcoin-NG can still maintain incentive compatibility against the microblock mining attack even under limited network capacity.
Cryptography and Security Distributed, Parallel, and Cluster Computing
no code implementations • ICML 2020 • Bin Dai, Ziyu Wang, David Wipf
In narrow asymptotic settings Gaussian VAE models of continuous data have been shown to possess global optima aligned with ground-truth distributions.
no code implementations • 2 Oct 2019 • Konrad Zolna, Scott Reed, Alexander Novikov, Sergio Gomez Colmenarejo, David Budden, Serkan Cabi, Misha Denil, Nando de Freitas, Ziyu Wang
We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels.
1 code implementation • 26 Sep 2019 • Serkan Cabi, Sergio Gómez Colmenarejo, Alexander Novikov, Ksenia Konyushkova, Scott Reed, Rae Jeong, Konrad Zolna, Yusuf Aytar, David Budden, Mel Vecerik, Oleg Sushkov, David Barker, Jonathan Scholz, Misha Denil, Nando de Freitas, Ziyu Wang
We present a framework for data-driven robotics that makes use of a large dataset of recorded robot experience and scales to several tasks using learned reward functions.
1 code implementation • ICLR 2020 • Tom Le Paine, Caglar Gulcehre, Bobak Shahriari, Misha Denil, Matt Hoffman, Hubert Soyer, Richard Tanburn, Steven Kapturowski, Neil Rabinowitz, Duncan Williams, Gabriel Barth-Maron, Ziyu Wang, Nando de Freitas, Worlds Team
This paper introduces R2D3, an agent that makes efficient use of demonstrations to solve hard exploration problems in partially observable environments with highly variable initial conditions.
3 code implementations • 9 Jun 2019 • Ruihan Yang, Dingsu Wang, Ziyu Wang, Tianyao Chen, Junyan Jiang, Gus Xia
Analogy-making is a key method for computer algorithms to generate both natural and creative music pieces.
no code implementations • ICLR 2019 • Scott Reed, Yusuf Aytar, Ziyu Wang, Tom Paine, Aäron van den Oord, Tobias Pfaff, Sergio Gomez, Alexander Novikov, David Budden, Oriol Vinyals
The proposed agent can solve a challenging robot manipulation task of block stacking from only video demonstrations and sparse reward, in which the non-imitating agents fail to learn completely.
1 code implementation • ICLR 2019 • Ziyu Wang, Tongzheng Ren, Jun Zhu, Bo Zhang
While Bayesian neural networks (BNNs) have drawn increasing attention, their posterior inference remains challenging, due to the high-dimensional and over-parameterized nature.
no code implementations • 28 Dec 2018 • Ziyu Wang, Gus Xia
Second, the melody generation model generates the lead melody and other voices (melody lines) of the accompaniment using seasonal ARMA (Autoregressive Moving Average) processes.
no code implementations • 17 Dec 2018 • Yutian Chen, Aja Huang, Ziyu Wang, Ioannis Antonoglou, Julian Schrittwieser, David Silver, Nando de Freitas
During the development of AlphaGo, its many hyper-parameters were tuned with Bayesian optimization multiple times.
no code implementations • ICLR 2019 • Tom Le Paine, Sergio Gómez Colmenarejo, Ziyu Wang, Scott Reed, Yusuf Aytar, Tobias Pfaff, Matt W. Hoffman, Gabriel Barth-Maron, Serkan Cabi, David Budden, Nando de Freitas
MetaMimic can learn both (i) policies for high-fidelity one-shot imitation of diverse novel skills, and (ii) policies that enable the agent to solve tasks more efficiently than the demonstrators.
1 code implementation • NeurIPS 2018 • Yusuf Aytar, Tobias Pfaff, David Budden, Tom Le Paine, Ziyu Wang, Nando de Freitas
One successful method of guiding exploration in these domains is to imitate trajectories provided by a human demonstrator.
1 code implementation • ICLR 2018 • Yuke Zhu, Ziyu Wang, Josh Merel, Andrei Rusu, Tom Erez, Serkan Cabi, Saran Tunyasuvunakool, János Kramár, Raia Hadsell, Nando de Freitas, Nicolas Heess
We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent.
no code implementations • ICLR 2018 • Karol Hausman, Jost Tobias Springenberg, Ziyu Wang, Nicolas Heess, Martin Riedmiller
We present a method for reinforcement learning of closely related skills that are parameterized via a skill embedding space.
no code implementations • 11 Jul 2017 • Serkan Cabi, Sergio Gómez Colmenarejo, Matthew W. Hoffman, Misha Denil, Ziyu Wang, Nando de Freitas
This paper introduces the Intentional Unintentional (IU) agent.
no code implementations • NeurIPS 2017 • Ziyu Wang, Josh Merel, Scott Reed, Greg Wayne, Nando de Freitas, Nicolas Heess
Compared to purely supervised methods, Generative Adversarial Imitation Learning (GAIL) can learn more robust controllers from fewer demonstrations, but is inherently mode-seeking and more difficult to train.
1 code implementation • 7 Jul 2017 • Josh Merel, Yuval Tassa, Dhruva TB, Sriram Srinivasan, Jay Lemmon, Ziyu Wang, Greg Wayne, Nicolas Heess
Rapid progress in deep reinforcement learning has made it increasingly feasible to train controllers for high-dimensional humanoid bodies.
6 code implementations • 7 Jul 2017 • Nicolas Heess, Dhruva TB, Srinivasan Sriram, Jay Lemmon, Josh Merel, Greg Wayne, Yuval Tassa, Tom Erez, Ziyu Wang, S. M. Ali Eslami, Martin Riedmiller, David Silver
The reinforcement learning paradigm allows, in principle, for complex behaviours to be learned directly from simple reward signals.
no code implementations • ICML 2017 • Scott Reed, Aäron van den Oord, Nal Kalchbrenner, Sergio Gómez Colmenarejo, Ziyu Wang, Dan Belov, Nando de Freitas
Our new PixelCNN model achieves competitive density estimation and orders of magnitude speedup - O(log N) sampling instead of O(N) - enabling the practical generation of 512x512 images.
Ranked #2 on
Image Compression
on ImageNet32
7 code implementations • 3 Nov 2016 • Ziyu Wang, Victor Bapst, Nicolas Heess, Volodymyr Mnih, Remi Munos, Koray Kavukcuoglu, Nando de Freitas
This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several continuous control problems.
73 code implementations • 20 Nov 2015 • Ziyu Wang, Tom Schaul, Matteo Hessel, Hado van Hasselt, Marc Lanctot, Nando de Freitas
In recent years there have been many successes of using deep representations in reinforcement learning.
Ranked #1 on
Atari Games
on Atari 2600 Pong
no code implementations • 22 Dec 2014 • Yishu Miao, Ziyu Wang, Phil Blunsom
This paper presents novel Bayesian optimisation algorithms for minimum error rate training of statistical machine translation systems.
1 code implementation • ICCV 2015 • Zichao Yang, Marcin Moczulski, Misha Denil, Nando de Freitas, Alex Smola, Le Song, Ziyu Wang
The fully connected layers of a deep convolutional neural network typically contain over 90% of the network parameters, and consume the majority of the memory required to store the network parameters.
Ranked #44 on
Image Classification
on MNIST
no code implementations • 27 Oct 2014 • John-Alexander M. Assael, Ziyu Wang, Bobak Shahriari, Nando de Freitas
At the core of this approach is a Gaussian process prior that captures our belief about the distribution over functions.
1 code implementation • 30 Jun 2014 • Ziyu Wang, Nando de Freitas
Bayesian optimisation has gained great popularity as a tool for optimising the parameters of machine learning algorithms and models.
no code implementations • 18 Jun 2014 • Bobak Shahriari, Ziyu Wang, Matthew W. Hoffman, Alexandre Bouchard-Côté, Nando de Freitas
How- ever, the performance of a Bayesian optimization method very much depends on its exploration strategy, i. e. the choice of acquisition function, and it is not clear a priori which choice will result in superior performance.
no code implementations • 27 Feb 2014 • Ziyu Wang, Babak Shakibi, Lin Jin, Nando de Freitas
In this paper, we introduce a new technique for efficient global optimization that combines Gaussian process confidence bounds and treed simultaneous optimistic optimization to eliminate the need for auxiliary optimization of acquisition functions.
1 code implementation • 9 Jan 2013 • Ziyu Wang, Frank Hutter, Masrour Zoghi, David Matheson, Nando de Freitas
Bayesian optimization techniques have been successfully applied to robotics, planning, sensor placement, recommendation, advertising, intelligent user interfaces and automatic algorithm configuration.