Hot Tweets

@DeepMind
Does Bayesian deep learning work? The Neural Testbed provides tools to evaluate uncertainty estimates. These tools… https://t.co/0vpB23VeZg
2021-10-12 Super Hot
@ylecun
Nice move, @DeepMind ! https://t.co/ZEOrDwVQg0
2021-10-18 Super Hot
@ylecun
A short history of neural net architectures 1958-2021. https://t.co/LJukW2rVX4
2021-10-09 Super Hot
@ylecun
"Facebook Loves Self-Supervised Learning. Period." Nice article at Analytics India. They got that right. (Though t… https://t.co/ChFoOIWR5G
2021-10-12 Super Hot
@stevenstrogatz
A big new review article about “social physics“ — The world of social phenomena as seen through the eyes of physici… https://t.co/g1nPc2yCAY
2021-10-06 Hot
@ylecun
"Learning in High Dimension Always Amounts to Extrapolation" by Randall Balestriero, Jerome Pesenti, and Yann LeCun… https://t.co/HO4xOCcqhY
2021-10-19 Hot
@ylecun
Huge announcement! Facebook will create 10,000 new high-skilled jobs within the European Union (EU) over the next f… https://t.co/LYvTNjE88D
2021-10-18 Hot
@iota
Did you know that messages with differing delays grow the #Tangle differently? We explore this topic in our most r… https://t.co/9TbgcwV5nw
2021-10-14 Hot
@KirkDBorne
Google is upping the #AutoML game with 162 resources on its website and 153 open-source AutoML APIs, libraries and… https://t.co/uJ6tOacyJ9
2021-10-11 Hot
@ylecun
Ego4D: 2200 hours of first-person videos collected from 700 persons around the world going about their daily activi… https://t.co/8MtEeYROM4
2021-10-14 Hot
@ylecun
Using deep learning to predict the (in)stability of planetary systems. Another example of training deep nets to che… https://t.co/UbLlWZMnEf
2021-10-15 Hot
@KirkDBorne
Get FREE 1020-page PDF at https://t.co/FOW0eGBtKd ➕ plus explore the interactive #DeepLearning eBook with Multi-Fra… https://t.co/Wwn3aelsuJ
2021-10-06 Hot
@TwitterEng
We built a causal estimation framework on the idea of statistical 'surrogacy' (Athey et al 2016) - when we can’t wa… https://t.co/44MSD93IMp
2021-10-18 Hot
@PantosIO
We have amazing news to share! Our paper on decentralised cross-blockchain asset transfers has been successfully ac… https://t.co/kSYeoTgVeS
2021-10-12 Hot
@ylecun
Tenure-track faculty positions in AI are open at NYU. This search is part of a university-wide AI initiative. Joi… https://t.co/1K1WTacOHy
2021-10-16 Hot
@ylecun
The multi-year heroic quest by FAIR's Sam Gross @colesbury to make a *true* multi-threaded version of CPython with… https://t.co/lixyJtD6Ys
2021-10-16 Hot
@ylecun
Cobtrastive Self-Supervised Learning applied to ConvNets for the detection of gravitational lensing galaxies. https://t.co/pFU3jbt6Pz
2021-10-06 Hot
@KirkDBorne
Download Free eBook (47-page PDF) — The #Mathematics needed in preparation for an introductory class in… https://t.co/odNi49o6P1
2021-10-14 Hot
@KirkDBorne
*Online* eBook [open access] — #MachineLearning from Scratch: https://t.co/u4GumM3qNZ via @DataScienceCtrl —————… https://t.co/wL5HnkcP5H
2021-10-14 Hot
@NandoDF
Very proud of this step. It’s through sharing of simulators, code and data that robotics will progress. This cable… https://t.co/hZs88ilbGl
2021-10-19 Hot
@NandoDF
Amazing ⁦@UniofOxford⁩ !! Oxford changes its start-up policy at last. I’m so happy for the departments, ⁦faculty an… https://t.co/N4yYPfwUqS
2021-10-17 Hot
@KirkDBorne
Get FREE PDF eBooks at @DataScienceCtrl https://t.co/VWdHNT2IQw #abdsc ————— #BigData #Analytics #MachineLearning… https://t.co/wvcDCKhFKM
2021-10-09 Hot
@skdh
I've written yet another paper (working off a backlog) https://t.co/pTVlVqCi7R
2021-10-15 Hot
@gcluley
#BugsInOurPockets Over a dozen security experts have published a new study that casts a critical eye at Apple's pl… https://t.co/KLmeKEvthF
2021-10-15 Hot
@DeepMind
A unified way to discover and manipulate options: how the successor representation can be seen as a natural substra… https://t.co/nFXAITuSUr
2021-10-13 Hot
@EFF
In client side scanning, “users’ data is searched by law enforcement in ways that cannot be predicted or audited by… https://t.co/CjEBeVGpx3
2021-10-19 Hot
@KirkDBorne
[FREE 479-page PDF eBook] The #Mathematics and #Statistics Foundations of #DataScience: https://t.co/13AdC8x8pA ———… https://t.co/4lrw1W9YsZ
2021-10-07 Hot
@KirkDBorne
The Most Important Fundamentals of #PyTorch to Know for #DeepLearning: https://t.co/qzkHtpJqB1 ————— #BigData… https://t.co/IODDReSMlh
2021-10-16 Hot
@EconomistaFlait
Un peiper que me gusta mucho del Nobel, Guido Imbens, es uno que tiene con la seca de su esposa la @Susan_Athey ha… https://t.co/E2v3HCqEDV
2021-10-11
@KirkDBorne
Get FREE 1000+ page PDF at https://t.co/FOW0eGT58N and explore this interactive #DeepLearning eBook with Multi-Fram… https://t.co/dz73sJrBJ7
2021-10-14
@omarsar0
Deep learning seems unstoppable! I'm particularly impressed by the recent progress of deep learning on tabular data… https://t.co/veRTtFjBjX
2021-10-06
@srlm
DOIS BILHÕES de TWEETS de 87 milhões de pessoas de 218 países, em 67 línguas... saiu o primeiro ESTUDO a capturar a… https://t.co/X5tn5THdWT
2021-10-12
@yoshitomo_cs
#技育展　AI・機械学習・データ分析部門でtorchdistillが最優秀賞を頂きましたー🎉🎉🎉 Code: https://t.co/4cWQIL8x1Z 論文: https://t.co/GX9JaDRW2r プレプリント:… https://t.co/KMXHXyhUqm
2021-10-09
@arduino
This paper presents the successful first attempt at deploying federated transfer learning to a Nano 33 BLE Sense:… https://t.co/WxR8ntHsK0
2021-10-07
@ylecun
Bumping this thread. Haha. https://t.co/PyXPed9vyw
2021-10-18
@goto_yuta_
ResNet登場(2015年)以来、ニューラルネットの訓練手法も進化していて、最新のレシピで訓練したResNetを評価したところ、精度がかなり上がったという話。 timm(pytorch-image-models)に公開されている。 https://t.co/AF2tKzytwu
2021-10-10
@SpirosMargaris
How is Technology #Changing The World Today? https://t.co/BFVCdanCtG #fintech #insurtech #AI… https://t.co/ltQhnquC4t
2021-10-09
@KirkDBorne
[UPDATED Free PDF] #DataScience Cheat Sheet covers concepts in Statistical Learning, #MachineLearning,… https://t.co/ozOh4vwwlP
2021-10-14
@SaudiAndroid
فريق من جامعة اكسفورد قام بتتبع نشاطات 12 الف تطبيق على iOS ووجدوا ان مافيه أي فرق يذكر عن اندرويد. التطبيقات على… https://t.co/w3g1OJTE4D
2021-10-10
@ylecun
Interesting thread. The science doesn't really support the headlines. https://t.co/QLm77iVEH7
2021-10-16
@omarsar0
Federated learning is a big topic for machine learning practitioners because of the challenges we face with modelin… https://t.co/lgZd2ZTajY
2021-10-11
@nvidia
Researchers at @uni_copenhagen train an “exaggeration detection system” using NVIDIA GPUs and #deeplearning to iden… https://t.co/etHIM4Ozfa
2021-10-13
@SpirosMargaris
Creepy New #Drone #Leo That #Walks and #Flies Is a Robopocalypse Nightmare Come True https://t.co/bI6eaz8xux… https://t.co/IEXBAvP4am
2021-10-08
@NandoDF
A thread on the history of convolutional neural nets, neocognitrons, and back-propagation. Both Fukushima and… https://t.co/RLyboE1NYZ
2021-10-16
@ylecun
The latter. Obviously. https://t.co/J21RShPi9J
2021-10-14
@omzn
2021年にもなって単純なソートアルゴリズムが発見されただと…？ https://t.co/SKzTJLyrsI
2021-10-09
@SpirosMargaris
Please join @psb_dc & @KevinLevitt and me on Nov 11 at 8 AM PST #AI in #Fintech: With Great Power comes Great Resp… https://t.co/oMyXHHpTKS
2021-10-07
@hsss_sa
تدعي ورقة بحثية جديدة أن الأرض قد تكون محاطة بنفق مغناطيسي عملاق . https://t.co/I3Ah2Ocyhn https://t.co/vneGJ3547m
2021-10-15
@ylecun
5. Hence almost all modern ML problems are in the *extrapolation* regime. 6. Qualitative claims such as "ML works O… https://t.co/2KVlEFZPfW
2021-10-19
@KirkDBorne
The Ultimate Guide To #PyTorch: https://t.co/0QxM8nyKtE ————— #BigData #DataScience #AI #DeepLearning… https://t.co/Xj6OBuMXxN
2021-10-18
@ylecun
@rao2z The reason Fukushima didn't use backprop is not that he was interested in biological plausibility (although… https://t.co/2Ad6oyGQIi
2021-10-15
@omarsar0
🔥 Data Augmentation Approaches in NLP 🔥 Data augmentation is useful in machine learning as there is a need for inc… https://t.co/7a7ql9tmYU
2021-10-06
@KirkDBorne
*Online* eBook [open access] — #MachineLearning from Scratch: https://t.co/u4GumM3qNZ via @DataScienceCtrl —————… https://t.co/PSZAetS8Io
2021-10-19
@johnschulman2
reinforcement learning people: our recent paper might change your understanding of methods like PPO, as well as pro… https://t.co/K5h8TmtNES
2021-10-09
@APSphysics
To celebrate 30 years of @arxiv APS has increased its contribution to become the first Gold Affiliate society. We… https://t.co/hganbDRgLc
2021-10-15
@ylecun
Aishwarya Kamath and our work on MDETR is on the front page of today's ICCV Daily! - MDETR Paper:… https://t.co/y1p6JbCQzr
2021-10-12
@SpirosMargaris
5 Ways #MachineLearning Is #Revolutionizing #DigitalMarketing https://t.co/HO4rjWn8cI #fintech #AI… https://t.co/lu38uihcuf
2021-10-18
@KirkDBorne
Brilliant book by Kevin P. Murphy! Probabilistic #MachineLearning (2nd Ed, 2022, PDF) is here:… https://t.co/5Pgk3Qqcu4
2021-10-14
@SpirosMargaris
Why #Improvisation Is the #Future in an #AI-Dominated World https://t.co/AlHVzYaUMZ #fintech #futureofwork… https://t.co/zF7gm5AF1x
2021-10-06
@Sydonahi
Holy Moly! My Handbook to scientific writing has been CITED IN AN EDUCATION PAPER! 😍😱 https://t.co/HJ4YZ6u5xG This… https://t.co/xYx75ki5W6
2021-10-13
@KirkDBorne
Download Free eBook (47-page PDF) — The #Mathematics needed in preparation for an introductory class in… https://t.co/652d6jdgPK
2021-10-19
@KirkDBorne
From #Jupyter Notebook to Deployment — A Straightforward Example: https://t.co/x0RReOYwET ————— #BigData… https://t.co/Q1BB7RrcSi
2021-10-18
@ylecun
Welcome Ravid! https://t.co/jdQIc72xBd
2021-10-08
@ESC_Journals
ECG-AI: electrocardiographic #ArtificialIntelligence model for prediction of heart failure https://t.co/ePYUF6fS5y… https://t.co/saG73XDZ6a
2021-10-15
@mark_riedl
Explainable AI (XAI) systems can inadvertently deploy explanations that cause negative effects such as over-trust 🚨… https://t.co/hDn4HyEyhB
2021-10-07
@ylecun
@rao2z He told me that our 1989 Neural Comp paper on ConvNets shocked him because he was working on training the Ne… https://t.co/W1NDkba2Pc
2021-10-15
@AkiraTOSEI
https://t.co/pR8XYeIBoj ViTを自己教師あり学習させた研究。蒸留のような機構で自己教師あり学習を行うDINOを提案し、複数のクロップされた画像で分布が一致するように学習させる。DINOで学習させたViTは意… https://t.co/hbs7k0QNSx
2021-10-09
@NandoDF
Great to see investment in Africa. https://t.co/GG9SuHC2xS
2021-10-07
@KirkDBorne
#AI for #PrecisionMedicine and better #Healthcare: https://t.co/yVbxF5EzsV ———————— #BigData #DataScience #AI4good… https://t.co/ErHMDSX4jb
2021-10-06
@ylecun
Most influential people on Twitter within the ICCV2021 community. Interesting methodology. https://t.co/jwGHF6Yfn3
2021-10-18
@NandoDF
If you’re advertising a machine learning or AI scholarship or job on Twitter, please consider announcing it to… https://t.co/V5oeOgoW36
2021-10-20
@grethlen
こんな安直なアルゴリズムで昇順になるのか。。知らなかった。。 https://t.co/kc12hhoGxY https://t.co/eRqiXP8Dmb
2021-10-09
@jo_brandstetter
Are you interested in graph structured data? Do you want to include geometry and physics to boost your GNNs? Check… https://t.co/zyyRYzGWyd
2021-10-07
@gabrielpeyre
In "Smooth Bilevel Programming for Sparse Regularization", we show how a simple re-writing of Lasso-type problems l… https://t.co/sFWQEN5xFg
2021-10-07
@tjowens
“Automatic Metadata Extraction Incorporating Visual Features from Scanned Electronic Theses and Dissertations”… https://t.co/TeLAH15ZHb
2021-10-18
@svlevine
Can walking robots be made robust enough to finetune with RL directly in the real world? In "Legged Robots that Kee… https://t.co/aRXE3L7HHn
2021-10-12
@WKahneman
At Apex, @joelKatz mentioned AMM implementation for the XRPL DEX. This paper, released on 10/5, systematizes "the k… https://t.co/OANTUZvYve
2021-10-11
@wgilpin0
Is chaos actually hard to predict? For NeurIPS this year I made a database of 131 known strange attractors, and tra… https://t.co/wR1x15PGeZ
2021-10-12
@hillbig
SEGNNはGNNが頂点や枝の属性に従来のようにスカラーだけでなく速度やスピンなどベクトルやテンソルを扱っても並進、回転、反射操作に同変となるよう、線形変換はクレブシュ-ゴルダンテンソル積で表し、同変な活性化関数を使う。属性は球面… https://t.co/rI3D1lVruB
2021-10-10
@KirkDBorne
Artificial Intelligence with #Python — a complete guide to building intelligent apps: https://t.co/ZQcEnw8NV4… https://t.co/KZDOBnUKbI
2021-10-09

Hot Papers

ADOP: Approximate Differentiable One-Pixel Point Rendering
Darius Rückert, Linus Franke, Marc Stamminger
2021-10-13 Super Hot
Delphi: Towards Machine Ethics and Norms
Liwei Jiang, Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Maxwell Forbes, Jon Borchardt, Jenny Liang, Oren Etzioni, Maarten Sap, Yejin Choi
2021-10-14 Super Hot
Multitask Prompted Training Enables Zero-Shot Task Generalization
Victor Sanh, Albert Webson, Colin Raffel, Stephen H. Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Teven Le Scao, Arun Raja, Manan Dey, M Saiful Bari, Canwen Xu, Urmish Thakker, Shanya Sharma Sharma, Eliza Szczechla, Taewoon Kim, Gunjan Chhablani, Nihal Nayak, Debajyoti Datta, Jonathan Chang, Mike Tian-Jian Jiang, Han Wang, Matteo Manica, Sheng Shen, Zheng Xin Yong, Harshit Pandey, Rachel Bawden, Thomas Wang, Trishala Neeraj, Jos Rozen, Abheesht Sharma, Andrea Santilli, Thibault Fevry, Jason Alan Fries, Ryan Teehan, Stella Biderman, Leo Gao, Tali Bers, Thomas Wolf, Alexander M. Rush
2021-10-15 Super Hot
Nonnegative spatial factorization
F. William Townes, Barbara E. Engelhardt
2021-10-12 Super Hot
Vectorization of Raster Manga by Deep Reinforcement Learning
Hao Su, Jianwei Niu, Xuefeng Liu, Jiahe Cui, Ji Wan
2021-10-10 Super Hot
Meta Internal Learning
Raphael Bensadoun, Shir Gur, Tomer Galanti, Lior Wolf
2021-10-06 Super Hot
Learning in High Dimension Always Amounts to Extrapolation
Randall Balestriero, Jerome Pesenti, Yann LeCun
2021-10-18 Super Hot
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
Yifu Zhang, Peize Sun, Yi Jiang, Dongdong Yu, Zehuan Yuan, Ping Luo, Wenyu Liu, Xinggang Wang
2021-10-13 Super Hot
3D Infomax improves GNNs for Molecular Property Prediction
Hannes Stärk, Dominique Beaini, Gabriele Corso, Prudencio Tossou, Christian Dallago, Stephan Günnemann, Pietro Liò
2021-10-08 Hot
Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling
Gianluigi Silvestri, Emily Fertig, Dave Moore, Luca Ambrogioni
2021-10-12 Hot
How to train RNNs on chaotic data?
Zahra Monfared, Jonas M. Mikhaeil, Daniel Durstewitz
2021-10-14 Hot
Non-deep Networks
Ankit Goyal, Alexey Bochkovskiy, Jia Deng, Vladlen Koltun
2021-10-14 Hot
ViDT: An Efficient and Effective Fully Transformer-based Object Detector
Hwanjun Song, Deqing Sun, Sanghyuk Chun, Varun Jampani, Dongyoon Han, Byeongho Heo, Wonjae Kim, Ming-Hsuan Yang
2021-10-08 Hot
Predictive models of RNA degradation through dual crowdsourcing
Hannah K. Wayment-Steele, Wipapat Kladwang, Andrew M. Watkins, Do Soon Kim, Bojan Tunguz, Walter Reade, Maggie Temkin, Jonathan Romano, Roger Wellington-Oguri, John J. Nicol, Jiayang Gao, Kazuki Onodera, Kazuki Fujikawa, Hanfei Mao, Gilles Vandewiele, Michele Tinti, Bram Steenwinckel, Takuya Ito, Taiga Noumi, Shujun He, Keiichiro Ishi, Youhan Lee, Fatih Öztürk, Anthony Chiu, Emin Öztürk, Karim Amer, Mohamed Fares, Eterna Participants, Rhiju Das
2021-10-14 Hot
KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE using Mel-spectrograms
Chien-Feng Liao, Jen-Yu Liu, Yi-Hsuan Yang
2021-10-08 Hot
Evaluating Predictive Distributions: Does Bayesian Deep Learning Work?
Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Botao Hao, Morteza Ibrahimi, Dieterich Lawson, Xiuyuan Lu, Brendan O'Donoghue, Benjamin Van Roy
2021-10-09 Hot
Collaging Class-specific GANs for Semantic Image Synthesis
Yuheng Li, Yijun Li, Jingwan Lu, Eli Shechtman, Yong Jae Lee, Krishna Kumar Singh
2021-10-08 Hot
Toward a Visual Concept Vocabulary for GAN Latent Space
Sarah Schwettmann, Evan Hernandez, David Bau, Samuel Klein, Jacob Andreas, Antonio Torralba
2021-10-08 Hot
ATISS: Autoregressive Transformers for Indoor Scene Synthesis
Despoina Paschalidou, Amlan Kar, Maria Shugrina, Karsten Kreis, Andreas Geiger, Sanja Fidler
2021-10-07 Hot
Symbolic Knowledge Distillation: from General Language Models to Commonsense Models
Peter West, Chandra Bhagavatula, Jack Hessel, Jena D. Hwang, Liwei Jiang, Ronan Le Bras, Ximing Lu, Sean Welleck, Yejin Choi
2021-10-14 Hot
Sparse MoEs meet Efficient Ensembles
James Urquhart Allingham, Florian Wenzel, Zelda E Mariet, Basil Mustafa, Joan Puigcerver, Neil Houlsby, Ghassen Jerfel, Vincent Fortuin, Balaji Lakshminarayanan, Jasper Snoek, Dustin Tran, Carlos Riquelme Ruiz, Rodolphe Jenatton
2021-10-07 Hot
Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning
Vibashan VS, Domenick Poster, Suya You, Shuowen Hu, Vishal M. Patel
2021-10-07 Hot
Understanding Dimensional Collapse in Contrastive Self-supervised Learning
Li Jing, Pascal Vincent, Yann LeCun, Yuandong Tian
2021-10-18 Hot
Hyperparameter Tuning with Renyi Differential Privacy
Nicolas Papernot, Thomas Steinke
2021-10-07 Hot
Causal ImageNet: How to discover spurious features in Deep Learning?
Sahil Singla, Soheil Feizi
2021-10-08 Hot
Creating User Interface Mock-ups from High-Level Text Descriptions with Deep-Learning Models
Forrest Huang, Gang Li, Xin Zhou, John F. Canny, Yang Li
2021-10-14 Hot
Leveraging Automated Unit Tests for Unsupervised Code Translation
Baptiste Roziere, Jie M. Zhang, Francois Charton, Mark Harman, Gabriel Synnaeve, Guillaume Lample
2021-10-13 Hot
Graph Neural Networks with Learnable Structural and Positional Representations
Vijay Prakash Dwivedi, Anh Tuan Luu, Thomas Laurent, Yoshua Bengio, Xavier Bresson
2021-10-15 Hot
Ego4D: Around the World in 3,000 Hours of Egocentric Video
Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, Miguel Martin, Tushar Nagarajan, Ilija Radosavovic, Santhosh Kumar Ramakrishnan, Fiona Ryan, Jayant Sharma, Michael Wray, Mengmeng Xu, Eric Zhongcong Xu, Chen Zhao, Siddhant Bansal, Dhruv Batra, Vincent Cartillier, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Christian Fuegen, Abrham Gebreselasie, Cristina Gonzalez, James Hillis, Xuhua Huang, Yifei Huang, Wenqi Jia, Weslie Khoo, Jachym Kolar, Satwik Kottur, Anurag Kumar, Federico Landini, Chao Li, Yanghao Li, Zhenqiang Li, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Rui
2021-10-13 Hot
Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations
Jiayao Zhang, Hua Wang, Weijie J. Su
2021-10-11 Hot

Fresh Papers

Continuous Control with Action Quantization from Demonstrations
Robert Dadashi, Léonard Hussenot, Damien Vincent, Sertan Girgin, Anton Raichuk, Matthieu Geist, Olivier Pietquin
2021-10-19 Hot
Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization
Timo M. Deist, Monika Grewal, Frank J. W. M. Dankers, Tanja Alderliesten, Peter A. N. Bosman
2021-10-19
Activation Landscapes as a Topological Summary of Neural Network Performance
Matthew Wheeler, Jose Bouza, Peter Bubenik
2021-10-19
Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes
Chonghua Liao, Jiafan He, Quanquan Gu
2021-10-19
FriendlyCore: Practical Differentially Private Aggregation
Eliad Tsfadia, Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer
2021-10-19
Robust Event Classification Using Imperfect Real-world PMU Data
Yunchuan Liu, Lei Yang, Amir Ghasemkhani, Hanif Livani, Virgilio A. Centeno, Pin-Yu Chen, Junshan Zhang
2021-10-19
Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs
Naman Agarwal, Syomantak Chaudhuri, Prateek Jain, Dheeraj Nagaraj, Praneeth Netrapalli
2021-10-19
Dual-CyCon Net: A Cycle Consistent Dual-Domain Convolutional Neural Network Framework for Detection of Partial Discharge
Mohammad Zunaed, Ankur Nath, Md. Saifur Rahman
2021-10-19
Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods with Entropy Regularization
Yuhao Ding, Junzi Zhang, Javad Lavaei
2021-10-19
On the Global Convergence of Momentum-based Policy Gradient
Yuhao Ding, Junzi Zhang, Javad Lavaei
2021-10-19
VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer
Zineng Tang, Jaemin Cho, Hao Tan, Mohit Bansal
2021-10-19
Broaden Your Views for Self-Supervised Video Learning
Adrià Recasens, Pauline Luc, Jean-Baptiste Alayrac, Luyu Wang, Ross Hemsley, Florian Strub, Corentin Tallec, Mateusz Malinowski, Viorica Patraucean, Florent Altché, Michal Valko, Jean-Bastien Grill, Aäron van den Oord, Andrew Zisserman
2021-10-19
Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound
Valentina Zantedeschi, Paul Viallard, Emilie Morvant, Rémi Emonet, Amaury Habrard, Pascal Germain, Benjamin Guedj
2021-10-19
Multiscale Simulations of Complex Systems by Learning their Effective Dynamics
Pantelis R. Vlachas, Georgios Arampatzis, Caroline Uhler, Petros Koumoutsakos
2021-10-19
TESSERACT: Gradient Flip Score to Secure Federated Learning Against Model Poisoning Attacks
Atul Sharma, Wei Chen, Joshua Zhao, Qiang Qiu, Somali Chaterji, Saurabh Bagchi
2021-10-19
Continual self-training with bootstrapped remixing for speech enhancement
Efthymios Tzinis, Yossi Adi, Vamsi K. Ithapu, Buye Xu, Anurag Kumar
2021-10-19
Alleviating Noisy-label Effects in Image Classification via Probability Transition Matrix
Ziqi Zhang, Yuexiang Li, Hongxin Wei, Kai Ma, Tao Xu, Yefeng Zheng
2021-10-19
Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition
Mirco Planamente, Chiara Plizzari, Emanuele Alberti, Barbara Caputo
2021-10-19
On-board Fault Diagnosis of a Laboratory Mini SR-30 Gas Turbine Engine
Richa Singh
2021-10-19
Stochastic Primal-Dual Deep Unrolling Networks for Imaging Inverse Problems
Junqi Tang
2021-10-19
LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation
Mohammad Abuzar Shaikh, Zhanghexuan Ji, Dana Moukheiber, Yan Shen, Sargur Srihari, Mingchen Gao
2021-10-19
Inductive Biases and Variable Creation in Self-Attention Mechanisms
Benjamin L. Edelman, Surbhi Goel, Sham Kakade, Cyril Zhang
2021-10-19
Some of Entity Resolution
Olivier Binette, Rebecca C. Steorts
2021-10-19
Contrastive Active Inference
Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt
2021-10-19
Nonparametric Sparse Tensor Factorization with Hierarchical Gamma Processes
Conor Tillinghast, Zheng Wang, Shandian Zhe
2021-10-19
ZeroWaste Dataset: Towards Deformable Object Segmentation in Extreme Clutter
Dina Bashkirova, Mohamed Abdelfattah, Ziliang Zhu, James Akl, Fadi Alladkani, Ping Hu, Vitaly Ablavsky, Berk Calli, Sarah Adel Bargal, Kate Saenko
2021-10-19
Stateful Offline Contextual Policy Evaluation and Learning
Nathan Kallus, Angela Zhou
2021-10-19
Large-Scale Learning with Fourier Features and Tensor Decompositions
Frederiek Wesel, Kim Batselier
2021-10-19
Improving the Accuracy-Memory Trade-Off of Random Forests Via Leaf-Refinement
Sebastian Buschjäger, Katharina Morik
2021-10-19
A realistic approach to generate masked faces applied on two novel masked face recognition data sets
Tudor Mare, Georgian Duta, Mariana-Iuliana Georgescu, Adrian Sandru, Bogdan Alexe, Marius Popescu, Radu Tudor Ionescu
2021-10-19

reinforcement learning

Where Did You Learn That From? Surprising Effectiveness of Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning
Maziar Gomrokchi, Susan Amin, Hossein Aboutalebi, Alexander Wong, Doina Precup
2021-10-12
REIN-2: Giving Birth to Prepared Reinforcement Learning Agents Using Reinforcement Learning Agents
Aristotelis Lazaridis, Ioannis Vlahavas
2021-10-11
Reinforcement Learning for Systematic FX Trading
Gabriel Borrageiro, Nick Firoozye, Paolo Barucca
2021-10-10 Hot
Reinforcement Learning for Systematic FX Trading
Gabriel Borrageiro, Nick Firoozye, Paolo Barucca
2021-10-15
Offline Reinforcement Learning with Implicit Q-Learning
Ilya Kostrikov, Ashvin Nair, Sergey Levine
2021-10-12
Attaining Interpretability in Reinforcement Learning via Hierarchical Primitive Composition
Jeong-Hoon Lee, Jongeun Choi
2021-10-15
Specifying and Interpreting Reinforcement Learning Policies through Simulatable Machine Learning
Pradyumna Tambwekar, Andrew Silva, Nakul Gopalan, Matthew Gombolay
2021-10-13
Dynamic Sparse Training for Deep Reinforcement Learning
Ghada Sokar, Elena Mocanu, Decebal Constantin Mocanu, Mykola Pechenizkiy, Peter Stone
2021-10-11
Wasserstein Unsupervised Reinforcement Learning
Shuncheng He, Yuhang Jiang, Hongchang Zhang, Jianzhun Shao, Xiangyang Ji
2021-10-15
Bad-Policy Density: A Measure of Reinforcement Learning Hardness
David Abel, Cameron Allen, Dilip Arumugam, D. Ellis Hershkowitz, Michael L. Littman, Lawson L. S. Wong
2021-10-07
Containerized Distributed Value-Based Multi-Agent Reinforcement Learning
Siyang Wu, Tonghan Wang, Chenghao Li, Chongjie Zhang
2021-10-15
State-based Episodic Memory for Multi-Agent Reinforcement Learning
Xiao Ma, Wu-Jun Li
2021-10-19
Improved Exploring Starts by Kernel Density Estimation-Based State-Space Coverage Acceleration in Reinforcement Learning
Maximilian Schenke, Oliver Wallscheid
2021-10-19
On the Sample Complexity of Actor-Critic Method for Reinforcement Learning with Function Approximation
Harshat Kumar, Alec Koppel, Alejandro Ribeiro
2021-10-07
A Broad-persistent Advising Approach for Deep Interactive Reinforcement Learning in Robotic Environments
Hung Son Nguyen, Francisco Cruz, Richard Dazeley
2021-10-15
Improving reinforcement learning algorithms: towards optimal learning rate policies
Othmane Mounjid, Charles-Albert Lehalle
2021-10-17
Reinforcement Learning in Reward-Mixing MDPs
Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor
2021-10-07 Hot
HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism
Zhiwei Xu, Yunpeng Bai, Bin Zhang, Dapeng Li, Guoliang Fan
2021-10-14
An Augmented Reality Platform for Introducing Reinforcement Learning to K-12 Students with Robots
Ziyi Zhang, Samuel Micah Akai-Nettey, Adonai Addo, Chris Rogers, Jivko Sinapov
2021-10-10
Reinforcement Learning for Ridesharing: A Survey
Zhiwei Qin, Hongtu Zhu, Jieping Ye
2021-10-15
On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning
Marc Aurel Vischer, Robert Tjarko Lange, Henning Sprekeler
2021-10-19
Effects of Different Optimization Formulations in Evolutionary Reinforcement Learning on Diverse Behavior Generation
Victor Villin, Naoki Masuyama, Yusuke Nojima
2021-10-15
Autonomous Racing using a Hybrid Imitation-Reinforcement Learning Architecture
Chinmay Vilas Samak, Tanmay Vilas Samak, Sivanathan Kandhasamy
2021-10-11
Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning
Trevor McInroe, Lukas Schäfer, Stefano V. Albrecht
2021-10-11
Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss
Shuang Qiu, Xiaohan Wei, Zhuoran Yang, Jieping Ye, Zhaoran Wang
2021-10-18
Learning a subspace of policies for online adaptation in Reinforcement Learning
Jean-Baptiste Gaya, Laure Soulier, Ludovic Denoyer
2021-10-11
Constraints Penalized Q-Learning for Safe Offline Reinforcement Learning
Haoran Xu, Xianyuan Zhan, Xiangyu Zhu
2021-10-14
CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning
Carolin Benjamins, Theresa Eimer, Frederik Schubert, André Biedenkapp, Bodo Rosenhahn, Frank Hutter, Marius Lindauer
2021-10-11
Identifiability in inverse reinforcement learning
Haoyang Cao, Samuel N. Cohen, Lukasz Szpruch
2021-10-06
Revisiting Design Choices in Model-Based Offline Reinforcement Learning
Cong Lu, Philip J. Ball, Jack Parker-Holder, Michael A. Osborne, Stephen J. Roberts
2021-10-08

language

OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages
Prem Selvaraj, Gokul NC, Pratyush Kumar, Mitesh Khapra
2021-10-12
Cross-Lingual Fine-Grained Entity Typing
Nila Selvaraj, Yasumasa Onoe, Greg Durrett
2021-10-15
Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters
Asa Cooper Stickland, Alexandre Bérard, Vassilina Nikoulina
2021-10-18
IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation
Samuel Cahyawijaya, Genta Indra Winata, Bryan Wilie, Karissa Vincentio, Xiaohong Li, Adhiguna Kuncoro, Sebastian Ruder, Zhi Yuan Lim, Syafri Bahar, Masayu Leylia Khodra, Ayu Purwarianti, Pascale Fung
2021-10-09
Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translation
Zhong Zhou, Alex Waibel
2021-10-16
BAS: An Answer Selection Method Using BERT Language Model
Jamshid Mozafari, Afsaneh Fatemi, Mohammad Ali Nematbakhsh
2021-10-14
MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators
Zhixing Tan, Xiangwen Zhang, Shuo Wang, Yang Liu
2021-10-13 Hot
Alternative Input Signals Ease Transfer in Multilingual Machine Translation
Simeng Sun, Angela Fan, James Cross, Vishrav Chaudhary, Chau Tran, Philipp Koehn, Francisco Guzman
2021-10-15
Multilingual Neural Machine Translation:Can Linguistic Hierarchies Help?
Fahimeh Saleh, Wray Buntine, Gholamreza Haffari, Lan Du
2021-10-15
Systematic Inequalities in Language Technology Performance across the World's Languages
Damián Blasi, Antonios Anastasopoulos, Graham Neubig
2021-10-13
Modulating Bottom-Up and Top-Down Visual Processing via Language-Conditional Filters
İlker Kesen, Ozan Arkan Can, Erkut Erdem, Aykut Erdem, Deniz Yuret
2021-10-18
Factorized Neural Transducer for Efficient Language Model Adaptation
Xie Chen, Zhong Meng, Sarangarajan Parthasarathy, Jinyu Li
2021-10-07
Multilingual unsupervised sequence segmentation transfers to extremely low-resource languages
C. M. Downey, Shannon Drizin, Levon Haroutunian, Shivin Thukral
2021-10-16
Improved Language Identification Through Cross-Lingual Self-Supervised Learning
Andros Tjandra, Diptanu Gon Choudhury, Frank Zhang, Kritika Singh, Alexis Conneau, Alexei Baevski, Assaf Sela, Yatharth Saraf, Michael Auli
2021-10-18
Generalizing to New Domains by Mapping Natural Language to Lifted LTL
Eric Hsiung, Hiloni Mehta, Junchi Chu, Xinyu Liu, Roma Patel, Stefanie Tellex, George Konidaris
2021-10-11
Factorized Neural Transducer for Efficient Language Model Adaptation
Xie Chen, Zhong Meng, Sarangarajan Parthasarathy, Jinyu Li
2021-10-06
LaoPLM: Pre-trained Language Models for Lao
Nankai Lin, Yingwen Fu, Chuwei Chen, Ziyu Yang, Shengyi Jiang
2021-10-13
LaoPLM: Pre-trained Language Models for Lao
Nankai Lin, Yingwen Fu, Ziyu Yang, Shengyi Jiang
2021-10-12
VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer
Zineng Tang, Jaemin Cho, Hao Tan, Mohit Bansal
2021-10-19
Factorized Neural Transducer for Efficient Language Model Adaptation
Xie Chen, Zhong Meng, Sarangarajan Parthasarathy, Jinyu Li
2021-10-18
LaoPLM: Pre-trained Language Models for Lao
Nankai Lin, Yingwen Fu, Chuwei Chen, Ziyu Yang, Shengyi Jiang
2021-10-14
Socially Aware Bias Measurements for Hindi Language Representations
Vijit Malik, Sunipa Dev, Akihiro Nishi, Nanyun Peng, Kai-Wei Chang
2021-10-15
Towards Language-guided Visual Recognition via Dynamic Convolutions
Gen Luo, Yiyi Zhou, Xiaoshuai Sun, Xinghao Ding, Yongjian Wu, Feiyue Huang, Yue Gao, Rongrong Ji
2021-10-17
Natural Language-Guided Programming
Geert Heyman, Rafael Huysegems, Pascal Justen, Tom Van Cutsem
2021-10-07
Interactive Hierarchical Guidance using Language
Bharat Prakash, Nicholas Waytowich, Tim Oates, Tinoosh Mohsenin
2021-10-09
Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners
Ningyu Zhang, Luoqiu Li, Xiang Chen, Shumin Deng, Zhen Bi, Chuanqi Tan, Fei Huang, Huajun Chen
2021-10-06
Few-shot Controllable Style Transfer for Low-Resource Settings: A Study in Indian Languages
Kalpesh Krishna, Deepak Nathani, Xavier Garcia, Bidisha Samanta, Partha Talukdar
2021-10-14
Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing
Minh Van Nguyen, Viet Dac Lai, Amir Pouran Ben Veyseh, Thien Huu Nguyen
2021-10-15
Machine Translation into Low-resource Language Varieties
Sachin Kumar, Antonios Anastasopoulos, Shuly Wintner, Yulia Tsvetkov
2021-10-15
Dict-BERT: Enhancing Language Model Pre-training with Dictionary
Wenhao Yu, Chenguang Zhu, Yuwei Fang, Donghan Yu, Shuohang Wang, Yichong Xu, Michael Zeng, Meng Jiang
2021-10-13 Hot