Week Ending 1.24.2021
RESEARCH WATCH: 1.24.2021
Over the past week, 974 new papers were published in "Computer Science".
The paper discussed most in the news over the past week was by a team at Ben-Gurion University of the Negev: "AIR-FI: Generating Covert Wi-Fi Signals from Air-Gapped Computers" by Mordechai Guri (Dec 2020), which was referenced 20 times, including in the article Secure Bitcoin self-custody: Balancing safety and ease of use in COINTELEGRAPH.COM. The paper author, Mordechai Guri (Ben-Gurion University of the Negev), was quoted saying "AIR-FI: Generating Covert Wi-Fi Signals from Air-Gapped Computers". The paper got social media traction with 614 shares. The authors show that attackers can exfiltrate data from air - gapped computers via Wi - Fi signals. A Twitter user, @SimonZerafa, commented "This Week in Exfil. Using DDR SDRAM buses to generate electromagnetic emissions in the 2.4 GHz Wi-Fi range ->", while @SimonZerafa posted "This Week in Exfil. Using DDR SDRAM buses to generate electromagnetic emissions in the 2.4 GHz Wi-Fi range ->".
Leading researcher Ruslan Salakhutdinov (Carnegie Mellon University) published "Understanding the Tradeoffs in Client-Side Privacy for Speech Recognition".
The paper shared the most on social media this week is by a team at Cornell: "VoterFraud2020: a Multi-modal Dataset of Election Fraud Claims on Twitter" by Anton Abilov et al (Jan 2021) with 13758 shares. @conrad1058 (Conrad Sieber) tweeted "Wow you're in this Tech Report on disinformation shared on twitter p. 10 And gas in CA averaging $3.36/gallon".
This week was active for "Computer Science - Artificial Intelligence", with 124 new papers.
The paper discussed most in the news over the past week was by a team at Google: "Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity" by William Fedus et al (Jan 2021), which was referenced 10 times, including in the article Google Switch Transformers: Scaling to Trillion Parameter Models with constant computational costs in Towards Data Science. The paper also got the most social media traction with 747 shares. A user, @LiamFedus, tweeted "Pleased to share new work! We design a sparse language model that scales beyond a trillion parameters. These versions are significantly more sample efficient and obtain up to 4-7x speed-ups over popular models like T5-Base, T5-Large, T5-XXL. Preprint".
The paper shared the most on social media this week is by a team at University of Toronto: "Noisy intermediate-scale quantum (NISQ) algorithms" by Kishor Bharti et al (Jan 2021) with 169 shares. @Ion_busters (Ion busters) tweeted "Fantastic summary of #NISQ algorithms from #machinelearning to nuclear physics! Even better it covers something that we should know more about - circuit compilation. We know what we're going to be reading over the weekend".
This week was active for "Computer Science - Computer Vision and Pattern Recognition", with 225 new papers.
The paper discussed most in the news over the past week was by a team at Sorbonne University: "Training data-efficient image transformers & distillation through attention" by Hugo Touvron et al (Dec 2020), which was referenced 5 times, including in the article Facebook DeIt: A promising new technique for image classification in Towards Data Science. The paper got social media traction with 296 shares. The researchers produce a competitive convolution - free transformer by training on Imagenet only. On Twitter, @omarsar0 said "DeiT - Transformer-based image classification model built for high performance and requiring less compute & data. Uses distillation through attention and achieves 84.2 top-1 accuracy on the ImageNet benchmark trained on a single 8-GPU server over 3 days".
Leading researcher Luc Van Gool (Computer Vision Laboratory) came out with "Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution" The researchers propose a trilevel neural architecture search (NAS) method for efficient single image super - resolution (SR).
The paper shared the most on social media this week is by a team at DeepMind: "Characterizing signal propagation to close the performance gap in unnormalized ResNets" by Andrew Brock et al (Jan 2021) with 219 shares. @sedielem (Sander Dieleman) tweeted "This work has the promise of freeing us from the technical debt that normalisation layers bring with them. I've often wondered if the gains from BatchNorm are offset by the myriad of bugs it has the potential to introduce 🤔 Now we can get competitive results without it!".
This week was active for "Computer Science - Computers and Society", with 32 new papers.
The paper discussed most in the news over the past week was "Setting the Record Straighter on Shadow Banning" by Erwan Le Merrer et al (Dec 2020), which was referenced 1 time, including in the article Exploring the underpinnings of shadowbanning on Twitter in Tech Xplore. The paper author, Erwan Le Merrer (Researchers), was quoted saying "Since at some point, Twitter claimed that they were not using shadowbanning methods (referring to problems being bugs), we decided to leverage statistical methods to test the likelihood of such bug scenario, which should be uniformly distributed across users and hence across our data". The paper was shared 4 times in social media. The authors be the first to address the plausibility or not of shadow banning on a major online platform, by adopting both a statistical and a graph topological approach. On Twitter, @Baaz29146264 observed "2/2 All this is shown with an extensive data collection of more than 2.5 million profiles".
This week was very active for "Computer Science - Human-Computer Interaction", with 44 new papers.
The paper discussed most in the news over the past week was by a team at Microsoft: "Evaluating the Robustness of Collaborative Agents" by Paul Knott et al (Jan 2021), which was referenced 2 times, including in the article What’s Cooking? After Poker and Go, Researchers Use New Game To Evaluate RL Agents’ Robustness in Analytics India Magazine. The paper got social media traction with 19 shares. A Twitter user, @gastronomy, commented "> In order for agents trained by deep reinforcement learning to work alongside humans in realistic settings, we will need to ensure that the agents are \emph{robus".
The paper shared the most on social media this week is by a team at Cornell: "VoterFraud2020: a Multi-modal Dataset of Election Fraud Claims on Twitter" by Anton Abilov et al (Jan 2021)
This week was very active for "Computer Science - Learning", with 319 new papers.
The paper discussed most in the news over the past week was by a team at Google: "Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity" by William Fedus et al (Jan 2021)
Leading researcher Luc Van Gool (Computer Vision Laboratory) published "Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution" The researchers propose a trilevel neural architecture search (NAS) method for efficient single image super - resolution (SR).
The paper shared the most on social media this week is by a team at DeepMind: "Characterizing signal propagation to close the performance gap in unnormalized ResNets" by Andrew Brock et al (Jan 2021)
Over the past week, 12 new papers were published in "Computer Science - Multiagent Systems".
The paper discussed most in the news over the past week was by a team at Microsoft: "Evaluating the Robustness of Collaborative Agents" by Paul Knott et al (Jan 2021)
Over the past week, 19 new papers were published in "Computer Science - Neural and Evolutionary Computing".
The paper shared the most on social media this week is "Can a Fruit Fly Learn Word Embeddings?" by Yuchen Liang et al (Jan 2021) with 131 shares. @hurrythas (Nikhil Harithas) tweeted "Imagine being a fruit fly, you got like two months to live and mfkrs tryna teach you how to read. Fruits and flying are more important 😤".
This week was active for "Computer Science - Robotics", with 49 new papers.
The paper discussed most in the news over the past week was by a team at University of Edinburgh: "Multi-expert learning of adaptive legged locomotion" by Chuanyu Yang et al (Dec 2020), which was referenced 1 time, including in the article Video Friday: Record-Breaking Drone Show Depicts Life of Van Gogh in Spectrum Online. The paper got social media traction with 7 shares. A Twitter user, @AIRoboticsLabEd, commented "A new step towards autonomous motor behaviours, inspired by back in 2015. Paper links: - Science Robotics: & Arxiv".