Week Ending 10.17.2021
RESEARCH WATCH: 10.17.2021
This week was active for "Computer Science", with 1,499 new papers.
The paper discussed most in the news over the past week was by a team at University of Oxford: "lambeq: An Efficient High-Level Python Library for Quantum NLP" by Dimitri Kartsaklis et al (Oct 2021), which was referenced 99 times, including in the article Cambridge Quantum toolkit converts natural language to quantum circuits in Embedded Systems Programming. The paper author, Kartsaklis, was quoted saying "There is a lot of interesting theoretical work on QNLP, but theory usually stands at some distance from practice".
Leading researcher Yoshua Bengio (Université de Montréal) published "Dynamic Inference with Neural Interpreters".
This week was extremely active for "Computer Science - Artificial Intelligence", with 252 new papers.
The paper discussed most in the news over the past week was by a team at University of Oxford: "lambeq: An Efficient High-Level Python Library for Quantum NLP" by Dimitri Kartsaklis et al (Oct 2021)
Leading researcher Ruslan Salakhutdinov (Carnegie Mellon University) published "ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers".
This week was very active for "Computer Science - Computer Vision and Pattern Recognition", with 325 new papers.
The paper discussed most in the news over the past week was by a team at University of Oxford: "PASS: An ImageNet replacement for self-supervised pretraining without humans" by Yuki M. Asano et al (Sep 2021), which was referenced 3 times, including in the article Overcoming ImageNet dataset biases with PASS. in Towards Data Science.
Leading researcher Yoshua Bengio (Université de Montréal) came out with "Dynamic Inference with Neural Interpreters".
This week was active for "Computer Science - Computers and Society", with 39 new papers.
The paper discussed most in the news over the past week was "Bugs in our Pockets: The Risks of Client-Side Scanning" by Hal Abelson et al (Oct 2021), which was referenced 18 times, including in the article Experts Slam Apple's Child Protection Phone-Scanning Technology in Forbes.com. The paper author, Ross Anderson (University of Cambridge), was quoted saying "If device vendors are compelled to install remote surveillance, the demands will start to roll in. Who could possibly be so cold-hearted as to argue against the system being extended to search for missing children?".
This week was active for "Computer Science - Human-Computer Interaction", with 32 new papers.
The paper discussed most in the news over the past week was "VIRUP : The Virtual Reality Universe Project" by Florian Cabot et al (Oct 2021), which was referenced 1 time, including in the article New VR software lets you explore the universe in Tech Explorist.
This week was extremely active for "Computer Science - Learning", with 552 new papers.
The paper discussed most in the news over the past week was by a team at DeepMind: "ETA Prediction with Graph Neural Networks in Google Maps" by Austin Derrow-Pinion et al (Aug 2021), which was referenced 6 times, including in the article DeepMind is developing one algorithm to rule them all in BusinessMayor.com.
Leading researcher Yoshua Bengio (Université de Montréal) published "Graph Neural Networks with Learnable Structural and Positional Representations".
This week was active for "Computer Science - Multiagent Systems", with 23 new papers.
Over the past week, 18 new papers were published in "Computer Science - Neural and Evolutionary Computing".
The paper discussed most in the news over the past week was by a team at Google: "Primer: Searching for Efficient Transformers for Language Modeling" by David R. So et al (Sep 2021), which was referenced 4 times, including in the article Best of arXiv.org for AI, Machine Learning, and Deep Learning – September 2021 in InsideBIGDATA.
This week was very active for "Computer Science - Robotics", with 81 new papers.
The paper discussed most in the news over the past week was "Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning" by Nikita Rudin et al (Sep 2021), which was referenced 2 times, including in the article Nvidia Develops Virtual Obstacle Course to Train 4,000 Robot Dogs to Walk in Minutes in Beebom.
Leading researcher Ruslan Salakhutdinov (Carnegie Mellon University) published "Recurrent Model-Free RL is a Strong Baseline for Many POMDPs".