Week Ending 7.4.2021
RESEARCH WATCH: 7.4.2021
This week was active for "Computer Science", with 1,226 new papers.
The paper discussed most in the news over the past week was "Empathy and Hope: Resource Transfer to Model Inter-country Social Media Dynamics" by Clay H. Yoo et al (Jun 2021), which was referenced 22 times, including in the article Pakistani Twitter supported Indians suffering in second COVID-19 wave: AI-based study in Geo Tv.
Leading researcher Yoshua Bengio (Université de Montréal) published "Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning".
This week was very active for "Computer Science - Artificial Intelligence", with 195 new papers.
The paper discussed most in the news over the past week was "A Survey of Transformers" by Tianyang Lin et al (Jun 2021), which was referenced 8 times, including in the article Best of Arxiv — Readings for July 2021 in Towards Data Science.
Leading researcher Yoshua Bengio (Université de Montréal) published "The Causal Neural Connection: Expressiveness, Learnability, and Inference".
This week was active for "Computer Science - Computer Vision and Pattern Recognition", with 302 new papers.
The paper discussed most in the news over the past week was by a team at Massachusetts Institute of Technology: "Efficient and Robust LiDAR-Based End-to-End Navigation" by Zhijian Liu et al (May 2021), which was referenced 7 times, including in the article MIT Researchers Develop Single Deep Neural Network For Autonomous Vehicles in Analytics India Magazine. The paper author, Alexander Amini (Massachusetts Institute of Technology), was quoted saying "We wanted to have a very flexible and modular AV system, and NVIDIA is the leader in this field".
Leading researcher Trevor Darrell (UC Berkeley) published "CLIP-It! Language-Guided Video Summarization".
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 "Empathy and Hope: Resource Transfer to Model Inter-country Social Media Dynamics" by Clay H. Yoo et al (Jun 2021)
This week was very active for "Computer Science - Human-Computer Interaction", with 41 new papers.
This week was very active for "Computer Science - Learning", with 426 new papers.
The paper discussed most in the news over the past week was by a team at Google: "Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better" by Gaurav Menghani (Jun 2021), which was referenced 21 times, including in the article How To Build Smaller, Faster, Better Deep Learning Models in Analytics India Magazine.
Leading researcher Yoshua Bengio (Université de Montréal) came out with "Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning".
Over the past week, 18 new papers were published in "Computer Science - Multiagent Systems".
Over the past week, 20 new papers were published in "Computer Science - Neural and Evolutionary Computing".
The paper discussed most in the news over the past week was "World-GAN: a Generative Model for Minecraft Worlds" by Maren Awiszus et al (Jun 2021), which was referenced 2 times, including in the article Leibniz University Hannover Proposes World-GAN: A 3D GAN for Minecraft Level Generation in SyncedReview.com.
Leading researcher Sergey Levine (University of California, Berkeley) came out with "Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment".
This week was very active for "Computer Science - Robotics", with 94 new papers.
The paper discussed most in the news over the past week was by a team at Massachusetts Institute of Technology: "Efficient and Robust LiDAR-Based End-to-End Navigation" by Zhijian Liu et al (May 2021)
Leading researcher Pieter Abbeel (University of California, Berkeley) published "Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble".