Week Ending 3.8.2020
RESEARCH WATCH: 3.8.2020
Over the past week, 1,017 new papers were published in "Computer Science".
The paper discussed most in the news over the past week was by a team at Google: "Learning to Walk in the Real World with Minimal Human Effort" by Sehoon Ha et al (Feb 2020), which was referenced 36 times, including in the article Google scientists built an adorable four-legged robot called 'Rainbow Dash' that taught itself to walk without human help in Business Insider. The paper author, Jie Tan (Google), was quoted saying "Now is still the early days of research. Next, we plan to test our learning system on a wide range of robots and in a more diverse set of environments". Chelsea Finn (University of California, Berkeley), who is not part of the study, said "Removing the person from the process is really hard. By allowing robots to learn more autonomously, robots are closer to being able to learn in the real world that we live in, rather than in a lab."
Leading researcher Yoshua Bengio (Université de Montréal) published "Benchmarking Graph Neural Networks".
Over the past week, 85 new papers were published in "Computer Science - Artificial Intelligence".
The paper discussed most in the news over the past week was by a team at Google: "Learning to Walk in the Real World with Minimal Human Effort" by Sehoon Ha et al (Feb 2020)
Leading researcher Ruslan Salakhutdinov (Carnegie Mellon University) published "On Emergent Communication in Competitive Multi-Agent Teams".
This week was active for "Computer Science - Computer Vision and Pattern Recognition", with 212 new papers.
The paper discussed most in the news over the past week was by a team at Microsoft: "Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data" by Sebastian Lunz et al (Feb 2020), which was referenced 5 times, including in the article Microsoft’s AI generates 3D objects from 2D images in Venturebeat.
Leading researcher Jianfeng Gao (Microsoft) published "Multi-View Learning for Vision-and-Language Navigation".
Over the past week, 17 new papers were published in "Computer Science - Computers and Society".
This week was active for "Computer Science - Human-Computer Interaction", with 34 new papers.
Leading researcher Devi Parikh (Georgia Institute of Technology) published "Predicting A Creators Preferences In, and From, Interactive Generative Art".
This week was very active for "Computer Science - Learning", with 379 new papers.
The paper discussed most in the news over the past week was by a team at Google: "Learning to Walk in the Real World with Minimal Human Effort" by Sehoon Ha et al (Feb 2020)
Leading researcher Yoshua Bengio (Université de Montréal) came out with "Benchmarking Graph Neural Networks".
Over the past week, eight 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 DeepMind: "Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games" by Edward Hughes et al (Feb 2020), which was referenced 2 times, including in the article DeepMind technique encourages AI players to cooperate in zero-sum games in Venturebeat.
Leading researcher Ruslan Salakhutdinov (Carnegie Mellon University)
Over the past week, 28 new papers were published in "Computer Science - Neural and Evolutionary Computing".
Leading researcher Aaron Courville (Université de Montréal) came out with "Out-of-Distribution Generalization via Risk Extrapolation (REx)".
This week was extremely active for "Computer Science - Robotics", with 117 new papers.
The paper discussed most in the news over the past week was by a team at Google: "Learning to Walk in the Real World with Minimal Human Effort" by Sehoon Ha et al (Feb 2020)
Leading researcher Pieter Abbeel (University of California, Berkeley) came out with "Hierarchically Decoupled Imitation for Morphological Transfer".