Week Ending 11.22.2020
RESEARCH WATCH: 11.22.2020
This week was active for "Computer Science", with 1,130 new papers.
The paper discussed most in the news over the past week was "How Did That Get In My Phone? Unwanted App Distribution on Android Devices" by Platon Kotzias et al (Oct 2020), which was referenced 17 times, including in the article 67% of Android malware comes through the Play Store in Techzim. The paper got social media traction with 5 shares. On Twitter, @vir2alexport said "A large part of monetization libraries are vulnerable and directly expose users’ information in «Man In The Middle» attacks. "between 10% and 24% of users devices encounter at least one unwanted app"".
Leading researcher Yoshua Bengio (Université de Montréal) came out with "Gradient Starvation: A Learning Proclivity in Neural Networks".
The paper shared the most on social media this week is by a team at University of Manchester: "Software must be recognised as an important output of scholarly research" by Caroline Jay et al (Nov 2020) with 191 shares. The investigators argue that as well as being important from a methodological perspective, software should, in many instances, be recognised as an output of research, equivalent to an academic paper. @toni___g (Toni G) tweeted "So true. It's also much less nonsense- and handwave- prone. Badly written software is self evident. Methods *are* the source: they may be more or less clear, but they must be there. If they are unclear or obfuscated, you can also draw conclusions".
The most influential Twitter user discussing papers is Sabine Hossenfelder who shared "Finite Quantum Gravity Amplitudes -- no strings attached" by Tom Draper et al (Jul 2020) and said: "The paper is here See page 4 bottom right for the remark about asg".
This week was very active for "Computer Science - Artificial Intelligence", with 161 new papers.
The paper discussed most in the news over the past week was by a team at New York University: "How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds" by Prithviraj Ammanabrolu et al (Oct 2020), which was referenced 5 times, including in the article To Teach an AI to Pursue Goals, Scientists Made It Play an RPG in Futurism. The paper author, Prithviraj Ammanabrolu (Georgia Institute of Technology), was quoted saying "Interactive narrative games are simulations in which an agent interacts with the world purely through natural language —-'perceiving,' 'acting upon' and 'talking to' the world using textual descriptions, commands and dialog". The paper got social media traction with 80 shares. On Twitter, @rajammanabrolu posted "🚨New Paper Alert🚨 Having trouble keeping your (AI) dragon motivated? Same here. So we figured out how to teach it, interactively w/ RL & lang pretraining, to act consistently + talk naturally wrt its motivations when questing in a fantasy text game. 1/4".
Leading researcher Ruslan Salakhutdinov (Carnegie Mellon University) published "C-Learning: Learning to Achieve Goals via Recursive Classification" @towards_AI tweeted "C-Learning learns goal-conditioned policies using classifiers, without any hand-designed rewards. The theoretical framework in C-Learning helps to explain connections between prediction and Q-functions, relabeling, and others. w/ Eysenbach".
The paper shared the most on social media this week is "FROST: Faster and more Robust One-shot Semi-supervised Training" by Helena E. Liu et al (Nov 2020) with 88 shares. The authors present a one - shot semi - supervised learning method that trains up to an order of magnitude faster and is more robust than state - of - the - art methods. @popular_ML (Popular ML resources) tweeted "The most popular ArXiv tweet in the last 24h".
The most influential Twitter user discussing papers is Sabine Hossenfelder who shared "Finite Quantum Gravity Amplitudes -- no strings attached" by Tom Draper et al (Jul 2020)
This week was active for "Computer Science - Computer Vision and Pattern Recognition", with 288 new papers.
The paper discussed most in the news over the past week was by a team at Karlsruhe Institute of Technology: "Super-Human Performance in Online Low-latency Recognition of Conversational Speech" by Thai-Son Nguyen et al (Oct 2020), which was referenced 10 times, including in the article Nope, Deep Learning is not enough in Medium.com. The paper got social media traction with 94 shares.
Leading researcher Dhruv Batra (Georgia Institute of Technology) published "Where Are You? Localization from Embodied Dialog".
The paper shared the most on social media this week is "FROST: Faster and more Robust One-shot Semi-supervised Training" by Helena E. Liu et al (Nov 2020)
The most influential Twitter user discussing papers is Sabine Hossenfelder who shared "Finite Quantum Gravity Amplitudes -- no strings attached" by Tom Draper et al (Jul 2020)
Over the past week, 27 new papers were published in "Computer Science - Computers and Society".
The paper discussed most in the news over the past week was "The De-democratization of AI: Deep Learning and the Compute Divide in Artificial Intelligence Research" by Nur Ahmed et al (Oct 2020), which was referenced 4 times, including in the article How Compute Divide Leads To Discrimination In AI Research in Analytics India Magazine. The paper got social media traction with 253 shares. A user, @hyounpark, tweeted "Great thread by on the need for bias awareness in AI research. The more we learn about #AI, the more we realize that it reifies status quo hierarchies without active governance", while @joftius posted "This paper is about a really important problem. One cause it mentions that I would emphasize more: the role of proprietary data. Most of the value of "AI" comes from the users and content moderators on massive platforms that generate/curate data".
The paper shared the most on social media this week is by a team at University of Manchester: "Software must be recognised as an important output of scholarly research" by Caroline Jay et al (Nov 2020)
The most influential Twitter user discussing papers is Sabine Hossenfelder who shared "Finite Quantum Gravity Amplitudes -- no strings attached" by Tom Draper et al (Jul 2020)
This week was active for "Computer Science - Human-Computer Interaction", with 35 new papers.
This week was very active for "Computer Science - Learning", with 398 new papers.
The paper discussed most in the news over the past week was by a team at California Institute of Technology: "Fourier Neural Operator for Parametric Partial Differential Equations" by Zongyi Li et al (Oct 2020), which was referenced 5 times, including in the article Keeping Up with Deep Learning - 19 Oct 2020 in Towards Data Science. The paper also got the most social media traction with 1658 shares. A Twitter user, @franciscojarceo, commented "This is awesome. I remember how amazed I was the first time I learned about #FourierTransforms. Seeming them applied to #DeepLearning and Partial Differential Equations is really exciting!!!", while @AnimaAnandkumar observed "Fourier neural operator for PDEs Solves family of #PDE from scratch at any resolution. Outperforms all existing #DeepLearning methods. 1000x faster than traditional solvers Experiments on Navier-Stokes equations #HPC".
Leading researcher Yoshua Bengio (Université de Montréal) published "Gradient Starvation: A Learning Proclivity in Neural Networks".
The paper shared the most on social media this week is "FROST: Faster and more Robust One-shot Semi-supervised Training" by Helena E. Liu et al (Nov 2020)
The most influential Twitter user discussing papers is Sabine Hossenfelder who shared "Finite Quantum Gravity Amplitudes -- no strings attached" by Tom Draper et al (Jul 2020)
Over the past week, 11 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 University College London: "SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving" by Ming Zhou et al (Oct 2020), which was referenced 2 times, including in the article Conference on Robot Learning (CoRL 2020) Underway, Best Paper Finalists Announced in SyncedReview.com. The paper got social media traction with 54 shares. On Twitter, @kargarisaac said "Lack of a fast simulator with diverse scenarios for multi-agent #RL was a huge obstacle for #AutonomousDriving research community. I tested several options but this new one, SMART, seems to be the best. It has also several state of the art #MARL algorithms implemented".
Over the past week, 28 new papers were published in "Computer Science - Neural and Evolutionary Computing".
This week was very active for "Computer Science - Robotics", with 108 new papers.
The paper discussed most in the news over the past week was by a team at Hong Kong University of Science and Technology: "Origami-based Shape Morphing Fingertip to Enhance Grasping Stability and Dexterity" by Zicheng Kan et al (Oct 2020), which was referenced 4 times, including in the article Video Friday: Matternet Launches Urban Drone Delivery in Berlin in Spectrum Online. The paper author, Yazhan Zhang (Hong Kong University of Science and Technology), was quoted saying "A Ph.D. student in our group, Mr. Song Haoran, also previously published a paper on contact surface clustering , showing three typical contact primitives for the representations of major local geometries".
Leading researcher Sergey Levine (University of California, Berkeley) came out with "Parrot: Data-Driven Behavioral Priors for Reinforcement Learning" @popular_ML tweeted "The most popular ArXiv tweet in the last 24h". This paper was also shared the most on social media with 46 tweets. @popular_ML (Popular ML resources) tweeted "The most popular ArXiv tweet in the last 24h".