Week Ending 11.8.2020
RESEARCH WATCH: 11.8.2020
This week was active for "Computer Science", with 1,178 new papers.
The paper discussed most in the news over the past week was "We Dont Speak the Same Language: Interpreting Polarization through Machine Translation" by Ashiqur R. KhudaBukhsh et al (Oct 2020), which was referenced 42 times, including in the article Study from CMU Illuminates the Divided US Political Lexicon in MultiLingual.com. The paper author, Mark S. Kamlet (University Professor of Economics and Public Policy), was quoted saying "Some of these so-called misaligned pairs seem pretty obvious". The paper got social media traction with 20 shares. On Twitter, @hrksrkr said "Research suggests that polarization in the political sphere has become so extreme that supporters literally express the same sentiments in different languages. One of the lead authors is my brother who just completed his bachelor's CS".
Leading researcher Kyunghyun Cho (New York University) came out with "Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning" The investigators propose feedback - weighted learning based on importance sampling to improve upon an initial supervised system using binary user feedback.
The paper shared the most on social media this week is by a team at University of Toronto: "Learning Deformable Tetrahedral Meshes for 3D Reconstruction" by Jun Gao et al (Nov 2020) with 132 shares.
This week was very active for "Computer Science - Artificial Intelligence", with 159 new papers.
The paper discussed most in the news over the past week was "Generating Correct Answers for Progressive Matrices Intelligence Tests" by Niv Pekar et al (Nov 2020), which was referenced 3 times, including in the article Researchers develop AI that solves a matrix-based visual cognitive test in Venturebeat. The paper got social media traction with 15 shares. A Twitter user, @DataScienceNIG, said "AI solves a matrix-based visual cognitive test. Researchers & have developed a ML model that solves the Raven Progressive Matrix, an intelligence test with the goal to generate the missing image in a grid of 3X3 abstract images".
Leading researcher Sergey Levine (University of California, Berkeley) came out with "Rearrangement: A Challenge for Embodied AI" @erikwijmans tweeted "Excited to see how fast we can make progress on these tasks".
The paper shared the most on social media this week is by a team at DeepMind: "Representation Matters: Improving Perception and Exploration for Robotics" by Markus Wulfmeier et al (Nov 2020) with 83 shares. The investigators systematically evaluate a number of common learnt and hand - engineered representations in the context of three robotics tasks : lifting, stacking and pushing of 3D blocks.
This week was active for "Computer Science - Computer Vision and Pattern Recognition", with 217 new papers.
The paper discussed most in the news over the past week was by a team at University of Texas at San Antonio: "Zoom on the Keystrokes: Exploiting Video Calls for Keystroke Inference Attacks" by Mohd Sabra et al (Oct 2020), which was referenced 5 times, including in the article Surprising New Zoom Hacking Threat Revealed—What Users Need To Know in Forbes.com. The paper author, Murtuza Jadliwala (University of Texas at San Antonio), was quoted saying "For someone to carry out this attack [today], they’d need a lot of experience and expertise". The paper got social media traction with 19 shares. The researchers design and evaluate an attack framework to infer one type of such private information from the video stream of a call -- keystrokes, i.e., text typed during the call. On Twitter, @paultaylorbrain commented "Crazy. Guessing what you type during Zoom from arm movements. Accuracy 18% at guessing passwords (already slightly scary) goes up beyond 90% at saying whether or not you are typing something specific like your username. Harder if wearing sleeves!".
Leading researcher Sergey Levine (University of California, Berkeley) came out with "Rearrangement: A Challenge for Embodied AI" @erikwijmans tweeted "Excited to see how fast we can make progress on these tasks".
The paper shared the most on social media this week is by a team at University of Toronto: "Learning Deformable Tetrahedral Meshes for 3D Reconstruction" by Jun Gao et al (Nov 2020) with 132 shares.
This week was active for "Computer Science - Computers and Society", with 34 new papers.
The paper discussed most in the news over the past week was "We Dont Speak the Same Language: Interpreting Polarization through Machine Translation" by Ashiqur R. KhudaBukhsh et al (Oct 2020)
Over the past week, 21 new papers were published in "Computer Science - Human-Computer Interaction".
The paper discussed most in the news over the past week was by a team at University of Texas at San Antonio: "Zoom on the Keystrokes: Exploiting Video Calls for Keystroke Inference Attacks" by Mohd Sabra et al (Oct 2020)
Leading researcher J. Wang (Chinese Academy of Sciences) published "Impact of delayed response on Wearable Cognitive Assistance" The investigators present an experimental study assessing how WCA users react to varying end - to - end delays induced by the application pipeline or infrastructure.
This week was very active for "Computer Science - Learning", with 401 new papers.
The paper discussed most in the news over the past week was by a team at University of Waterloo: "Less Than One-Shot Learning: Learning N Classes From M by Ilia Sucholutsky et al (Sep 2020), which was referenced 13 times, including in the article Radar trends to watch: November 2020 in O'Reilly Network. The paper author, Ilia Sucholutsky (University of Waterloo), was quoted saying "More efficient machine learning and deep learning models mean that AI can learn faster, are potentially smaller, and are lighter and easier to deploy". The paper got social media traction with 140 shares. On Twitter, @MichaelAzmy posted "That's so cool! Research "Less than one-shot learning can teach a model to identify more objects than the number of examples it is trained on." Article: Paper"
Leading researcher Sergey Levine (University of California, Berkeley) published "Amortized Conditional Normalized Maximum Likelihood" The investigators propose the amortized conditional normalized maximum likelihood (ACNML) method as a scalable general - purpose approach for uncertainty estimation, calibration, and out - of - distribution robustness with deep networks.
The paper shared the most on social media this week is by a team at Google: "Power of data in quantum machine learning" by Hsin-Yuan Huang et al (Nov 2020) with 107 shares. The investigators show that some problems that are classically hard to compute can be predicted easily with classical machines that learn from data. @dabacon (Dave 🥓) tweeted "I've started the plot comparing largest classical simulation of quantum machine learning versus the largest quantum computation of quantum machine learning. This will be a fun race".
Over the past week, 17 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 Dublin: "I-nteract 2.0: A Cyber-Physical System to Design 3D Models using Mixed Reality Technologies and Deep Learning for Additive Manufacturing" by Ammar Malik et al (Oct 2020), which was referenced 1 time, including in the article I-nteract Allows User to Design, Feel and 3D Print Objects in Mixed Reality in 3DPrint.com. The paper got social media traction with 5 shares. The authors present novel advances in the development of the interaction platform they - nteract to generate 3D models using both constructive solid geometry and artificial intelligence.
Over the past week, 16 new papers were published in "Computer Science - Neural and Evolutionary Computing".
This week was extremely active for "Computer Science - Robotics", with 128 new papers.
The ), which was referenced 1 time, including in the article The Power of Offline Reinforcement Learning in Towards Data Science. The paper got social media traction with 32 shares. On Twitter, @svlevine posted "COG uses offline RL (CQL) to incorporate past data to generalize new skills. E.g., a robot picking a ball from a drawer will know it must open the drawer if it is closed, even if it never performed these steps together. thread ->".
Leading researcher Sergey Levine (University of California, Berkeley) published "Rearrangement: A Challenge for Embodied AI" @erikwijmans tweeted "Excited to see how fast we can make progress on these tasks".
The paper shared the most on social media this week is by a team at DeepMind: "Representation Matters: Improving Perception and Exploration for Robotics" by Markus Wulfmeier et al (Nov 2020)