Week Ending 6.14.2020
RESEARCH WATCH: 6.14.2020
This week was active for "Computer Science - Artificial Intelligence", with 123 new papers.
The paper discussed most in the news over the past week was "Universal Masking is Urgent in the COVID-19 Pandemic: SEIR and Agent Based Models, Empirical Validation, Policy Recommendations" by De Kai et al (Apr 2020), which was referenced 260 times, including in the article Trump Unmasked in Moyers & Company. The paper author, Vitamin D. Kai, was quoted saying "I saw the country where I grew up [China], where my family lives [now mostly in the Bay Area], about to face this pandemic without knowing much about something as simple as wearing a mask to protect themselves and others". The paper also got the most social media traction with 3884 shares. On Twitter, @chrish_99 posted "Masks more effective than lockdown at suppressing spread. Mandate mask wearing and end the lockdown? Even non medical masks are recommended", while @gastronomy posted "> We present two models for the COVID-19 pandemic predicting the impact of u".
The paper shared the most on social media this week is "SECure: A Social and Environmental Certificate for AI Systems" by Abhishek Gupta (Microsoft) et al (Jun 2020) with 51 shares.
This week was active for "Computer Science - Computer Vision and Pattern Recognition", with 273 new papers.
The paper discussed most in the news over the past week was "YOLOv4: Optimal Speed and Accuracy of Object Detection" by Alexey Bochkovskiy et al (Apr 2020), which was referenced 9 times, including in the article One stop for object detectors in Medium.com. The paper got social media traction with 834 shares. A Twitter user, @__usamah___, posted "idk why but reading a YOLO paper without pjreddie (and his antics) made me feel sad".
Leading researcher Trevor Darrell (UC Berkeley) came out with "Quasi-Dense Instance Similarity Learning" The investigators present a simple yet effective quasi - dense matching method to learn instance similarity from hundreds of region proposals in a pair of images.
The paper shared the most on social media this week is by a team at University of Michigan: "VirTex: Learning Visual Representations from Textual Annotations" by Karan Desai et al (Jun 2020) with 405 shares. @NeurAutomata (NeurAutomata) tweeted "karpathy "RT jcjohnss: Our new paper (w/kdexd) argues that "language is all you need" for good visual features: we train CNN+Transformer *from scratch* on ~100k images+captions from COCO, transfer the CNN to 6 downstream vision tasks, and match/ex".
This week was very active for "Computer Science - Computers and Society", with 59 new papers.
The paper discussed most in the news over the past week was "Pandemic Programming: How COVID-19 affects software developers and how their organizations can help" by Paul Ralph et al (May 2020), which was referenced 6 times, including in the article Programmers suffer through pandemic Survey finds low productivity and well-being among developers. in ACS News. The paper author, Dr Sebastian Baltes, was quoted saying "Many developers began working from home, often at short notice and under difficult and stressful conditions, as COVID-19 swept across the world". The paper got social media traction with 9 shares. The investigators seek to understand the effects of the pandemic on developers wellbeing and productivity.
The paper shared the most on social media this week is by a team at Philipps-Universität Marburg: "Mind the GAP: Security & Privacy Risks of Contact Tracing Apps" by Lars Baumgärtner (TU Darmstadt) et al (Jun 2020) with 179 shares. @nipafx (Nicolai Parlog) tweeted "First, I'm a security noob and none of these are my original thoughts. It's a (hopefully accurate) rendition of the research of et al from Paper: All credit is theirs, all errors are mine. 2/10".
This week was active for "Computer Science - Human-Computer Interaction", with 31 new papers.
The paper discussed most in the news over the past week was "Situated and Interactive Multimodal Conversations" by Seungwhan Moon et al (Jun 2020), which was referenced 5 times, including in the article Facebook uses real-life furniture interactions to train chatbots in Furniture Today. The paper got social media traction with 9 shares.
This week was extremely active for "Computer Science - Learning", with 749 new papers.
The paper discussed most in the news over the past week was by a team at Rice University: "SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation" by Yang Zhao et al (May 2020), which was referenced 8 times, including in the article Rice engineers offer smart, timely ideas for AI bottlenecks in Rice University. The paper author, Yingyan Lin (Rice University), was quoted saying "It can cost about 200 times more energy to access the main memory — the DRAM — than to perform a computation, so the key idea for SmartExchange is enforcing structures within the algorithm that allow us to trade higher-cost memory for much-lower-cost computation". The paper got social media traction with 8 shares.
Leading researcher Oriol Vinyals (DeepMind) published "Pointer Graph Networks" The investigators introduce Pointer Graph Networks (PGNs) which augment sets or graphs with additional inferred edges for improved model expressivity.
The paper shared the most on social media this week is by a team at Microsoft: "Linformer: Self-Attention with Linear Complexity" by Sinong Wang et al (Jun 2020) with 320 shares. @veydpz_public (Seung-won Park) tweeted "Unbelievable. The key-query matching can be reduced from O(n^2) to O(n*k), where projected dimension k can be set constant regardless of sequence length n".
This week was active for "Computer Science - Multiagent Systems", with 27 new papers.
The paper discussed most in the news over the past week was by a team at DeepMind: "Learning to Play No-Press Diplomacy with Best Response Policy Iteration" by Thomas Anthony et al (Jun 2020), which was referenced 1 time, including in the article DeepMind hopes to teach AI to cooperate by playing Diplomacy in Venturebeat. The paper got social media traction with 23 shares. A Twitter user, @irinimalliaraki, commented "Deepmind proposes using games like Diplomacy to study the emergence and detection of manipulative behaviors to "make sure that we know how to mitigate such behaviors in real-world applications". AI geopolitics took an interesting twist".
The paper shared the most on social media this week is "Efficient democratic decisions via nondeterministic proportional consensus" by Jobst Heitzig et al (Jun 2020) with 81 shares.
This week was active for "Computer Science - Neural and Evolutionary Computing", with 49 new papers.
The paper discussed most in the news over the past week was by a team at Stanford University: "Machine Learning on Graphs: A Model and Comprehensive Taxonomy" by Ines Chami et al (May 2020), which was referenced 1 time, including in the article London Bike Ride Forecasting with Graph Convolutional Networks in Towards Data Science. The paper also got the most social media traction with 329 shares. On Twitter, @kerstingAIML posted "Nice overview & conceptualization of (differentiable) approaches to learning on graphs. It is really important to get overviews & unifying views. 🙏 Follow up could be on learning with graphs, showing also the strong connection to graph kernels (via WL & neural fingerprints etc.)".
The paper shared the most on social media this week is "A bio-inspired bistable recurrent cell allows for long-lasting memory" by Nicolas Vecoven et al (Jun 2020) with 124 shares. @glouppe (Gilles Louppe) tweeted "Who knew? Changing the reset gate in GRU so that the gate can take values in ]0,20,1[ makes the cell bistable, hence enabling long-lasting memories! Very nice work by my colleagues and Guillaume Drion!".
This week was very active for "Computer Science - Robotics", with 66 new papers.
The paper discussed most in the news over the past week was by a team at University of Zurich and ETH Zurich: "Deep Drone Acrobatics" by Elia Kaufmann et al (Jun 2020), which was referenced 3 times, including in the article Researchers train drones to perform flips, rolls, and loops with AI in Venturebeat. The paper was shared 1 time in social media. The researchers propose to learn a sensorimotor policy that enables an autonomous quadrotor to fly extreme acrobatic maneuvers with only onboard sensing and computation.