Week Ending 5.1.2022
RESEARCH WATCH: 5.1.2022
SPONSORED BY
This week was very active for "Computer Science - Artificial Intelligence", with 196 new papers.
The paper discussed most in the news over the past week was by a team at Cornell: "Unsupervised Semantic Segmentation by Distilling Feature Correspondences" by Mark Hamilton et al (Mar 2022), which was referenced 22 times, including in the article Deep Science: AI simulates economies and predicts which startups receive funding in Yahoo! News. The paper author, Mark Hamilton (Microsoft), was quoted saying "If you're looking at oncological scans, the surface of planets, or high-resolution biological images, it’s hard to know what objects to look for without expert knowledge. In emerging domains, sometimes even human experts don't know what the right objects should be". The paper got social media traction with 21 shares. A user, @ZetaVector, tweeted "More image segmentation without supervision. "Unsupervised Semantic Segmentation by Distilling Feature Correspondences" by Mark Hamilton, now at".
Leading researcher Oriol Vinyals (DeepMind) published "Flamingo: a Visual Language Model for Few-Shot Learning".
The paper shared the most on social media this week is by a team at IT University of Copenhagen: "HyperNCA: Growing Developmental Networks with Neural Cellular Automata" by Elias Najarro et al (Apr 2022) with 101 shares. The investigators propose a new hypernetwork approach to grow artificial neural networks based on neural cellular automata (NCA). @summarizedml (SummarizedML) tweeted "A new hypernetwork approach to grow artificial neural networks based on neuralcellular automata that can solve commonreinforcement learning tasks. 📄".
This week was active for "Computer Science - Computer Vision and Pattern Recognition", with 282 new papers.
The paper discussed most in the news over the past week was by a team at Cornell: "Unsupervised Semantic Segmentation by Distilling Feature Correspondences" by Mark Hamilton et al (Mar 2022)
Leading researcher Oriol Vinyals (DeepMind) published "Flamingo: a Visual Language Model for Few-Shot Learning".
The paper shared the most on social media this week is by a team at Google: "PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions" by Zhaoqi Leng et al (Apr 2022) with 280 shares. @nathanewest (Nathan West) tweeted "Off to the cluster, codename trainingbeaches, to evaluate a handful of unique rf datasets 🏖🏖🏖. I’m hiring for my te for anyone who wants to build cool ai-native rf processing systems 😎. Bonus points for people that like to build platforms to automate the job".
The most influential Twitter user discussing papers is AK who shared "RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning" by Xiaojian Ma et al (Apr 2022) and said: "RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning abs: RelViT significantly outperforms prior approaches on HICO and GQA by 16% and 13% in the original split, and by 43% and 18% in the systematic split".
This week was active for "Computer Science - Computers and Society", with 37 new papers.
The paper discussed most in the news over the past week was by a team at University of Oxford: "Goodbye Tracking? Impact of iOS App Tracking Transparency and Privacy Labels" by Konrad Kollnig et al (Apr 2022), which was referenced 51 times, including in the article The winners and losers of Apple’s anti-tracking feature in MSN United States. The paper author, Konrad Kollnig (University of Oxford), was quoted saying "It’s a bit of a cat-and-mouse game". The paper got social media traction with 160 shares. A Twitter user, @RDBinns, commented "One of the worrying details from this research was the circumvention of Apple's privacy controls by trackers. When you 'Ask App Not to Track', iOS stops third parties accessing the advertising ID. So some resort to fingerprinting instead. One example is Alibaba-owned Umeng".
This week was very active for "Computer Science - Human-Computer Interaction", with 52 new papers.
The paper discussed most in the news over the past week was by a team at Columbia University: "Opal: Multimodal Image Generation for News Illustration" by Vivian Liu et al (Apr 2022), which was referenced 15 times, including in the article Deep Science: AI simulates economies and predicts which startups receive funding in Yahoo! News. The paper got social media traction with 5 shares.
This week was very active for "Computer Science - Learning", with 386 new papers.
The paper discussed most in the news over the past week was by a team at Cornell: "Unsupervised Semantic Segmentation by Distilling Feature Correspondences" by Mark Hamilton et al (Mar 2022)
Leading researcher Oriol Vinyals (DeepMind) came out with "Flamingo: a Visual Language Model for Few-Shot Learning".
The paper shared the most on social media this week is "Its DONE: Direct ONE-shot learning without training optimization" by Kazufumi Hosoda et al (Apr 2022) with 292 shares. @summarizedml (SummarizedML) tweeted "Direct ONE-shot learning (DONE) adds a new class to a DNN classifier with neither training optimization nor other-classes modification. 📄".
This week was active for "Computer Science - Multiagent Systems", with 21 new papers.
The paper discussed most in the news over the past week was by a team at Harvard University: "Using Reinforcement Learning to Study Platform Economies under Market Shocks" by Xintong Wang et al (Mar 2022), which was referenced 14 times, including in the article Deep Science: AI simulates economies and predicts which startups receive funding in Yahoo! News. The paper was shared 4 times in social media. The authors develop a multi - agent simulation environment to capture key elements of a platform economy, including the kinds of economic shocks that disrupt a traditional, off - platform market.
Over the past week, 26 new papers were published in "Computer Science - Neural and Evolutionary Computing".
The paper shared the most on social media this week is by a team at IT University of Copenhagen: "HyperNCA: Growing Developmental Networks with Neural Cellular Automata" by Elias Najarro et al (Apr 2022)
This week was active for "Computer Science - Robotics", with 58 new papers.
The paper discussed most in the news over the past week was by a team at Massachusetts Institute of Technology: "GelSight Fin Ray: Incorporating Tactile Sensing into a Soft Compliant Robotic Gripper" by Sandra Q. Liu et al (Apr 2022), which was referenced 11 times, including in the article Robotic hand created with sense of touch, better at picking up objects (or punching kaiju) in Syfy Wire. The paper author, Sandra Q. Liu (Massachusetts Institute of Technology), was quoted saying "There’s a lot of potential applications, like homecare robots. If you need to have a robot assist someone in dressing or in the kitchen, having this sort of sensory touching can help because it’s a lot safer to interact with people". Wenzhen Yuan (Carnegie Mellon University), who is not part of the study, said "Sensing with soft robots has been a big challenge, because it is difficult to set up sensors — which are traditionally rigid — on soft bodies". The paper was shared 2 times in social media.
Leading researcher Pieter Abbeel (UC Berkeley) published "Coarse-to-fine Q-attention with Tree Expansion" @summarizedml tweeted "To use Q-attention as a tree that can be expanded and used to accumulate value estimates across the top-k vox 📄".
The paper shared the most on social media this week is by a team at Google: "Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items" by Laura Downs et al (Apr 2022) with 99 shares. @JeffDean (Jeff Dean (@🏡)) tweeted ""Google Scanned Objects (GSO) dataset, a curated collection of over 1000 3D scanned common household items for use in the Ignition Gazebosimulators" 17 action figures, 28 bags, 254 shoes, and more!".