Week Ending 1.2.2022
RESEARCH WATCH: 1.2.2022
Over the past week, 745 new papers were published in "Computer Science".
The paper discussed most in the news over the past week was "FLAVA: A Foundational Language And Vision Alignment Model" by Amanpreet Singh et al (Dec 2021), which was referenced 9 times, including in the article A look back at recent AI trends — and what 2022 might hold in BusinessMayor.com. The paper got social media traction with 31 shares. On Twitter, @ak92501 said "FLAVA: A Foundational Language And Vision Alignment Model abs: demonstrate impressive performance on a wide range of 35 tasks spanning these target modalities".
Leading researcher Yoshua Bengio (Université de Montréal) published "Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models" @summarizedml tweeted "A balanced batch sampling technique for generalization of chest X-ray pathologies that improves performance over baseline models trained withoutbalancing. 📄".
The paper shared the most on social media this week is by a team at Columbia University: "A Neural Network Solves and Generates Mathematics Problems by Program Synthesis: Calculus, Differential Equations, Linear Algebra, and More" by Iddo Drori et al (Dec 2021) with 275 shares. @HochreiterSepp (Sepp Hochreiter) tweeted "ArXiv Transformers pre-trained on text and fine-tuned on code solve math problems by program synthesis (questions as Codex prompts). Solves and grades problems from MIT's math courses and a math benchmark perfectly. Generates new math questions".
This week was active for "Computer Science - Artificial Intelligence", with 121 new papers.
The paper discussed most in the news over the past week was by a team at DeepMind: "Player of Games" by Martin Schmid et al (Dec 2021), which was referenced 8 times, including in the article Interesting Innovations From DeepMind In 2021 in Analytics India Magazine. The paper author, Schmid, was quoted saying "[O]ne would expect that the applications that benefited from AlphaZero might also benefit from Player of Games". The paper got social media traction with 403 shares. A Twitter user, @PatrickPilarski, posted "Excellent new research from our Edmonton DeepMind office, showing an agent that can learn to skillfully engage in perfect and imperfect information games, including Scotland Yard. Great work folks!", while @MichaelHBowling said "Really excited that this work is finally coming out: seeing search, learning, and game theory really demonstrate its generality. So glad that I get to work with this great team".
This paper was also shared the most on social media with 275 tweets. @HochreiterSepp (Sepp Hochreiter) tweeted "ArXiv Transformers pre-trained on text and fine-tuned on code solve math problems by program synthesis (questions as Codex prompts). Solves and grades problems from MIT's math courses and a math benchmark perfectly. Generates new math questions".
Over the past week, 170 new papers were published in "Computer Science - Computer Vision and Pattern Recognition".
The paper discussed most in the news over the past week was "FLAVA: A Foundational Language And Vision Alignment Model" by Amanpreet Singh et al (Dec 2021)
Leading researcher Yoshua Bengio (Université de Montréal) came out with "Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models" @summarizedml tweeted "A balanced batch sampling technique for generalization of chest X-ray pathologies that improves performance over baseline models trained withoutbalancing. 📄".
The paper shared the most on social media this week is "StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2" by Ivan Skorokhodov et al (Dec 2021) with 76 shares. The investigators think of videos of what they should be - time - continuous signals, and extend the paradigm of neural representations to build a continuous - time video generator. @summarizedml (SummarizedML) tweeted "We extend the paradigm of neurological representations to build a continuous-time video generator, achieving state-of-the-art results on four modern 256 📄".
The most influential Twitter user discussing papers is AK who shared "Augmenting Convolutional networks with attention-based aggregation" by Hugo Touvron et al (Dec 2021) and said: "Augmenting Convolutional networks with attention-based aggregation abs: introduced a full patch-based ConvNet with no pyramidal structure".
Over the past week, 15 new papers were published in "Computer Science - Computers and Society".
The paper shared the most on social media this week is "A Survey on Gender Bias in Natural Language Processing" by Karolina Stanczak et al (Dec 2021) with 65 shares. The authors present a survey of 304 papers on gender bias in natural language processing. @leftoblique (Dana Fried) tweeted ""Despite a myriad of papers on gender bias in NLP methods, we find that most of the newly developed algorithms do not test their models for bias and disregard possible ethical considerations of their work." 🙃".
Over the past week, 15 new papers were published in "Computer Science - Human-Computer Interaction".
This week was active for "Computer Science - Learning", with 259 new papers.
The paper discussed most in the news over the past week was by a team at DeepMind: "Player of Games" by Martin Schmid et al (Dec 2021)
Leading researcher Kyunghyun Cho (New York University) published "LINDA: Unsupervised Learning to Interpolate in Natural Language Processing" @summarizedml tweeted "An unsupervised learning approach to text interpolation for dataaugmentation, to which we refer as "Learning to INterpol 📄".
The paper shared the most on social media this week is by a team at Columbia University: "A Neural Network Solves and Generates Mathematics Problems by Program Synthesis: Calculus, Differential Equations, Linear Algebra, and More" by Iddo Drori et al (Dec 2021)
The most influential Twitter user discussing papers is AK who shared "Augmenting Convolutional networks with attention-based aggregation" by Hugo Touvron et al (Dec 2021)
Over the past week, ten new papers were published in "Computer Science - Multiagent Systems".
Over the past week, eight new papers were published in "Computer Science - Neural and Evolutionary Computing".
Over the past week, 37 new papers were published in "Computer Science - Robotics".