Week Ending 4.24.2022

 

RESEARCH WATCH: 4.24.2022

SPONSORED BY

 

This week was active for "Computer Science", with 1,169 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 45 times, including in the article A year after Apple enforces app tracking policy, covert iOS tracking remains in ArsTechnica. The paper got social media traction with 158 shares. A Twitter user, @RDBinns, posted "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".

  • Leading researcher Sergey Levine (University of California, Berkeley) published "Context-Aware Language Modeling for Goal-Oriented Dialogue Systems" The investigators formulate goal - oriented dialogue as a partially observed Markov decision process, interpreting the language model as a representation of both the dynamics and the policy. @ak92501 tweeted "Context-Aware Language Modeling for Goal-Oriented Dialogue Systems abs: project page: CALM outperforms the state-of-the-art method by 7% in terms of task success, matching human-level task performance".

  • The paper shared the most on social media this week is "VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance" by Katherine Crowson et al (Apr 2022) with 255 shares. @HochreiterSepp (Sepp Hochreiter) tweeted "ArXiv Generating images from open domain text prompts using CLIP to guide VQGAN. Higher visual quality outputs than DALL-E, GLIDE and Open-Edit. Prompts of higher semantic complexity. Code available (colab notebooks)".

  • The most influential Twitter user discussing papers is AK who shared "mGPT: Few-Shot Learners Go Multilingual" by Oleh Shliazhko et al (Apr 2022) and said: "mGPT: Few-Shot Learners Go Multilingual abs: introduces two autoregressive GPT-like models with 1.3 billion and 13 billion parameters trained on 60 languages from 25 language families using Wikipedia and Colossal Clean Crawled Corpus".

This week was very active for "Computer Science - Artificial Intelligence", with 185 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 18 times, including in the article MIT's newest computer vision algorithm identifies images down to the pixel 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 20 shares. A user, @ZetaVector, tweeted "More image segmentation without supervision. "Unsupervised Semantic Segmentation by Distilling Feature Correspondences" by Mark Hamilton, now at".

  • Leading researcher Sergey Levine (University of California, Berkeley) came out with "Context-Aware Language Modeling for Goal-Oriented Dialogue Systems" The investigators formulate goal - oriented dialogue as a partially observed Markov decision process, interpreting the language model as a representation of both the dynamics and the policy. @ak92501 tweeted "Context-Aware Language Modeling for Goal-Oriented Dialogue Systems abs: project page: CALM outperforms the state-of-the-art method by 7% in terms of task success, matching human-level task performance".

  • The paper shared the most on social media this week is by a team at Carnegie Mellon University: "Deep Equilibrium Optical Flow Estimation" by Shaojie Bai et al (Apr 2022) with 84 shares. @HochreiterSepp (Sepp Hochreiter) tweeted "ArXiv Optical flow estimation by deep equilibrium models. 4 to 6× times less memory than recurrent networks since using cheap inexact gradient makes backward pass almost for free. Improves SOTA methods on Sintel and KITTI with less compute and memory".

This week was very active for "Computer Science - Computer Vision and Pattern Recognition", with 329 new papers.

Over the past week, 27 new papers were published in "Computer Science - Computers and Society".

This week was very active for "Computer Science - Human-Computer Interaction", with 49 new papers.

This week was very active for "Computer Science - Learning", with 341 new papers.

Over the past week, 13 new papers were published in "Computer Science - Multiagent Systems".

Over the past week, 17 new papers were published in "Computer Science - Neural and Evolutionary Computing".

This week was active for "Computer Science - Robotics", with 59 new papers.


EYE ON A.I. GETS READERS UP TO DATE ON THE LATEST FUNDING NEWS AND RELATED ISSUES. SUBSCRIBE FOR THE WEEKLY NEWSLETTER.