Week Ending 5.29.2022
RESEARCH WATCH: 5.29.2022
SPONSORED BY
This week was extremely active for "Computer Science - Artificial Intelligence", with 332 new papers.
The paper discussed most in the news over the past week was by a team at DeepMind: "A Generalist Agent" by Scott Reed et al (May 2022), which was referenced 30 times, including in the article Gato, the latest from Deepmind. Towards true AI? in Towards Data Science. The paper author, Scott Reed (DeepMind), was quoted saying "With a single set of weights, Gato can engage in dialogue, caption images, stack blocks with a real robot arm, outperform humans at playing Atari games, navigate in simulated 3D environments, follow instructions, and more". The paper got social media traction with 209 shares. A user, @HochreiterSepp, tweeted "ArXiv Gato: a single generalist policy. Can play Atari, caption images, chat, stack blocks. Output determined by context (text, joint torques, buttons). 1.2B para. decoder-only transformer with 24 layers. Impressive results on control, robotics, language".
Leading researcher Yoshua Bengio (Université de Montréal) came out with "FL Games: A federated learning framework for distribution shifts" The researchers argue that in order to generalize better across non - i.i.d. @summarizedml tweeted "FL Games, a game-theoretic framework for federated learning for learning causal features that are invariant across clients. 📄".
The paper shared the most on social media this week is by a team at The University of Tokyo: "Large Language Models are Zero-Shot Reasoners" by Takeshi Kojima et al (May 2022) with 1979 shares. @ak92501 (AK) tweeted "Large Language Models are Zero-Shot Reasoners abs: LLMs are decent zero-shot reasoners by simply adding “Let’s think step by step” before each answer, increasing the accuracy on MultiArith from 17.7% to 78.7% and GSM8K from 10.4% to 40.7% with 175B model".
The most influential Twitter user discussing papers is AK who shared "Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation" by Vikram Voleti et al (May 2022) and said: "Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation abs: SOTA across standard video prediction and interpolation benchmarks, computation times for training models measured in 1-12 days using ≤ 4 GPUs".
This week was very active for "Computer Science - Computer Vision and Pattern Recognition", with 336 new papers.
The paper discussed most in the news over the past week was by a team at Google: "Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding" by Chitwan Saharia et al (May 2022), which was referenced 8 times, including in the article Google's Imagen AI produces photorealistic images from natural text with frightening fidelity in Digital Photography Review. The paper also got the most social media traction with 2508 shares.
Leading researcher Yann LeCun (New York University) came out with "Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods" The researchers propose a unifying framework under the helm of spectral manifold learning to address those limitations. @BlindDou tweeted "Who wants to give a review on this? Check and search".
This week was active for "Computer Science - Computers and Society", with 36 new papers.
The paper discussed most in the news over the past week was "A Peek into the Political Biases in Email Spam Filtering Algorithms During US Election 2020" by Hassan Iqbal et al (Mar 2022), which was referenced 84 times, including in the article Republicans seized on a study as proof of Google’s bias. Its authors say it's being misrepresented. in Washington Post. The paper author, Muhammad Shahzad (Technical University of Munich), was quoted saying "default behavior". The paper also got the most social media traction with 614 shares. A Twitter user, @blackseraphimi1, commented ""A new study found that Google’s Gmail favors liberal candidates, allowing the vast majority of emails from left-wing politicians to land in the user’s inbox while more than two-thirds of messages from conservative candidates are marked as spam."".
This week was active for "Computer Science - Human-Computer Interaction", with 26 new papers.
Leading researcher Sergey Levine (University of California, Berkeley) came out with "First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization".
This week was extremely active for "Computer Science - Learning", with 644 new papers.
The paper discussed most in the news over the past week was by a team at DeepMind: "A Generalist Agent" by Scott Reed et al (May 2022)
Leading researcher Yoshua Bengio (Université de Montréal) came out with "FL Games: A federated learning framework for distribution shifts" The authors argue that in order to generalize better across non - i.i.d. @summarizedml tweeted "FL Games, a game-theoretic framework for federated learning for learning causal features that are invariant across clients. 📄".
The paper shared the most on social media this week is by a team at Google: "Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding" by Chitwan Saharia et al (May 2022) with 2508 shares.
The most influential Twitter user discussing papers is AK who shared "Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation" by Vikram Voleti et al (May 2022)
Over the past week, 14 new papers were published in "Computer Science - Multiagent Systems".
The paper discussed most in the news over the past week was "Learning Eco-Driving Strategies at Signalized Intersections" by Vindula Jayawardana et al (Apr 2022), which was referenced 18 times, including in the article On the Road to Cleaner, Greener, and Faster Driving – With Some Help From AI in SciTechDaily. The paper author, Cathy Wu (University of Delaware), was quoted saying "This is a really interesting place to intervene. No one’s life is better because they were stuck at an intersection. With a lot of other climate change interventions, there is a quality-of-life difference that is expected, so there is a barrier to entry there. Here, the barrier is much lower". The paper was shared 1 time in social media. The investigators propose a reinforcement learning (RL) approach to learn effective eco - driving control strategies. On Twitter, @summarizedml posted "A reinforcementlearning approach to learn effective eco-driving control strategies at intersections. 📄".
Over the past week, 28 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 Google: "An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems" by Andrea Gesmundo et al (May 2022) with 62 shares. @ak92501 (AK) tweeted "An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems abs: best test accuracy reported for a model trained only on public data for competitive tasks such as cifar10: 99.43%".
The most influential Twitter user discussing papers is AK who shared "Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation" by Vikram Voleti et al (May 2022)
This week was active for "Computer Science - Robotics", with 61 new papers.
The paper discussed most in the news over the past week was by a team at DeepMind: "A Generalist Agent" by Scott Reed et al (May 2022)
Leading researcher Sergey Levine (University of California, Berkeley) published "First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization".