Stefan Blum

[arxiv @arxiv_org]

Causal-BERT : Language models for causality detection between events expressed in text. https://t.co/HrGBf9k9eJ

[arxiv @arxiv_org]

COVID-19 Cough Classification using Machine Learning and Global Smartphone Recordings. https://t.co/YfHhm38KmL

[TensorFlow @TensorFlow]

✏️ Create fun animations from doodles with Scroobly!

Scroobly is an AI Experiment that’s #MadeWithTFJS using FaceMesh and PoseNet models to bring your doodles to life in real-time with your camera. No design expertise or coding required!

Try it out 👉 https://t.co/xYghlbOcxA

[Andrej Karpathy @karpathy]

Added a new demo to minGPT that trains a GPT on pixels of CIFAR-10 images instead of text. Quite powerful that one can run the same training code/model on both domains. Notebook: https://t.co/nAt9VWXnrG . Produced reasonable samples after ~only 30 minutes on an 8-GPU V100 node:

[Greg Brockman @gdb]

An OpenAI-powered game design tool for creating dialogue flows. A good example of where our technology can boost productivity & creativity, but does not fully automate work:

[Mike Schroepfer @schrep]

Virtual assistants should help you remember the important parts of your day, remind you where you left your keys, or tell you if you forget an ingredient in a recipe. The Facebook AI Research team’s Embodied AI research is bringing that one step closer to reality. (1/7)

[arxiv @arxiv_org]

Model-based actor-critic: GAN + DRL (actor-critic) => AGI. https://t.co/OxjCXZ3AYz

[arxiv @arxiv_org]

Hybrid Graph Neural Networks for Crowd Counting. https://t.co/FcA3NUUXMJ

[Google DeepMind @GoogleDeepMind]

Our latest work uses reinforcement learning to learn to explore graph structured spaces, which improves the coverage for programs and Android apps testing with limited budget.
Paper: https://t.co/MjWkeuvLTn
@hanjundai, @liyuajia, Chenglong Wang, @rishabhs, @huangposen, @pushmeet

[Greg Brockman @gdb]

Just released the largest version of GPT-2, completing our 9-month staged release process: https://t.co/D55AUptD97

[arxiv @arxiv_org]

Pay Attention: Leveraging Sequence Models to Predict the Useful Life of Batteries. https://t.co/p6bZFEZgQz

[arxiv @arxiv_org]

Self-supervised Attention Model for Weakly Labeled Audio Event Classification. https://t.co/U8Fe6AZK8L

[arxiv @arxiv_org]

Learning Representations and Agents for Information Retrieval. https://t.co/qFS79T7tX7

[arxiv @arxiv_org]

Building a Massive Corpus for Named Entity Recognition using Free Open Data Sources. https://t.co/PGimf94an7

[arxiv @arxiv_org]

Multi-stakeholder Recommendation and its Connection to Multi-sided Fairness. https://t.co/TK5UMINO7s

[arxiv @arxiv_org]

Grape detection, segmentation and tracking using deep neural networks and three-dimension... https://t.co/h0QXbG8o8I

[arxiv @arxiv_org]

An Encoder-Decoder Based Approach for Anomaly Detection with Application in Additive Manu... https://t.co/Aw39aChELn

[arxiv @arxiv_org]

Deep Reinforcement Learning for Personalized Search Story Recommendation. https://t.co/fDl9ENg7g3

[arxiv @arxiv_org]

On Hard Exploration for Reinforcement Learning: a Case Study in Pommerman. https://t.co/6SRrNQPNjj