— David Robinson (@drob) July 20, 2021
— David Robinson (@drob) July 20, 2021
In addition to CoPilot, @Microsoft, the owners of GitHub, have created a different but related product called “API Usage Examples”. It shows examples of API use with links to their source.
— Jeremy Howard (@jeremyphoward) July 20, 2021
Sometimes, this might be what you really need.https://t.co/d5hghPjjBa
Most time coding is not taken up in writing code, but with designing, debugging, and maintaining code. When code is automatically generated, it’s easy to end up with a lot more of it.
— Jeremy Howard (@jeremyphoward) July 20, 2021
Especially since Copilot code tends to be verbose.
YOLOX: Exceeding YOLO Series in 2021
— AK (@ak92501) July 20, 2021
pdf: https://t.co/xC1ZEPOLRW
abs: https://t.co/BNkflEgqaC
github: https://t.co/rym6pRl10e pic.twitter.com/7Gg3ov9SUN
Internet-Augmented Dialogue Generation
— AK (@ak92501) July 19, 2021
pdf: https://t.co/qcQ5ZmAA47
abs: https://t.co/u4mnlnjP6o pic.twitter.com/nm2NQXxhNb
Graph Kernel Attention Transformers
— AK (@ak92501) July 19, 2021
pdf: https://t.co/Uyy5ZcTD1I
abs: https://t.co/KTxHRuYvVV
comparison of method with 9 different GNN classes on tasks, showing consistent gains coming from GKATs pic.twitter.com/acoHALTKjv
Today we're announcing fastchan, a new conda mini-distribution with a focus on the PyTorch ecosystem. Using fastchan, installation and updates of libraries such as @PyTorch, @huggingface and @RAPIDSai is faster, easier, and more reliablehttps://t.co/UMNkQGi3XJ
— Jeremy Howard (@jeremyphoward) July 16, 2021
TorchShard is a lightweight engine for slicing a PyTorch tensor into parallel shards. It can reduce GPU memory and scale up the training when the model has massive linear layers or huge classes. Read more below:https://t.co/DBLXYTCmEO
— PyTorch (@PyTorch) July 16, 2021
Blender Bot 2.0: An open source chatbot that builds long-term memory and searches the internet
— Kyunghyun Cho (@kchonyc) July 16, 2021
very cool! https://t.co/D15jBGCBNT
Slides for my #SciPy2021 talk on PyNNDescent can be found here: https://t.co/FePhGpclhp
— Leland McInnes (@leland_mcinnes) July 16, 2021
After a lot of work, we have finished the implementation of PEP 657 🚀🎉. In Python 3.11🐍, tracebacks will annotate where exactly the error is happening in your code 🤯. No more confusion having to guess what part of the expression is wrong. Learn more at https://t.co/bCbXYp5rN7 pic.twitter.com/EnxPY6eojb
— Pablo Galindo (@pyblogsal) July 16, 2021
Passive attention in artificial neural networks predicts human visual selectivity
— AK (@ak92501) July 16, 2021
pdf: https://t.co/px3yAu6rEM
78 new experiments and 6,610 participants, show that passive attention techniques reveal a significant overlap with human visual selectivity estimates pic.twitter.com/WKhgIOrFFo