8/ CodeT5+ – supports a wide range of code understanding and generation tasks and different training methods to improve efficacy and computing efficiency; achieves SoTA on tasks like code completion, math programming, and text-to-code retrieval tasks.
RESEARCH
-
Symbol Tuning Boosts Language Models In-Context Learning Performance
By
–
9/ Symbol Tuning – an approach to finetune LMs on in-context input-label pairs where natural language labels are replaced by arbitrary symbols; boosts performance on unseen in-context learning tasks and algorithmic reasoning tasks.
-
DoReMi: Domain-Weighted Resampling for Efficient Model Training
By
–
7/ DoReMi – trains a small proxy model over domains to produce domain weights without knowledge of downstream tasks; it resamples a dataset with the domain weights which allows using a 280M proxy model to train an 8B model (30x larger) more efficiently.
-
TinyStories: Efficient Language Models for Story Generation
By
–
6/ TinyStories – uses a synthetic dataset of short stories to train and evaluate LMs that are much smaller than SoTA models but can produce fluent and consistent stories with several paragraphs, and demonstrate reasoning capabilities.
-
Drag Your GAN: Interactive Point-Based Image Control Method
By
–
1/ Drag Your GAN – an approach for controlling GANs that allows dragging points of the image to precisely reach target points in a user-interactive manner.https://t.co/Nbhtle5VRG
— DAIR.AI (@dair_ai) 21 mai 20231/ Drag Your GAN – an approach for controlling GANs that allows dragging points of the image to precisely reach target points in a user-interactive manner.
-
Top ML Papers of the Week: DragGAN, CodeT5+, Med-PaLM 2
By
–
Top ML Papers of the Week (May 15 – 21): – DragGAN
– CodeT5+
– StructGPT
– Med-PaLM 2
– Symbol Tuning
– Evidence of Meaning in LLMs
… -
ML on Graphs: Solving Problems Traditional Methods Failed
By
–
That's a wrap! I build maps for a living, we have used ML on graphs to solve problems where traditional methods failed. Sharing these resources based on my experience!! Find me → @akshay_pachaar Everyday, I share tutorials around ML! Check one of my older threads
-
Stanford CS224W: Machine Learning with Graphs Course
By
–
Stanford CS224W: Machine Learning with Graphs Offered by Stanford, a comprehensive course for ML on Graphs. Check this out https://
youtube.com/playlist?list=
PLoROMvodv4rPLKxIpqhjhPgdQy7imNkDn
… -
GNNs Fundamentals: YouTube Playlist and Expert Talks
By
–
GNNs by AI Overloards A fantastic YouTube playlist for grasping the fundamentals! Also featuring invited talks by industry experts using ML on Graphs. Check this out https://
youtube.com/playlist?list=
PLSgGvve8UweGx4_6hhrF3n4wpHf_RV76_
… -
Graph Neural Networks Foundations: Message Passing and Node Embedding
By
–
Foundations of Graph Neural Networks By @PetarV_93 (Scientist at DeepMind) The perfect starting point! What you'll learn:
– GNNs from first principles
– Message passing on graphs
– Node Embedding
– Geometric Deep Learning Check this