Hackernews posts about Transformer
Transformer is a type of neural network architecture designed for natural language processing tasks that relies on self-attention mechanisms to process input sequences in parallel.
Related:
Apple
- Transformers Are Graph Neural Networks (arxiv.org)
- We reimagined Transformer architectures inspired by nature's hidden structures (ieeexplore.ieee.org)
- Turbine Transport Transformer (mitxela.com)
- Text-to-LoRA: Instant Transformer Adaption (arxiv.org)
- Vision Transformers Don't Need Trained Registers (arxiv.org)
- Text-to-LoRA: Instant Transformer Adaption (www.arxiv.org)
- Energy-Based Transformers Are Scalable Learners and Thinkers (energy-based-transformers.github.io)
- Analog Transformers (oklo.org)
- Erwin: A Tree-Based Hierarchical Transformer for Large-Scale Physical Systems (maxxxzdn.github.io)
- Transformers: Deprecating TensorFlow and Flax support (twitter.com)
- Happy Birthday Transformer (twitter.com)
- Simplified Transformers (github.com)
- Show HN: Vpuna AI Search – A semantic search platform (aisearch.vpuna.com)
- So You Want to Work in Mechanistic Interpretability? (transformer-circuits.pub)
- Deprecate TF + JAX (github.com)