🤖 Transformer Architecture - tomasz · Scour

🧠 Bidirectional Encoder Representations from Transformers (BERT) 🔗RAG

medium.com·6d

Task Bert 📝TextRank

producthunt.com·2d

Neural Networks for Language: How Context Became a Learned Transformation 💬Prompt Engineering

pub.towardsai.net

·5h

Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers 🔍Vector Search

arxiv.org·1d

Attention : The Secret Superpower Inside Every AI 🦊Information Foraging

medium.com·3d

milanm/AutoGrad-Engine: A complete GPT language model (training and inference) in ~600 lines of pure C#, zero dependencies 💬Prompt Engineering

github.com·1d·Hacker News

Building GPT from Scratch 🔢Kolmogorov Complexity

medium.com·3d

Team Fusion@ SU@ BC8 SympTEMIST track: transformer-based approach for symptom recognition and linking 🔍Vector Search

arxiv.org·2d

tmaselko/paper-attncap: Repository associated with the "Separate and Amplify: Attention's Geometry of Retrieval" paper. Contains TSAR synthetic task, minimal model, training/repro code, and chart/table generation. 🔢Kolmogorov Complexity

github.com·2d·Hacker News

Automated Attention Pattern Discovery at Scale in Large Language Models 🔗RAG

arxiv.org·4d

Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning 💬Prompt Engineering

arxiv.org·2d

Hybrid CNN-Transformer Architecture for Arabic Speech Emotion Recognition 👁️Computer Vision

arxiv.org·1d

LAG-XAI: A Lie-Inspired Affine Geometric Framework for Interpretable Paraphrasing in Transformer Latent Spaces 🔢Kolmogorov Complexity

arxiv.org·3d

Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding 🔢Kolmogorov Complexity

arxiv.org·1d

Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion 🧠Deep Learning

arxiv.org·3d

On the Geometry of Positional Encodings in Transformers 🔢Kolmogorov Complexity

arxiv.org·3d

Brain-to-Speech: Prosody Feature Engineering and Transformer-Based Reconstruction ✂️Tokenization

arxiv.org·3d

PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer 🔢Kolmogorov Complexity

arxiv.org·3d

Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner 💬Prompt Engineering

arxiv.org·3d

Training Transformers in Cosine Coefficient Space 🔍Vector Search

arxiv.org·4d

Loading more...