🤖 Transformer Architecture - tomasz · Scour

🧠 Bidirectional Encoder Representations from Transformers (BERT) 🔗RAG

medium.com·4d

Task Bert 📝TextRank

producthunt.com·16h

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

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·19h·Hacker News

Attention : The Secret Superpower Inside Every AI 🦊Information Foraging

medium.com·1d

Building GPT from Scratch 🔢Kolmogorov Complexity

medium.com·1d

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

arxiv.org·5h

RPNT: Robust Pre-trained Neural Transformer -- A Pathway for Generalized Motor Decoding 💬Prompt Engineering

arxiv.org·6d

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

arxiv.org·5h

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

arxiv.org·1d

DDCL-INCRT: A Self-Organising Transformer with Hierarchical Prototype Structure (Theoretical Foundations) 🧠Symbolic AI

arxiv.org·6d

On the Geometry of Positional Encodings in Transformers 🔢Kolmogorov Complexity

arxiv.org·1d

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

arxiv.org·1d

Attention Mechanisms Through the Lens of Numerical Methods: Approximation Methods and Alternative Formulations 🔄Systems Thinking

arxiv.org·6d

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

arxiv.org·1d

Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling 🧠Symbolic AI

arxiv.org·3d

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

arxiv.org·1d

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

arxiv.org·1d

S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models 💬Prompt Engineering

arxiv.org·6d

Training Transformers in Cosine Coefficient Space 🔍Vector Search

arxiv.org·2d

Loading more...