Memory Attention
Transformers now runs llama.cpp quants
GeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression
1
Origin Is All You Need: Provenance-Aware Transformers for Structural Trust-Boundary Separation
How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents
Disentangling Representation Evolution in Transformers through Directional Decomposition
1
Disentangling Representation Evolution in Transformers through Directional Decomposition
Retrospectively Reverse-Engineering Apple's Neural Engine
15 min2
Type Diversity Enables Transformers to Generalise Compositionally
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
2
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
1
Distance generalization in transformers: why bother with positional encoding?
2
Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens
1
It's Not RoPE that Creates Sinks: The Role of Self-Concentration and Value-Non-Mixing in Attention
Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise
1
VU#456290: Hugging Face Transformers library writes remote code to disk prior to consent check
1