On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “Connection-Attention”

Dual-Attention Graph Convolutional Networkcs.LG

Dual-attention GCN improves text classification by adapting to textual complexity.

problem Challenges in learning discriminative features from texts due to graph variants.

method Proposes a dual-attention GCN with connection-attention and hop-attention mechanisms.

result Achieves state-of-the-art performance on text classification tasks.

Graph Convolutional Network Text Classification Dual-Attention Connection-Attention Hop-Attention

2019-11-28abs ↗pdf ↗

Every Feedforward Neural Network Definable in an o-Minimal Structure Has Finite Sample Complexitystat.ML

New findings show modern neural networks have finite sample complexity in o-minimal structures.

problem Understanding the learnability of modern neural networks in a broad context.

method Analyzing feedforward neural networks definable in o-minimal structures.

result Modern neural networks, including MLPs, CNNs, GNNs, and transformers, have finite sample complexity in the agnostic PAC setting.

Neural Networks PAC Learnability o-Minimal Structures Finite Sample Complexity Modern Architectures

2026-05-08abs ↗pdf ↗

Self-attention Networks Localize When QK-eigenspectrum Concentratesstat.ML

Self-attention networks localize when eigenspectrum variance is small.

problem Self-attention mechanisms can lead to rank and entropy collapses, reducing model expressivity and trainability.

method Characterized attention localization using query-key eigenspectrum variance.

result Small eigenspectrum variance prevents both rank and entropy collapses, improving model performance.

self-attention eigenspectrum localization model performance entropy collapse

2024-02-03abs ↗pdf ↗

Training-Free Spectral Fingerprints of Voice Processing in Transformerscs.CL

Transformer models show distinct spectral fingerprints under voice changes.

problem Detecting architectural biases in transformer models.

method Spectral analysis of attention-induced token graphs.

result Clear architectural signatures in model fingerprints correlate with language-specific behavior.

transformers spectral fingerprints voice processing graph signal processing algebraic connectivity

2025-10-21abs ↗pdf ↗