{"total":35,"rows":[{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347,"area":null},{"id":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2105.00335","title":"Audio Transformers","created":"2021-05-01","cited_by_count":41,"area":null},{"id":"2412.17739","title":"Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization","created":"2024-12-23","cited_by_count":39,"area":null},{"id":"2212.10711","title":"Task Ambiguity in Humans and Language Models","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2203.11370","title":"Language modeling via stochastic processes","created":"2022-03-21","cited_by_count":18,"area":null},{"id":"2302.01925","title":"Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers","created":"2023-02-03","cited_by_count":10,"area":null},{"id":"2107.05984","title":"Deep Autoregressive Models with Spectral Attention","created":"2021-07-13","cited_by_count":9,"area":null},{"id":"2212.08378","title":"Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning","created":"2022-12-16","cited_by_count":9,"area":null},{"id":"2406.10254","title":"Towards Signal Processing In Large Language Models","created":"2024-06-10","cited_by_count":7,"area":null},{"id":"2408.08073","title":"Extracting Sentence Embeddings from Pretrained Transformer Models","created":"2024-08-15","cited_by_count":7,"area":null},{"id":"2505.17101","title":"A quantitative analysis of semantic information in deep representations of text and images","created":"2025-05-21","cited_by_count":7,"area":null},{"id":"2601.04765","title":"Differential syntactic and semantic encoding in LLMs","created":"2026-01-08","cited_by_count":7,"area":null},{"id":"2209.12816","title":"Fast-FNet: Accelerating Transformer Encoder Models via Efficient Fourier Layers","created":"2022-09-26","cited_by_count":5,"area":null},{"id":"2508.13768","title":"MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral Alignment","created":"2025-08-19","cited_by_count":5,"area":null},{"id":"2605.21842","title":"Energy-Gated Attention: Spectral Salience as an Inductive Bias for Transformer Attention","created":"2026-05-21","cited_by_count":5,"area":null},{"id":"2605.26355","title":"Energy-Gated Attention and Wavelet Positional Encoding: Complementary Inductive Biases for Transformer Attention","created":"2026-05-25","cited_by_count":4,"area":null},{"id":"2606.01258","title":"Beyond Sinusoids: A Morlet Wavelet Framework for Transformer Positional Encoding","created":"2026-05-31","cited_by_count":3,"area":null},{"id":"2109.13090","title":"Oscillatory Fourier Neural Network: A Compact and Efficient Architecture for Sequential Processing","created":"2021-09-14","cited_by_count":2,"area":null},{"id":"2511.06285","title":"Exploiting Inter-Session Information with Frequency-enhanced Dual-Path Networks for Sequential Recommendation","created":"2025-11-09","cited_by_count":2,"area":null},{"id":"2512.23824","title":"MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2210.11860","title":"Spectral Probing","created":"2022-10-21","cited_by_count":1,"area":null},{"id":"2307.00461","title":"Conformer LLMs -- Convolution Augmented Large Language Models","created":"2023-07-02","cited_by_count":1,"area":null},{"id":"2407.11439","title":"Repurformer: Transformers for Repurposing-Aware Molecule Generation","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2409.12924","title":"Wavelet GPT: Wavelet Inspired Large Language Models","created":"2024-09-04","cited_by_count":1,"area":null},{"id":"2506.16550","title":"A Free Probabilistic Framework for Analyzing the Transformer-based Language Models","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2607.07478","title":"FourierQK: Spectral Preprocessing of Query-Key Projections Improves Transformer Attention","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2310.11940","title":"Interpretable Spectral Variational AutoEncoder (ISVAE) for time series clustering","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2512.22378","title":"Towards Efficient Post-Training via Fourier-Driven Adapter Architectures","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2603.03782","title":"DisenReason: Behavior Disentanglement and Latent Reasoning for Shared-Account Sequential Recommendation","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2604.17986","title":"Latent Fourier Transform","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2606.08191","title":"Frequency-Domain Latent Attention Gating for Cross-Domain Token Aggregation","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2608.20804","title":"Denoising the Future: Context-Aware Spectral Diffusion for Temporal Knowledge Graph Extrapolation","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.00831","title":"FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.35664","title":"MS-GLA: Multi-Scale Gated Linear Attention for Addressing Representational Bottlenecks via Multi-Temporal Resolution","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}