{"total":98,"rows":[{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788,"area":"ssm"},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471,"area":null},{"id":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213,"area":"lr"},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2110.15343","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","created":"2021-10-28","cited_by_count":130,"area":null},{"id":"2310.08744","title":"Circuit Component Reuse Across Tasks in Transformer Language Models","created":"2023-10-12","cited_by_count":108,"area":"mechinterp"},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96,"area":null},{"id":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87,"area":null},{"id":"2202.06258","title":"Flowformer: Linearizing Transformers with Conservation Flows","created":"2022-02-13","cited_by_count":69,"area":null},{"id":"2111.00035","title":"Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\\\"om Method","created":"2021-10-29","cited_by_count":63,"area":null},{"id":"2404.08801","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length","created":"2024-04-12","cited_by_count":46,"area":null},{"id":"2206.05379","title":"A Benchmark for Compositional Visual Reasoning","created":"2022-06-11","cited_by_count":43,"area":"lr"},{"id":"2312.05355","title":"Neither hype nor gloom do DNNs justice","created":"2023-12-08","cited_by_count":40,"area":null},{"id":"2212.08136","title":"Efficient Long Sequence Modeling via State Space Augmented Transformer","created":"2022-12-15","cited_by_count":37,"area":null},{"id":"2310.02980","title":"Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors","created":"2023-10-04","cited_by_count":34,"area":null},{"id":"2501.15061","title":"PolaFormer: Polarity-aware Linear Attention for Vision Transformers","created":"2025-01-25","cited_by_count":32,"area":null},{"id":"2204.04667","title":"Linear Complexity Randomized Self-attention Mechanism","created":"2022-04-10","cited_by_count":31,"area":null},{"id":"2305.19798","title":"Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation","created":"2023-05-31","cited_by_count":29,"area":null},{"id":"2201.11729","title":"Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks","created":"2022-01-27","cited_by_count":27,"area":null},{"id":"2108.02347","title":"FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention","created":"2021-08-05","cited_by_count":26,"area":null},{"id":"2212.00768","title":"Simplifying and Understanding State Space Models with Diagonal Linear RNNs","created":"2022-12-01","cited_by_count":23,"area":null},{"id":"2306.11197","title":"Sparse Modular Activation for Efficient Sequence Modeling","created":"2023-06-19","cited_by_count":20,"area":null},{"id":"2106.02749","title":"Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics","created":"2021-06-04","cited_by_count":19,"area":null},{"id":"2405.06147","title":"State-Free Inference of State-Space Models: The Transfer Function Approach","created":"2024-05-10","cited_by_count":18,"area":null},{"id":"2111.09714","title":"You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling","created":"2021-11-18","cited_by_count":17,"area":null},{"id":"2106.07091","title":"On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification","created":"2021-06-13","cited_by_count":15,"area":null},{"id":"2305.19534","title":"Recasting Self-Attention with Holographic Reduced Representations","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2312.02829","title":"MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition","created":"2023-12-05","cited_by_count":14,"area":"mechinterp"},{"id":"2201.02143","title":"Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks","created":"2022-01-06","cited_by_count":13,"area":null},{"id":"2402.02941","title":"Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey","created":"2024-02-05","cited_by_count":13,"area":null},{"id":"2105.13351","title":"Tracking Without Re-recognition in Humans and Machines","created":"2021-05-27","cited_by_count":12,"area":null},{"id":"2203.07302","title":"Mixed Evidence for Gestalt Grouping in Deep Neural Networks","created":"2022-03-14","cited_by_count":12,"area":null},{"id":"2405.02670","title":"From Generalization Analysis to Optimization Designs for State Space Models","created":"2024-05-04","cited_by_count":11,"area":null},{"id":"2411.07538","title":"Unraveling the Gradient Descent Dynamics of Transformers","created":"2024-11-12","cited_by_count":11,"area":null},{"id":"2102.01955","title":"Predictive coding feedback results in perceived illusory contours in a recurrent neural network","created":"2021-02-03","cited_by_count":10,"area":null},{"id":"2411.02824","title":"Layer-Adaptive State Pruning for Deep State Space Models","created":"2024-11-05","cited_by_count":10,"area":null},{"id":"2504.16940","title":"Better artificial intelligence does not mean better models of biology","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2110.13492","title":"TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining","created":"2021-10-26","cited_by_count":8,"area":null},{"id":"2405.02842","title":"IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs","created":"2024-05-05","cited_by_count":8,"area":null},{"id":"2406.13770","title":"Elliptical Attention","created":"2024-06-19","cited_by_count":7,"area":null},{"id":"2104.03589","title":"PQA: Perceptual Question Answering","created":"2021-04-08","cited_by_count":6,"area":null},{"id":"2203.12276","title":"ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention","created":"2022-03-23","cited_by_count":6,"area":null},{"id":"2204.10670","title":"Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-Attention","created":"2022-04-22","cited_by_count":6,"area":null},{"id":"2302.08374","title":"Efficiency 360: Efficient Vision Transformers","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2306.11582","title":"Computing a human-like reaction time metric from stable recurrent vision models","created":"2023-06-20","cited_by_count":6,"area":null},{"id":"2311.06964","title":"Adaptive recurrent vision performs zero-shot computation scaling to unseen difficulty levels","created":"2023-11-12","cited_by_count":6,"area":null},{"id":"2403.17978","title":"Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection","created":"2024-03-23","cited_by_count":6,"area":null},{"id":"2405.17534","title":"SMR: State Memory Replay for Long Sequence Modeling","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2504.05253","title":"Contour Integration Underlies Human-Like Vision","created":"2025-04-07","cited_by_count":6,"area":null},{"id":"2112.05359","title":"Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences","created":"2021-12-10","cited_by_count":5,"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":"2405.15310","title":"Spectraformer: A Unified Random Feature Framework for Transformer","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2406.08128","title":"Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2210.15541","title":"Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2211.16368","title":"DBA: Efficient Transformer with Dynamic Bilinear Low-Rank Attention","created":"2022-11-24","cited_by_count":4,"area":null},{"id":"2302.05400","title":"DNArch: Learning Convolutional Neural Architectures by Backpropagation","created":"2023-02-10","cited_by_count":4,"area":null},{"id":"2309.16515","title":"Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping","created":"2023-09-28","cited_by_count":4,"area":null},{"id":"2406.13781","title":"A Primal-Dual Framework for Transformers and Neural Networks","created":"2024-06-19","cited_by_count":4,"area":null},{"id":"2505.08516","title":"Learning Advanced Self-Attention for Linear Transformers in the Singular Value Domain","created":"2025-05-13","cited_by_count":4,"area":null},{"id":"2104.05500","title":"Updater-Extractor Architecture for Inductive World State Representations","created":"2021-04-12","cited_by_count":3,"area":null},{"id":"2110.02772","title":"The Challenge of Appearance-Free Object Tracking with Feedforward Neural Networks","created":"2021-09-30","cited_by_count":3,"area":null},{"id":"2301.07807","title":"Measuring uncertainty in human visual segmentation","created":"2023-01-18","cited_by_count":3,"area":null},{"id":"2410.02094","title":"Tracking objects that change in appearance with phase synchrony","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2507.00493","title":"Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models","created":"2025-07-01","cited_by_count":3,"area":null},{"id":"2106.04225","title":"On the role of feedback in visual processing: a predictive coding perspective","created":"2021-06-08","cited_by_count":2,"area":null},{"id":"2108.04962","title":"Adaptive Multi-Resolution Attention with Linear Complexity","created":"2021-08-10","cited_by_count":2,"area":null},{"id":"2109.08184","title":"Sparse Factorization of Large Square Matrices","created":"2021-09-16","cited_by_count":2,"area":null},{"id":"2404.00130","title":"FISBe: A real-world benchmark dataset for instance segmentation of long-range thin filamentous structures","created":"2024-03-29","cited_by_count":2,"area":null},{"id":"2406.00894","title":"Pretrained Hybrids with MAD Skills","created":"2024-06-02","cited_by_count":2,"area":null},{"id":"2406.03478","title":"Convolutional Neural Networks and Vision Transformers for Fashion MNIST Classification: A Literature Review","created":"2024-06-05","cited_by_count":2,"area":null},{"id":"2410.10914","title":"Towards Better Multi-head Attention via Channel-wise Sample Permutation","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2509.17186","title":"Dendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modeling","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2509.20503","title":"Myosotis: structured computation for attention like layer","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2510.22951","title":"Hankel Singular Value Regularization for Highly Compressible State Space Models","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2601.22488","title":"Elastic Spectral State Space Models for Train-Once Budgeted Inference","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2602.10195","title":"Versor: A Geometric Sequence Architecture","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2112.04162","title":"Symmetry Perception by Deep Networks: Inadequacy of Feed-Forward Architectures and Improvements with Recurrent Connections","created":"2021-12-08","cited_by_count":1,"area":null},{"id":"2303.00077","title":"Beyond the limitations of any imaginable mechanism: large language models and psycholinguistics","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2310.17683","title":"Sliceformer: Make Multi-head Attention as Simple as Sorting in Discriminative Tasks","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2602.00534","title":"AIRE-Prune: Asymptotic Impulse-Response Energy for State Pruning in State Space Models","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2604.09942","title":"I Walk the Line: Examining the Role of Gestalt Continuity in Object Binding for Vision Transformers","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2605.21070","title":"Towards Understanding Self-Pretraining for Sequence Classification","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2201.10664","title":"Do Neural Networks for Segmentation Understand Insideness?","created":"2022-01-25","cited_by_count":0,"area":null},{"id":"2301.06216","title":"CogReact: A Reinforced Framework to Model Human Cognitive Reaction Modulated by Dynamic Intervention","created":"2023-01-15","cited_by_count":0,"area":null},{"id":"2305.03835","title":"Spatiotemporal Transformer for Stock Movement Prediction","created":"2023-05-05","cited_by_count":0,"area":null},{"id":"2309.13181","title":"Diagnosing and exploiting the computational demands of videos games for deep reinforcement learning","created":"2023-09-22","cited_by_count":0,"area":null},{"id":"2310.14206","title":"Manifold-Preserving Transformers are Effective for Short-Long Range Encoding","created":"2023-10-22","cited_by_count":0,"area":null},{"id":"2311.12819","title":"Fixing the problems of deep neural networks will require better training data and learning algorithms","created":"2023-09-26","cited_by_count":0,"area":null},{"id":"2311.18735","title":"Dimension Mixer: Group Mixing of Input Dimensions for Efficient Function Approximation","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2402.04239","title":"CAST: Clustering Self-Attention using Surrogate Tokens for Efficient Transformers","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2402.15290","title":"Efficient State Space Model via Fast Tensor Convolution and Block Diagonalization","created":"2024-02-23","cited_by_count":0,"area":"ssm"},{"id":"2408.05391","title":"SAMSA: Efficient Transformer for Many Data Modalities","created":"2024-08-10","cited_by_count":0,"area":null},{"id":"2408.05822","title":"Sampling Foundational Transformer: A Theoretical Perspective","created":"2024-08-11","cited_by_count":0,"area":null},{"id":"2501.12896","title":"Irrational Complex Rotations Empower Low-bit Optimizers","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2502.00585","title":"Converting Transformers into DGNNs Form","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2509.23677","title":"MSD-KMamba: Bidirectional Spatial-Aware Multi-Modal 3D Brain Segmentation via Multi-scale Self-Distilled Fusion Strategy","created":"2025-09-28","cited_by_count":0,"area":"distill"},{"id":"2605.15672","title":"VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following","created":"2026-05-15","cited_by_count":0,"area":"mllm"},{"id":"2608.09468","title":"MixFormer: Linear Transformer with Mixture of Memory Experts","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}