{"total":74,"rows":[{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460,"area":null},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194,"area":"lr"},{"id":"2303.15647","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","created":"2023-03-28","cited_by_count":173,"area":null},{"id":"2106.02795","title":"Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding","created":"2021-06-05","cited_by_count":93,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2203.16329","title":"Parameter-efficient Model Adaptation for Vision Transformers","created":"2022-03-29","cited_by_count":81,"area":null},{"id":"2211.13609","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","created":"2022-11-24","cited_by_count":76,"area":null},{"id":"2405.15179","title":"VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks","created":"2024-05-24","cited_by_count":52,"area":null},{"id":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25,"area":null},{"id":"2403.06082","title":"FrameQuant: Flexible Low-Bit Quantization for Transformers","created":"2024-03-10","cited_by_count":18,"area":null},{"id":"2102.04394","title":"Learning with Density Matrices and Random Features","created":"2021-02-08","cited_by_count":17,"area":null},{"id":"2109.09703","title":"Learning to Forecast Dynamical Systems from Streaming Data","created":"2021-09-20","cited_by_count":17,"area":null},{"id":"2403.19928","title":"DiJiang: Efficient Large Language Models through Compact Kernelization","created":"2024-03-29","cited_by_count":16,"area":null},{"id":"2402.08823","title":"Random Representations Outperform Online Continually Learned Representations","created":"2024-02-13","cited_by_count":11,"area":null},{"id":"2204.05424","title":"A Call for Clarity in Beam Search: How It Works and When It Stops","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2207.06856","title":"Low-Precision Arithmetic for Fast Gaussian Processes","created":"2022-07-14","cited_by_count":10,"area":null},{"id":"2212.04604","title":"Localized Contrastive Learning on Graphs","created":"2022-12-08","cited_by_count":10,"area":null},{"id":"2402.03994","title":"Efficient Sketches for Training Data Attribution and Studying the Loss Landscape","created":"2024-02-06","cited_by_count":10,"area":null},{"id":"2403.11887","title":"SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modules","created":"2024-03-18","cited_by_count":10,"area":"diffusion"},{"id":"2311.12214","title":"Random Fourier Signature Features","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2203.13556","title":"Deformable Butterfly: A Highly Structured and Sparse Linear Transform","created":"2022-03-25","cited_by_count":8,"area":null},{"id":"2211.03393","title":"Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies for Robot Manipulation","created":"2022-11-07","cited_by_count":8,"area":"offlinerl"},{"id":"2403.07221","title":"LookupFFN: Making Transformers Compute-lite for CPU inference","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2605.13810","title":"Provable Quantization with Randomized Hadamard Transform","created":"2026-05-13","cited_by_count":8,"area":"inference"},{"id":"2407.00584","title":"Hyperparameter Optimization for Randomized Algorithms: A Case Study on Random Features","created":"2024-06-30","cited_by_count":7,"area":null},{"id":"2506.00799","title":"Uni-LoRA: One Vector is All You Need","created":"2025-06-01","cited_by_count":7,"area":null},{"id":"2202.03474","title":"Random Gegenbauer Features for Scalable Kernel Methods","created":"2022-02-07","cited_by_count":6,"area":null},{"id":"2101.11751","title":"Faster Kernel Interpolation for Gaussian Processes","created":"2021-01-28","cited_by_count":5,"area":null},{"id":"2312.09969","title":"Nearest Neighbor Sampling for Covariate Shift Adaptation","created":"2023-12-15","cited_by_count":5,"area":null},{"id":"2601.08828","title":"Motion Attribution for Video Generation","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2109.11928","title":"Is the Number of Trainable Parameters All That Actually Matters?","created":"2021-09-24","cited_by_count":3,"area":null},{"id":"2111.10461","title":"Gaussian Process Inference Using Mini-batch Stochastic Gradient Descent: Convergence Guarantees and Empirical Benefits","created":"2021-11-19","cited_by_count":3,"area":null},{"id":"2112.09631","title":"Sublinear Time Approximation of Text Similarity Matrices","created":"2021-12-17","cited_by_count":3,"area":null},{"id":"2503.14836","title":"On the Robustness Tradeoff in Fine-Tuning","created":"2025-03-19","cited_by_count":3,"area":null},{"id":"2506.01597","title":"Policy Newton Algorithm in Reproducing Kernel Hilbert Space","created":"2025-06-02","cited_by_count":3,"area":"deeprl"},{"id":"2104.00669","title":"Deep Multi-Resolution Dictionary Learning for Histopathology Image Analysis","created":"2021-04-01","cited_by_count":2,"area":null},{"id":"2208.00789","title":"Self-supervised learning with rotation-invariant kernels","created":"2022-07-28","cited_by_count":2,"area":null},{"id":"2405.16541","title":"Variance-Reducing Couplings for Random Features","created":"2024-05-26","cited_by_count":2,"area":null},{"id":"2603.28678","title":"Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2604.20077","title":"Analysis of Nystrom method with sequential ridge leverage scores","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2604.23418","title":"Approximating Uniform Random Rotations by Two-Stage Structured Hadamard Rotations in High Dimensions","created":"2026-04-25","cited_by_count":2,"area":null},{"id":"2112.03108","title":"Flood Inflow Forecast Using L2-norm Ensemble Weighting Sea Surface Feature","created":"2021-12-06","cited_by_count":1,"area":null},{"id":"2210.13311","title":"Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Delta Tuning","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2302.11174","title":"Error Estimation for Random Fourier Features","created":"2023-02-22","cited_by_count":1,"area":null},{"id":"2310.07370","title":"Orthogonal Random Features: Explicit Forms and Sharp Inequalities","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2311.04673","title":"Compressive Recovery of Sparse Precision Matrices","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2502.15575","title":"Feature maps for the Laplacian kernel and its generalizations","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2509.20605","title":"Function Spaces Without Kernels: Learning Compact Hilbert Space Representations","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2510.03727","title":"Bridging the Gap Between Multimodal Foundation Models and World Models","created":"2025-10-04","cited_by_count":1,"area":"wm"},{"id":"2601.04159","title":"ToTMNet: FFT-Accelerated Toeplitz Temporal Mixing Network for Lightweight Remote Photoplethysmography","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2605.01263","title":"New Bounds for Kernel Sums via Fast Spherical Embeddings","created":"2026-05-02","cited_by_count":1,"area":null},{"id":"2605.14841","title":"GPart: End-to-End Isometric Fine-Tuning via Global Parameter Partitioning","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2110.15440","title":"HD-cos Networks: Efficient Neural Architectures for Secure Multi-Party Computation","created":"2021-10-28","cited_by_count":0,"area":null},{"id":"2112.09893","title":"Revisiting Memory Efficient Kernel Approximation: An Indefinite Learning Perspective","created":"2021-12-18","cited_by_count":0,"area":null},{"id":"2301.09525","title":"DeepFEL: Deep Fastfood Ensemble Learning for Histopathology Image Analysis","created":"2023-01-23","cited_by_count":0,"area":null},{"id":"2305.10445","title":"Memorization for Good: Encryption with Autoregressive Language Models","created":"2023-05-15","cited_by_count":0,"area":null},{"id":"2311.08125","title":"Lite it fly: An All-Deformable-Butterfly Network","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2402.04022","title":"Beyond State Space Representation: A General Theory for Kernel Packets","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2406.05999","title":"fSEAD: a Composable FPGA-based Streaming Ensemble Anomaly Detection Library","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2411.03375","title":"Kernel Approximation using Analog In-Memory Computing","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2503.06041","title":"Randomized Quasi-Monte Carlo Features for Kernel Approximation","created":"2025-03-08","cited_by_count":0,"area":null},{"id":"2503.17353","title":"NdLinear: Preserving Multi-Dimensional Structure for Parameter-Efficient Neural Networks","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2506.16418","title":"Efficient Transformations in Deep Learning Convolutional Neural Networks","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2507.13772","title":"Feature Engineering is Not Dead: Reviving Classical Machine Learning with Entropy, HOG, and LBP Feature Fusion for Image Classification","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2508.17412","title":"A Ridge Too Far: Correcting Over-Shrinkage via Negative Regularization","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2602.13098","title":"Barron-Wiener-Laguerre models","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2603.04127","title":"Data-Aware Random Feature Kernel for Transformers","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.08343","title":"Rethinking Attention Output Projection: Structured Hadamard Transforms for Efficient Transformers","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2606.11255","title":"Bernstein-Schur Kernels: Random Features by Sketched Modulation and Radial Randomization","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2608.02378","title":"Gecko: Fast Private Inference via Secure Public Encoder Offloading","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.12503","title":"Fast Length-Squared Sampling for Positive-Semidefinite Matrices","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.35177","title":"Subgroup Rank-1 Lattice for Practical High-dimensional Black-box Integral Approximation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.14751","title":"Random Fourier Features in Near-Linear Time","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.16289","title":"Fast Quantized Johnson$-$Lindenstrauss Transforms","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}