{"total":80,"rows":[{"id":"2405.16406","title":"SpinQuant: LLM quantization with learned rotations","created":"2024-05-26","cited_by_count":471,"area":"inference"},{"id":"2104.07167","title":"Orthogonalizing Convolutional Layers with the Cayley Transform","created":"2021-04-14","cited_by_count":105,"area":null},{"id":"2501.13987","title":"OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting","created":"2025-01-23","cited_by_count":97,"area":null},{"id":"2311.11385","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","created":"2023-11-19","cited_by_count":49,"area":null},{"id":"2102.07432","title":"Fast and accurate optimization on the orthogonal manifold without retraction","created":"2021-02-15","cited_by_count":35,"area":null},{"id":"2307.05432","title":"Self-Supervised Learning with Lie Symmetries for Partial Differential Equations","created":"2023-07-11","cited_by_count":29,"area":null},{"id":"2505.11695","title":"Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization","created":"2025-05-16","cited_by_count":28,"area":null},{"id":"2203.05483","title":"projUNN: efficient method for training deep networks with unitary matrices","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2502.09720","title":"NestQuant: Nested Lattice Quantization for Matrix Products and LLMs","created":"2025-02-13","cited_by_count":23,"area":null},{"id":"2511.04214","title":"Block Rotation is All You Need for MXFP4 Quantization","created":"2025-11-06","cited_by_count":20,"area":null},{"id":"2511.04063","title":"DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2108.05623","title":"Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks","created":"2021-08-12","cited_by_count":16,"area":null},{"id":"2103.00673","title":"Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training","created":"2021-03-01","cited_by_count":15,"area":null},{"id":"2306.01485","title":"Robust low-rank training via approximate orthonormal constraints","created":"2023-06-02","cited_by_count":13,"area":null},{"id":"2305.19059","title":"Geometry-aware training of factorized layers in tensor Tucker format","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2503.01483","title":"KurTail : Kurtosis-based LLM Quantization","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2102.08443","title":"Unsupervised Energy-based Out-of-distribution Detection using Stiefel-Restricted Kernel Machine","created":"2021-02-16","cited_by_count":11,"area":null},{"id":"2205.14173","title":"Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport","created":"2022-05-27","cited_by_count":11,"area":null},{"id":"2305.01777","title":"Representation Learning via Manifold Flattening and Reconstruction","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2503.05431","title":"Quantum-PEFT: Ultra parameter-efficient fine-tuning","created":"2025-03-07","cited_by_count":11,"area":null},{"id":"2402.01344","title":"Monotone, Bi-Lipschitz, and Polyak-Lojasiewicz Networks","created":"2024-02-02","cited_by_count":9,"area":null},{"id":"2410.05499","title":"Unitary convolutions for learning on graphs and groups","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2208.00812","title":"Gradient-descent quantum process tomography by learning Kraus operators","created":"2022-08-01","cited_by_count":6,"area":null},{"id":"2505.08022","title":"Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks","created":"2025-05-12","cited_by_count":6,"area":null},{"id":"2505.23049","title":"DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration","created":"2025-05-29","cited_by_count":6,"area":null},{"id":"2605.12492","title":"Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2105.13921","title":"tensorflow-riemopt: A Library for Optimization on Riemannian Manifolds","created":"2021-05-27","cited_by_count":5,"area":null},{"id":"2205.08385","title":"Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs","created":"2022-05-12","cited_by_count":5,"area":null},{"id":"2403.13351","title":"OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning","created":"2024-03-20","cited_by_count":5,"area":null},{"id":"2503.17513","title":"Improving Quantization with Post-Training Model Expansion","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2503.20505","title":"Riemannian Optimization on Relaxed Indicator Matrix Manifold","created":"2025-03-26","cited_by_count":5,"area":null},{"id":"2602.18308","title":"JPmHC Dynamical Isometry via Orthogonal Hyper-Connections","created":"2026-02-20","cited_by_count":5,"area":null},{"id":"2101.02916","title":"Accelerating Training of Batch Normalization: A Manifold Perspective","created":"2021-01-08","cited_by_count":4,"area":null},{"id":"2604.02309","title":"go-$m$HC: Direct Parameterization of Manifold-Constrained Hyper-Connections via Generalized Orthostochastic Matrices","created":"2026-04-02","cited_by_count":4,"area":null},{"id":"2301.13764","title":"Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification","created":"2023-01-31","cited_by_count":3,"area":null},{"id":"2305.16901","title":"Generalizing Adam to Manifolds for Efficiently Training Transformers","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2402.03883","title":"A Framework for Bilevel Optimization on Riemannian Manifolds","created":"2024-02-06","cited_by_count":3,"area":null},{"id":"2505.12378","title":"Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2602.01105","title":"OLion: Approaching the Hadamard Ideal by Intersecting Spectral and $\\ell_{\\infty}$ Implicit Biases","created":"2026-02-01","cited_by_count":3,"area":null},{"id":"2603.28845","title":"OneComp: One-Line Revolution for Generative AI Model Compression","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2606.01556","title":"TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization","created":"2026-06-01","cited_by_count":3,"area":null},{"id":"2110.03898","title":"Differentiable Programming of Isometric Tensor Networks","created":"2021-10-08","cited_by_count":2,"area":null},{"id":"2311.04207","title":"Deep Hashing via Householder Quantization","created":"2023-11-07","cited_by_count":2,"area":null},{"id":"2505.11881","title":"Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2506.13472","title":"ROSAQ: Rotation-based Saliency-Aware Weight Quantization for Efficiently Compressing Large Language Models","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2602.17681","title":"LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2604.11080","title":"ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2305.17251","title":"Duality in Multi-View Restricted Kernel Machines","created":"2023-05-26","cited_by_count":1,"area":null},{"id":"2310.12986","title":"A survey of manifold learning and its applications for multimedia","created":"2023-09-08","cited_by_count":1,"area":null},{"id":"2311.14658","title":"Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2312.05907","title":"Hypergraph-Guided Disentangled Spectrum Transformer Networks for Near-Infrared Facial Expression Recognition","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2404.14857","title":"Variational Bayesian surrogate modelling with application to robust design optimisation","created":"2024-04-23","cited_by_count":1,"area":null},{"id":"2404.18840","title":"Fast Quantum Process Tomography via Riemannian Gradient Descent","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2511.22316","title":"Outlier Smoothing with Closed-Form Rotations for W4A4 Large Language Model Quantization","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2512.24124","title":"OptRot: Mitigating Weight Outliers via Data-Free Rotations for Post-Training Quantization","created":"2025-12-30","cited_by_count":1,"area":null},{"id":"2601.21626","title":"HeRo-Q: A General Framework for Stable Low Bit Quantization via Hessian Conditioning","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2603.03238","title":"On Geometry Regularization in Autoencoder Reduced-Order Models with Latent Neural ODE Dynamics","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2603.08374","title":"This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.21684","title":"LipsAM: Lipschitz-Continuous Amplitude Modifier for Audio Signal Processing and its Application to Plug-and-Play Dereverberation","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2605.05136","title":"CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2607.20757","title":"GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2106.13272","title":"Generalized One-Class Learning Using Pairs of Complementary Classifiers","created":"2021-06-24","cited_by_count":0,"area":null},{"id":"2210.06546","title":"Auto-Encoding Goodness of Fit","created":"2022-10-12","cited_by_count":0,"area":null},{"id":"2211.13902","title":"TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2309.13531","title":"Robust Principal Component Analysis using Density Power Divergence","created":"2023-09-24","cited_by_count":0,"area":null},{"id":"2404.06218","title":"Quantum Circuit $C^*$-algebra Net","created":"2024-04-09","cited_by_count":0,"area":null},{"id":"2411.16325","title":"Luminance Component Analysis for Exposure Correction","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2502.02185","title":"Generative Kernel Spectral Clustering","created":"2025-02-04","cited_by_count":0,"area":null},{"id":"2502.06268","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2509.17543","title":"Bilateral Distribution Compression: Reducing Both Data Size and Dimensionality","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2602.13759","title":"Discrete Double-Bracket Flows for Isotropic-Noise Invariant Eigendecomposition","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2604.00733","title":"Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and Stiefel QR Retraction","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.10496","title":"CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts","created":"2026-04-12","cited_by_count":0,"area":"moe"},{"id":"2605.26175","title":"InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.02328","title":"Riemannian Gradient Descent for Low-Rank Architectures","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.22117","title":"Projection Pursuit CPCANet for Domain Generalization","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2607.25967","title":"Quasi-SVD: Learning a Lie-constrained matrix factorisation for real-time imaging","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.19363","title":"Directions That Don't Drift: Stiefel Manifold Routing for Transformer Attention","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.21039","title":"Stiefel-AdamW: Geometry-Aware AdamW for Linear Factorization Blocks","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.30885","title":"Retraction-Based Gradient Projection Algorithms on Manifolds","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}