{"total":24,"rows":[{"id":"2410.23179","title":"Does equivariance matter at scale?","created":"2024-10-30","cited_by_count":52,"area":null},{"id":"2506.04761","title":"Log-Linear Attention","created":"2025-06-05","cited_by_count":40,"area":null},{"id":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29,"area":null},{"id":"2602.24281","title":"Memory Caching: RNNs with Growing Memory","created":"2026-02-27","cited_by_count":15,"area":null},{"id":"2506.12383","title":"Scaling Probabilistic Circuits via Monarch Matrices","created":"2025-06-14","cited_by_count":9,"area":null},{"id":"2503.18368","title":"MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning","created":"2025-03-24","cited_by_count":6,"area":null},{"id":"2602.12429","title":"Stabilizing Native Low-Rank LLM Pretraining","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2406.17740","title":"Structured Unrestricted-Rank Matrices for Parameter Efficient Fine-tuning","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2505.22922","title":"Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2410.02147","title":"Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement","created":"2024-10-03","cited_by_count":4,"area":null},{"id":"2410.03040","title":"Geometry is All You Need: A Unified Taxonomy of Matrix and Tensor Factorization for Compression of Generative Language Models","created":"2024-10-03","cited_by_count":4,"area":null},{"id":"2411.02001","title":"Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation","created":"2024-11-04","cited_by_count":4,"area":null},{"id":"2412.20891","title":"DoTA: Weight-Decomposed Tensor Adaptation for Large Language Models","created":"2024-12-30","cited_by_count":3,"area":null},{"id":"2507.09428","title":"On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2509.15113","title":"Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2505.24241","title":"Advantageous Parameter Expansion Training Makes Better Large Language Models","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2506.13514","title":"TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2509.07963","title":"Customizing the Inductive Biases of Softmax Attention using Structured Matrices","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2605.00448","title":"Learning from Compressed CT: Feature Attention Style Transfer and Structured Factorized Projections for Resource-Efficient Medical Image Analysis","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.22869","title":"FuRA: Full-Rank Parameter-Efficient Fine-Tuning with Spectral Preconditioning","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.25344","title":"A Hamiltonian-Inspired Local-Operator Ansatz for Slimming Large Language Models","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2609.32814","title":"Change the Product, Keep the Parameters: Associative Algebra Layers for Transformers","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.02882","title":"DyRA: Dynamic Residual Approximation for Efficient Matrix Multiplication in DNNs","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.13568","title":"Rationally Linearized MLPs","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}