{"total":20,"rows":[{"id":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38,"area":null},{"id":"2602.10825","title":"Flow caching for autoregressive video generation","created":"2026-02-11","cited_by_count":25,"area":null},{"id":"2504.20437","title":"GaLore 2: Large-Scale LLM Pre-Training by Gradient Low-Rank Projection","created":"2025-04-29","cited_by_count":14,"area":null},{"id":"2506.13771","title":"LittleBit: Ultra Low-Bit Quantization via Latent Factorization","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2503.19859","title":"An Overview of Low-Rank Structures in the Training and Adaptation of Large Models","created":"2025-03-25","cited_by_count":9,"area":null},{"id":"2502.01378","title":"CE-LoRA: Computation-Efficient LoRA Fine-Tuning for Language Models","created":"2025-02-03","cited_by_count":6,"area":null},{"id":"2605.18632","title":"Position: Weight Space Should Be a First-Class Generative AI Modality","created":"2026-05-18","cited_by_count":6,"area":null},{"id":"2509.17874","title":"Deep Hierarchical Learning with Nested Subspace Networks for Large Language Models","created":"2025-09-22","cited_by_count":5,"area":null},{"id":"2602.00398","title":"MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2603.05500","title":"POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2509.23472","title":"Memory-Efficient Fine-Tuning via Low-Rank Activation Compression","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2505.01744","title":"Memory-Efficient LLM Training by Various-Grained Low-Rank Projection of Gradients","created":"2025-05-03","cited_by_count":1,"area":null},{"id":"2605.05769","title":"Adaptive Selection of LoRA Components in Privacy-Preserving Federated Learning","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.06316","title":"Pro-KLShampoo: Projected KL-Shampoo with Whitening Recovered by Orthogonalization","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2607.08754","title":"SLORR: Simple and Efficient In-Training Low-Rank Regularization","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2602.06208","title":"Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.08007","title":"From $O(mn)$ to $O(r^2)$: Two-Sided Low-Rank Communication for Adam in Distributed Training with Memory Efficiency","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2609.31983","title":"Understanding the Subspace Stabilization of the Hessian and Gradient Covariance Matrix","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.35257","title":"AIM-ZO: Activation-Informed Subspace Maintenance for Zeroth-Order LLM Fine-Tuning","created":"2026-09-28","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}],"next_cursor":null}