{"list":"other","total":52,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"2405.16406","title":"SpinQuant: LLM quantization with learned rotations","created":"2024-05-26","cited_by_count":471},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"2303.10512","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","created":"2023-03-18","cited_by_count":357},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269},{"id":"2303.10420","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","created":"2023-03-18","cited_by_count":246},{"id":"2307.05695","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","created":"2023-07-11","cited_by_count":204},{"id":"2301.11235","title":"Handbook of Convergence Theorems for (Stochastic) Gradient Methods","created":"2023-01-26","cited_by_count":163},{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137},{"id":"2402.03293","title":"Flora: Low-Rank Adapters Are Secretly Gradient Compressors","created":"2024-02-05","cited_by_count":108},{"id":"2403.17919","title":"LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning","created":"2024-03-26","cited_by_count":89},{"id":"2407.18242","title":"LoRA-Pro: Are Low-Rank Adapters Properly Optimized?","created":"2024-07-25","cited_by_count":77},{"id":"2405.18137","title":"Exploiting LLM Quantization","created":"2024-05-28","cited_by_count":65},{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54},{"id":"2406.02214","title":"SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining","created":"2024-06-04","cited_by_count":45},{"id":"2410.01623","title":"Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?","created":"2024-10-02","cited_by_count":43},{"id":"2408.12857","title":"Memory-Efficient LLM Training with Online Subspace Descent","created":"2024-08-23","cited_by_count":39},{"id":"2407.08296","title":"Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients","created":"2024-07-11","cited_by_count":38},{"id":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38},{"id":"2410.11289","title":"Subspace Optimization for Large Language Models with Convergence Guarantees","created":"2024-10-15","cited_by_count":34},{"id":"2209.13569","title":"Exploring Low Rank Training of Deep Neural Networks","created":"2022-09-27","cited_by_count":30},{"id":"2406.06248","title":"Compute Better Spent: Replacing Dense Layers with Structured Matrices","created":"2024-06-10","cited_by_count":28},{"id":"2501.06842","title":"SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training","created":"2025-01-12","cited_by_count":28},{"id":"2502.10940","title":"CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation","created":"2025-02-16","cited_by_count":28},{"id":"2405.17991","title":"VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections","created":"2024-05-28","cited_by_count":18},{"id":"2405.18144","title":"4-bit Shampoo for Memory-Efficient Network Training","created":"2024-05-28","cited_by_count":18},{"id":"2406.17660","title":"Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients","created":"2024-06-25","cited_by_count":18},{"id":"2502.01586","title":"SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training","created":"2025-02-03","cited_by_count":16},{"id":"2405.14377","title":"CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization","created":"2024-05-23","cited_by_count":15},{"id":"2410.15352","title":"CompAct: Compressed Activations for Memory-Efficient LLM Training","created":"2024-10-20","cited_by_count":15},{"id":"2410.20650","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","created":"2024-10-28","cited_by_count":14},{"id":"2504.20437","title":"GaLore 2: Large-Scale LLM Pre-Training by Gradient Low-Rank Projection","created":"2025-04-29","cited_by_count":14},{"id":"2406.09958","title":"Memory-Efficient Optimization with Factorized Hamiltonian Descent","created":"2024-06-14","cited_by_count":11},{"id":"2407.11722","title":"Exploring Quantization for Efficient Pre-Training of Transformer Language Models","created":"2024-07-16","cited_by_count":10},{"id":"2411.07837","title":"FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training","created":"2024-11-12","cited_by_count":10},{"id":"2406.17296","title":"BlockLLM: Memory-Efficient Adaptation of LLMs by Selecting and Optimizing the Right Coordinate Blocks","created":"2024-06-25","cited_by_count":9},{"id":"2412.00071","title":"COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection","created":"2024-11-26","cited_by_count":8},{"id":"2412.19820","title":"GaLore$+$: Boosting Low-Rank Adaptation for LLMs with Cross-Head Projection","created":"2024-12-15","cited_by_count":8},{"id":"2502.05790","title":"Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining","created":"2025-02-09","cited_by_count":7},{"id":"2411.02063","title":"Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention","created":"2024-11-04","cited_by_count":6},{"id":"2501.02379","title":"TensorGRaD: Tensor Gradient Robust Decomposition for Memory-Efficient Neural Operator Training","created":"2025-01-04","cited_by_count":6},{"id":"2502.17055","title":"GradientStabilizer:Fix the Norm, Not the Gradient","created":"2025-02-24","cited_by_count":6},{"id":"2502.09003","title":"RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models","created":"2025-02-13","cited_by_count":5},{"id":"2410.16029","title":"Natural GaLore: Accelerating GaLore for memory-efficient LLM Training and Fine-tuning","created":"2024-10-21","cited_by_count":4}],"next_cursor":null}