{"total":59,"rows":[{"id":"2410.17770","title":"Small Singular Values Matter: A Random Matrix Analysis of Transformer Models","created":"2024-10-23","cited_by_count":21,"area":null},{"id":"2410.09615","title":"SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression","created":"2024-10-12","cited_by_count":12,"area":null},{"id":"2501.15674","title":"TensorLLM: Tensorising Multi-Head Attention for Enhanced Reasoning and Compression in LLMs","created":"2025-01-26","cited_by_count":12,"area":"lr"},{"id":"2505.01658","title":"A Survey on Inference Engines for Large Language Models: Perspectives on Optimization and Efficiency","created":"2025-05-03","cited_by_count":12,"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":"2510.24273","title":"SALS: Sparse Attention in Latent Space for KV cache Compression","created":"2025-10-28","cited_by_count":11,"area":"inference"},{"id":"2602.00135","title":"LLaVA-FA: Learning Fourier Approximation for Compressing Large Multimodal Models","created":"2026-01-28","cited_by_count":11,"area":"mllm"},{"id":"2602.17835","title":"Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning","created":"2026-02-19","cited_by_count":10,"area":null},{"id":"2505.12942","title":"A3 : an Analytical Low-Rank Approximation Framework for Attention","created":"2025-05-19","cited_by_count":8,"area":"inference"},{"id":"2509.25622","title":"Layer-wise dynamic rank for compressing large language models","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2410.21271","title":"EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation","created":"2024-10-28","cited_by_count":7,"area":null},{"id":"2505.18413","title":"LatentLLM: Attention-Aware Joint Tensor Compression","created":"2025-05-23","cited_by_count":7,"area":"mllm"},{"id":"2505.20112","title":"ERC-SVD: Error-Controlled SVD for Large Language Model Compression","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2406.17261","title":"TRAWL: Tensor Reduced and Approximated Weights for Large Language Models","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2501.15014","title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2501.16385","title":"FBQuant: FeedBack Quantization for Large Language Models","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2504.13237","title":"ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2501.19090","title":"Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models","created":"2025-01-31","cited_by_count":4,"area":null},{"id":"2505.11076","title":"Addition is almost all you need: Compressing large language models with double binary factorization","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2505.18451","title":"$\\mu$-MoE: Test-Time Pruning as Micro-Grained Mixture-of-Experts","created":"2025-05-24","cited_by_count":3,"area":"moe"},{"id":"2506.02818","title":"ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2507.17417","title":"A Comprehensive Evaluation on Quantization Techniques for Large Language Models","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2509.23410","title":"PATCH: Learnable Tile-level Hybrid Sparsity for LLMs","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2512.17073","title":"Bandwidth-Efficient Adaptive Mixture-of-Experts via Low-Rank Compensation","created":"2025-12-18","cited_by_count":3,"area":"moe"},{"id":"2601.19675","title":"LoPRo: Enhancing Low-Rank Quantization via Permuted Block-Wise Rotation","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2603.01376","title":"3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2412.07902","title":"Low-Rank Correction for Quantized LLMs","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2505.14871","title":"Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2601.05684","title":"FLRQ: Faster LLM Quantization with Flexible Low-Rank Matrix Sketching","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2504.14569","title":"NoWag: A Unified Framework for Shape Preserving Compression of Large Language Models","created":"2025-04-20","cited_by_count":1,"area":null},{"id":"2505.21077","title":"Efficient Large Language Model Inference with Neural Block Linearization","created":"2025-05-27","cited_by_count":1,"area":"inference"},{"id":"2506.02077","title":"Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition","created":"2025-06-02","cited_by_count":1,"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":"2510.13832","title":"Entropy Meets Importance: A Unified Head Importance-Entropy Score for Stable and Efficient Transformer Pruning","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2602.02001","title":"Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.09509","title":"Beyond Student: An Asymmetric Network for Neural Network Inheritance","created":"2026-02-10","cited_by_count":1,"area":"distill"},{"id":"2603.08185","title":"SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.19296","title":"TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference On The Fly","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.16940","title":"D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2606.01412","title":"GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2607.01876","title":"SAB-LVLM: Significance-Aware Binarization for Large Vision-Language Models","created":"2026-07-02","cited_by_count":1,"area":"mllm"},{"id":"2407.15508","title":"Compensate Quantization Errors+: Quantized Models Are Inquisitive Learners","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2503.20798","title":"Payload-Aware Intrusion Detection with CMAE and Large Language Models","created":"2025-03-23","cited_by_count":0,"area":null},{"id":"2503.22074","title":"Penrose Tiled Low-Rank Compression and Section-Wise Q&A Fine-Tuning: A General Framework for Domain-Specific Large Language Model Adaptation","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2504.11995","title":"A Review of YOLOv12: Attention-Based Enhancements vs. Previous Versions","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2506.02210","title":"Exchangeability in Neural Network and its Application to Dynamic Pruning","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2510.01718","title":"Accelerating Attention with Basis Decomposition","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2510.04044","title":"Quantization Range Estimation for Convolutional Neural Networks","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2510.13147","title":"D-com: Accelerating Iterative Processing to Enable Low-rank Decomposition of Activations","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2510.18650","title":"Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2510.26446","title":"1+1>2: A Synergistic Sparse and Low-Rank Compression Method for Large Language Models","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2601.09865","title":"Advancing Model Refinement: Muon-Optimized Distillation and Quantization for LLM Deployment","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2604.02659","title":"Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2606.00494","title":"ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.07098","title":"SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.08565","title":"EinSort: Sorting is All We Need for Tensorizing LLM","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2608.14149","title":"QuaSAR: Quantization Compensation via Stable Activation-Aware Rank Truncation","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.21137","title":"A Multi-Engine Dataflow for MoE Decoding on Scratchpad-Based Tensor Accelerators","created":"2026-09-17","cited_by_count":0,"area":"moe"},{"id":"2610.09916","title":"NeuralZip: Reusable Setup for Fast Lossless Compression","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}