{"total":168,"rows":[{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167,"area":null},{"id":"2503.12340","title":"SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression","created":"2025-03-16","cited_by_count":67,"area":null},{"id":"2408.09632","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","created":"2024-08-19","cited_by_count":48,"area":null},{"id":"2406.09519","title":"Talking Heads: Understanding Inter-layer Communication in Transformer Language Models","created":"2024-06-13","cited_by_count":41,"area":null},{"id":"2410.03765","title":"Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression","created":"2024-10-02","cited_by_count":35,"area":null},{"id":"2407.11239","title":"From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications","created":"2024-07-15","cited_by_count":25,"area":null},{"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":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2501.15296","title":"You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning","created":"2025-01-25","cited_by_count":17,"area":null},{"id":"2502.00896","title":"LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation","created":"2025-02-02","cited_by_count":17,"area":null},{"id":"2503.02659","title":"Put the Space of LoRA Initialization to the Extreme to Preserve Pre-trained Knowledge","created":"2025-03-04","cited_by_count":16,"area":null},{"id":"2410.17711","title":"Beware of Calibration Data for Pruning Large Language Models","created":"2024-10-23","cited_by_count":15,"area":null},{"id":"2407.10886","title":"SLIP: Securing LLMs IP Using Weights Decomposition","created":"2024-07-15","cited_by_count":14,"area":null},{"id":"2505.02819","title":"ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization","created":"2025-05-05","cited_by_count":13,"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":"2508.02668","title":"LOST: Low-rank and Sparse Pre-training for Large Language Models","created":"2025-08-04","cited_by_count":10,"area":null},{"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":"2508.01506","title":"FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models","created":"2025-08-02","cited_by_count":9,"area":null},{"id":"2411.07762","title":"ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization","created":"2024-11-12","cited_by_count":8,"area":null},{"id":"2412.06071","title":"KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models","created":"2024-12-08","cited_by_count":8,"area":null},{"id":"2505.17974","title":"Generalized Fisher-Weighted SVD: Scalable Kronecker-Factored Fisher Approximation for Compressing Large Language Models","created":"2025-05-23","cited_by_count":8,"area":null},{"id":"2505.18502","title":"Knowledge Fusion of Large Language Models Via Modular SkillPacks","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2506.20353","title":"DipSVD: Dual-importance Protected SVD for Efficient LLM Compression","created":"2025-06-25","cited_by_count":8,"area":null},{"id":"2509.25622","title":"Layer-wise dynamic rank for compressing large language models","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2602.02848","title":"Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression","created":"2026-02-02","cited_by_count":8,"area":null},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"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":"2505.20112","title":"ERC-SVD: Error-Controlled SVD for Large Language Model Compression","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2602.20208","title":"Model Merging in the Essential Subspace","created":"2026-02-23","cited_by_count":7,"area":null},{"id":"2604.02119","title":"AA-SVD : Anchored and Adaptive SVD for Large Language Model Compression","created":"2026-04-02","cited_by_count":7,"area":null},{"id":"2506.20194","title":"DuoGPT: Training-free Dual Sparsity through Activation-aware Pruning in LLMs","created":"2025-06-25","cited_by_count":6,"area":null},{"id":"2509.22075","title":"CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2512.03383","title":"UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2501.00339","title":"GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression","created":"2024-12-31","cited_by_count":5,"area":null},{"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,"area":null},{"id":"2502.13794","title":"LESA: Learnable LLM Layer Scaling-Up","created":"2025-02-19","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":"2507.07580","title":"COALA: Numerically Stable and Efficient Framework for Context-Aware Low-Rank Approximation","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2509.10971","title":"PHLoRA: data-free Post-hoc Low-Rank Adapter extraction from full-rank checkpoint","created":"2025-09-13","cited_by_count":5,"area":null},{"id":"2601.11042","title":"Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse","created":"2026-01-16","cited_by_count":5,"area":null},{"id":"2606.07684","title":"Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching","created":"2026-06-05","cited_by_count":5,"area":null},{"id":"2410.00340","title":"Sparse Attention Decomposition Applied to Circuit Tracing","created":"2024-10-01","cited_by_count":4,"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":"2502.15092","title":"Optimizing Singular Spectrum for Large Language Model Compression","created":"2025-02-20","cited_by_count":4,"area":null},{"id":"2503.09657","title":"T\\'yr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2506.13187","title":"Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2512.13733","title":"Low-Rank Compression of Language Models via Differentiable Rank Selection","created":"2025-12-14","cited_by_count":4,"area":null},{"id":"2603.03597","title":"NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training","created":"2026-03-04","cited_by_count":4,"area":null},{"id":"2604.00821","title":"Optimal Brain Decomposition for Accurate LLM Low-Rank Approximation","created":"2026-04-01","cited_by_count":4,"area":null},{"id":"2604.03258","title":"SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression","created":"2026-03-12","cited_by_count":4,"area":null},{"id":"2411.09816","title":"Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition","created":"2024-11-14","cited_by_count":3,"area":null},{"id":"2502.01717","title":"Choose Your Model Size: Any Compression of Large Language Models Without Re-Computation","created":"2025-02-03","cited_by_count":3,"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":"2505.18350","title":"How Many Parameters Does Your Task Really Need? Task Specific Pruning with LLM-Sieve","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2506.02818","title":"ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2509.11092","title":"PanoLora: Bridging Perspective and Panoramic Video Generation with LoRA Adaptation","created":"2025-09-14","cited_by_count":3,"area":null},{"id":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2510.14163","title":"Towards Reversible Model Merging For Low-rank Weights","created":"2025-10-15","cited_by_count":3,"area":null},{"id":"2510.14697","title":"Purifying Task Vectors in Knowledge-Aware Subspace for Model Merging","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2510.19389","title":"ARA: Adaptive Rank Allocation for Efficient Large Language Model SVD Compression","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2512.01980","title":"Low-Rank Prehab: Preparing Neural Networks for SVD Compression","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2512.03062","title":"Globally optimized SVD compression of LLMs via Fermi-function-based rank selection and gauge fixing","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2602.07804","title":"Pruning as a Cooperative Game: Surrogate-Assisted Layer Contribution Estimation for Large Language Models","created":"2026-02-08","cited_by_count":3,"area":null},{"id":"2603.18426","title":"Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2604.03298","title":"ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs","created":"2026-03-28","cited_by_count":3,"area":null},{"id":"2506.03230","title":"DiaBlo: Diagonal Blocks Are Sufficient For Finetuning","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.11044","title":"Boost Post-Training Quantization via Null Space Optimization for Large Language Models","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2509.23595","title":"Timber: Training-free Instruct Model Refining with Base via Effective Rank","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2509.25136","title":"BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.05064","title":"Boomerang Distillation Enables Zero-Shot Model Size Interpolation","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2510.23652","title":"The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models","created":"2025-10-25","cited_by_count":2,"area":null},{"id":"2512.09946","title":"ELANA: A Simple Energy and Latency Analyzer for LLMs","created":"2025-12-07","cited_by_count":2,"area":null},{"id":"2512.12131","title":"BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models","created":"2025-12-13","cited_by_count":2,"area":null},{"id":"2512.17720","title":"Mitigating Forgetting in Low Rank Adaptation","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2602.02680","title":"FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.11008","title":"ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2605.10793","title":"ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2608.08506","title":"Understanding Calibration and Truncation Error Propagation in Training-Free Low-Rank Compression for LLMs","created":"2026-08-09","cited_by_count":2,"area":null},{"id":"2405.15877","title":"Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications","created":"2024-05-24","cited_by_count":1,"area":null},{"id":"2501.16322","title":"Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecture","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2502.14008","title":"MaskPrune: Mask-based LLM Pruning for Layer-wise Uniform Structures","created":"2025-02-19","cited_by_count":1,"area":null},{"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":"2507.01900","title":"High-Layer Attention Pruning with Rescaling","created":"2025-07-02","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":"2507.09616","title":"MLoRQ: Bridging Low-Rank and Quantization for Transformer Compression","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2510.11234","title":"Neural Weight Compression for Language Models","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2510.16851","title":"Neuronal Group Communication for Efficient Neural representation","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2510.24037","title":"Kernelized Sparse Fine-Tuning with Bi-level Parameter Competition for Vision Models","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2511.06786","title":"Rethinking Parameter Sharing as Graph Coloring for Structured Compression","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2511.11641","title":"EcoSpa: Efficient Transformer Training with Coupled Sparsity","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2512.20861","title":"Memory-Efficient Acceleration of Block Low-Rank Foundation Models on Resource Constrained GPUs","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2602.00161","title":"LLM Compression by Block Removal with Constrained Binary Optimization","created":"2026-01-29","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":"2602.15200","title":"COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2603.12272","title":"ActTail: Global Activation Sparsity in Large Language Models","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2605.08568","title":"Different Prompts, Different Ranks: Prompt-aware Dynamic Rank Selection for SVD-based LLM Compression","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.18904","title":"Dynamic Model Merging Made Slim","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2605.20440","title":"Exact Symmetry as Algebra: Group-Structured Tensors that Enforce Physical Selection Rules","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2605.22205","title":"Skill Weaving: Efficient LLM Improvement via Modular Skillpacks","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.19164","title":"Data-Aware Model Merging in the Essential Subspace for Multi-Task Knowledge Aggregation","created":"2026-06-17","cited_by_count":1,"area":null}],"next_cursor":"100"}