{"total":112,"rows":[{"id":"2403.07378","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","created":"2024-03-12","cited_by_count":243,"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":"2406.05223","title":"CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning","created":"2024-06-07","cited_by_count":44,"area":null},{"id":"2406.14909","title":"Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths","created":"2024-06-21","cited_by_count":44,"area":null},{"id":"2412.14363","title":"ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals","created":"2024-12-18","cited_by_count":36,"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":"2410.03129","title":"ARB-LLM: Alternating Refined Binarizations for Large Language Models","created":"2024-10-04","cited_by_count":31,"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":"2405.17849","title":"I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models","created":"2024-05-28","cited_by_count":23,"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":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2410.05437","title":"ESPACE: Dimensionality Reduction of Activations for Model Compression","created":"2024-10-07","cited_by_count":15,"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":"2502.13178","title":"Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2510.03274","title":"Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models","created":"2025-09-27","cited_by_count":12,"area":null},{"id":"2409.12963","title":"Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner","created":"2024-09-19","cited_by_count":11,"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":"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":"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":"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":"2412.20185","title":"DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization","created":"2024-12-28","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":"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":"2406.16893","title":"A Survey of Transformer-based Language Models with Focus on Efficiency","created":"2024-05-15","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":"2602.04852","title":"On State Reduction in Linear Attention","created":"2026-02-04","cited_by_count":6,"area":null},{"id":"2502.01705","title":"Progressive Binarization with Semi-Structured Pruning for LLMs","created":"2025-02-03","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":"2505.00985","title":"Position: Enough of Scaling LLMs! Lets Focus on Downscaling","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2505.05086","title":"Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning","created":"2025-05-08","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":"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":"2503.04704","title":"Universality of Layer-Level Entropy-Weighted Quantization Beyond Model Architecture and Size","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2505.20132","title":"Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks","created":"2025-05-26","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":"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":"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":"2505.18350","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":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","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":"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":"2509.23472","title":"Memory-Efficient Fine-Tuning via Low-Rank Activation Compression","created":"2025-09-27","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":"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":"2501.05017","title":"Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learning","created":"2025-01-09","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":"2507.03828","title":"IMPACT: Importance-Aware Activation Space Reconstruction","created":"2025-07-04","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":"2510.11234","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":"2511.06786","title":"Rethinking Parameter Sharing as Graph Coloring for Structured Compression","created":"2025-11-10","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":"2603.16435","title":"VQKV: High-Fidelity and High-Ratio Cache Compression via Vector-Quantization","created":"2026-03-17","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":"2604.09406","title":"OASIS: Online Activation Subspace Learning for Memory-Efficient Training","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2605.07297","title":"Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers","created":"2026-05-08","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":"2605.20440","title":"Exact Symmetry as Algebra: Group-Structured Tensors that Enforce Physical Selection Rules","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.23568","title":"SVD-Surgeon: Optimal Singular-Value Surgery for Large Language Model Compression","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2406.08904","title":"AdaPTwin: Low-Cost Adaptive Compression of Product Twins in Transformers","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2503.17101","title":"Large Language Model Compression via the Nested Activation-Aware Decomposition","created":"2025-03-21","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":"2507.03294","title":"MGAA: Multi-Granular Adaptive Allocation fof Low-Rank Compression of LLMs","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2508.16680","title":"CALR: Corrective Adaptive Low-Rank Decomposition for Efficient Large Language Model Layer Compression","created":"2025-08-21","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":"2510.09160","title":"Efficient Resource-Constrained Training of Transformers via Subspace Optimization","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2603.14110","title":"SVD Contextual Sparsity Predictors for Fast LLM Inference","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2604.04493","title":"SLaB: Sparse-Lowrank-Binary Decomposition for Efficient Large Language Models","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.09595","title":"Why Smaller Is Slower? Dimensional Misalignment in Compressed LLMs","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.18085","title":"Predicting LLM Compression Degradation from Spectral Statistics","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.00140","title":"Technical Report: Activation Residual Hessian Quantization (ARHQ) for Low-Bit LLM Quantization","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.01627","title":"Importance-Guided Basis Selection for Low-Rank Decomposition of Large Language Models","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.03109","title":"Gated Subspace Inference for Transformer Acceleration","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.07706","title":"Bayesian Fine-tuning in Projected Subspaces","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.17985","title":"SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.30836","title":"Cross-Layer Subspace Coupling for LLM Compression: A Unifying Framework and Its Empirical Limits","created":"2026-05-29","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":"2606.19993","title":"Activation- and Influence-Aware Ranks (AIR): Function-Preserving SVD Compression for LLMs","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.27785","title":"Output-Space Allocation Costs for Calibration-Guided LLM Compression: An Empirical Study","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.03057","title":"LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.18284","title":"Compressing What Matters: Neuron Importance Meets Data-Aware Low Rank Approximation for Language Model Compression","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.29071","title":"Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.12953","title":"Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.25188","title":"Transforms for LLM Quantization: The Great Inversion and Format Co-Design","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.26389","title":"LowRankArena: A Standardized Evaluation Platform for SVD-Based LLM Compression","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":"100"}