{"total":104,"rows":[{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269,"area":null},{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260,"area":"agents"},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2310.08659","title":"LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models","created":"2023-10-12","cited_by_count":196,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2411.05007","title":"SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models","created":"2024-11-07","cited_by_count":170,"area":"diffusion"},{"id":"2312.05821","title":"ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models","created":"2023-12-10","cited_by_count":169,"area":"inference"},{"id":"2402.01109","title":"Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-02-02","cited_by_count":115,"area":"alignment"},{"id":"2310.01334","title":"Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy","created":"2023-10-02","cited_by_count":108,"area":"moe"},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2402.09398","title":"Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference","created":"2024-02-14","cited_by_count":75,"area":"inference"},{"id":"2408.05646","title":"Eigen Attention: Attention in Low-Rank Space for KV Cache Compression","created":"2024-08-10","cited_by_count":72,"area":"lr"},{"id":"2308.14352","title":"EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices","created":"2023-08-28","cited_by_count":69,"area":"moe"},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2411.01433","title":"HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference","created":"2024-11-03","cited_by_count":55,"area":"moe"},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47,"area":"moe"},{"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,"area":null},{"id":"2310.18859","title":"SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models","created":"2023-10-29","cited_by_count":38,"area":"moe"},{"id":"2406.10594","title":"BlockPruner: Fine-grained Pruning for Large Language Models","created":"2024-06-15","cited_by_count":36,"area":null},{"id":"2309.02784","title":"Norm Tweaking: High-performance Low-bit Quantization of Large Language Models","created":"2023-09-06","cited_by_count":33,"area":null},{"id":"2402.19348","title":"Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlook","created":"2024-02-29","cited_by_count":33,"area":null},{"id":"2502.17298","title":"Delta Decompression for MoE-based LLMs Compression","created":"2025-02-24","cited_by_count":33,"area":"moe"},{"id":"2309.14021","title":"LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression","created":"2023-09-25","cited_by_count":26,"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":"2402.17946","title":"SparseLLM: Towards Global Pruning for Pre-trained Language Models","created":"2024-02-28","cited_by_count":23,"area":null},{"id":"2402.01799","title":"Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward","created":"2024-02-02","cited_by_count":21,"area":null},{"id":"2404.01365","title":"Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation","created":"2024-04-01","cited_by_count":21,"area":"moe"},{"id":"2406.10777","title":"RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning","created":"2024-06-16","cited_by_count":21,"area":null},{"id":"2405.16325","title":"SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs","created":"2024-05-25","cited_by_count":20,"area":null},{"id":"2409.13652","title":"OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition","created":"2024-09-20","cited_by_count":20,"area":null},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16,"area":"lr"},{"id":"2403.13269","title":"AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models","created":"2024-03-20","cited_by_count":15,"area":null},{"id":"2510.12474","title":"SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression","created":"2025-10-14","cited_by_count":14,"area":null},{"id":"2402.14833","title":"CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness","created":"2024-02-17","cited_by_count":12,"area":null},{"id":"2404.09695","title":"LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models","created":"2024-04-15","cited_by_count":12,"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":"2503.06881","title":"ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration","created":"2025-03-10","cited_by_count":12,"area":"moe"},{"id":"2503.01901","title":"Identifying Sensitive Weights via Post-quantization Integral","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2505.12805","title":"FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA","created":"2025-05-19","cited_by_count":11,"area":null},{"id":"2405.10616","title":"Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization","created":"2024-05-17","cited_by_count":10,"area":null},{"id":"2502.14816","title":"Dynamic Low-Rank Sparse Adaptation for Large Language Models","created":"2025-02-20","cited_by_count":10,"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":"2504.04215","title":"Towards Understanding and Improving Refusal in Compressed Models via Mechanistic Interpretability","created":"2025-04-05","cited_by_count":7,"area":"mechinterp"},{"id":"2505.18413","title":"LatentLLM: Attention-Aware Joint Tensor Compression","created":"2025-05-23","cited_by_count":7,"area":"mllm"},{"id":"2602.20208","title":"Model Merging in the Essential Subspace","created":"2026-02-23","cited_by_count":7,"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":"2602.05929","title":"KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs","created":"2026-02-05","cited_by_count":5,"area":"inference"},{"id":"2402.06004","title":"Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy","created":"2024-02-08","cited_by_count":4,"area":null},{"id":"2410.03040","title":"Geometry is All You Need: A Unified Taxonomy of Matrix and Tensor Factorization for Compression of Generative Language Models","created":"2024-10-03","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":"2505.13515","title":"LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades","created":"2025-05-17","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":"2406.05276","title":"VTrans: Accelerating Transformer Compression with Variational Information Bottleneck based Pruning","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2410.14852","title":"FedSpaLLM: Federated Pruning of Large Language Models","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2502.00899","title":"HASSLE-free: A unified Framework for Sparse plus Low-Rank Matrix Decomposition for LLMs","created":"2025-02-02","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":"2405.13039","title":"Surgical Feature-Space Decomposition of LLMs: Why, When and How?","created":"2024-05-17","cited_by_count":2,"area":null},{"id":"2408.11855","title":"FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models","created":"2024-08-15","cited_by_count":2,"area":"moe"},{"id":"2410.06846","title":"Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity","created":"2024-10-09","cited_by_count":2,"area":"ssm"},{"id":"2505.13547","title":"Exploring Federated Pruning for Large Language Models","created":"2025-05-19","cited_by_count":2,"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":"2510.05528","title":"ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2604.01609","title":"Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression","created":"2026-04-02","cited_by_count":2,"area":"inference"},{"id":"2605.07271","title":"Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2408.11799","title":"Practical token pruning for foundation models in few-shot conversational virtual assistant systems","created":"2024-08-21","cited_by_count":1,"area":"inference"},{"id":"2411.00969","title":"Magnitude Pruning of Large Pretrained Transformer Models with a Mixture Gaussian Prior","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2503.05920","title":"IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2505.03745","title":"AccLLM: Accelerating Long-Context LLM Inference Via Algorithm-Hardware Co-Design","created":"2025-04-07","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":"2506.02561","title":"Pruning General Large Language Models into Customized Expert Models","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2506.16316","title":"Bayesian Optimization over Bounded Domains with the Beta Product Kernel","created":"2025-06-19","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":"2510.16439","title":"FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2602.00942","title":"SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2603.03318","title":"Quantum-Inspired Self-Attention in a Large Language Model","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2603.06920","title":"DLRMamba: Distilling Low-Rank Mamba for Edge Multispectral Fusion Object Detection","created":"2026-03-06","cited_by_count":1,"area":"ssm"},{"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":"2605.05659","title":"Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks","created":"2026-05-07","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},{"id":"2501.16376","title":"SwiftPrune: Hessian-Free Weight Pruning for Large Language Models","created":"2025-01-24","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":"2505.11204","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2506.11498","title":"Lag-Relative Sparse Attention In Long Context Training","created":"2025-06-13","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":"2509.04244","title":"Integrating Pruning with Quantization for Efficient Deep Neural Networks Compression","created":"2025-09-04","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":"2510.26446","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":"2511.01296","title":"LSHFed: Robust and Communication-Efficient Federated Learning with Locally-Sensitive Hashing Gradient Mapping","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2511.02681","title":"Optimal Singular Damage: Efficient LLM Inference in Low Storage Regimes","created":"2025-11-04","cited_by_count":0,"area":"inference"},{"id":"2512.22106","title":"Pruning as a Game: Equilibrium-Driven Sparsification of Neural Networks","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2604.21952","title":"Focus Session: Hardware and Software Techniques for Accelerating Multimodal Foundation Models","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.06216","title":"TIDE: Every Layer Knows the Token Beneath the Context","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2607.13735","title":"Constraint-Driven Model Optimization: An Industry Framework for Selecting Compression and Acceleration Techniques in Modern Machine Learning Systems","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.20214","title":"ELSAA: Efficient Low-Rank and Sparse Attention Approximation for Training Transformers","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.22489","title":"\\k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating","created":"2026-07-24","cited_by_count":0,"area":null}],"next_cursor":"100"}