{"total":195,"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":"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":"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":"2307.09458","title":"Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla","created":"2023-07-18","cited_by_count":149,"area":null},{"id":"2306.11222","title":"LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation","created":"2023-06-20","cited_by_count":104,"area":null},{"id":"2311.12023","title":"LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning","created":"2023-11-20","cited_by_count":92,"area":null},{"id":"2312.17238","title":"Fast Inference of Mixture-of-Experts Language Models with Offloading","created":"2023-12-28","cited_by_count":91,"area":"moe"},{"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":"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":"2407.21118","title":"Palu: Compressing KV-Cache with Low-Rank Projection","created":"2024-07-30","cited_by_count":64,"area":"inference"},{"id":"2405.18886","title":"Compressing Large Language Models using Low Rank and Low Precision Decomposition","created":"2024-05-29","cited_by_count":59,"area":null},{"id":"2411.01016","title":"MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition","created":"2024-11-01","cited_by_count":57,"area":"moe"},{"id":"2408.09632","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","created":"2024-08-19","cited_by_count":48,"area":null},{"id":"2505.16831","title":"Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs","created":"2025-05-22","cited_by_count":42,"area":"safety"},{"id":"2408.06621","title":"Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs","created":"2024-08-13","cited_by_count":36,"area":"lr"},{"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":"2302.09019","title":"Tensor Networks Meet Neural Networks: A Survey and Future Perspectives","created":"2023-01-22","cited_by_count":32,"area":null},{"id":"2208.13049","title":"TrojViT: Trojan Insertion in Vision Transformers","created":"2022-08-27","cited_by_count":31,"area":"safety"},{"id":"2509.12235","title":"RL Fine-Tuning Heals OOD Forgetting in SFT","created":"2025-09-08","cited_by_count":31,"area":"lr"},{"id":"2402.03902","title":"A phase transition between positional and semantic learning in a solvable model of dot-product attention","created":"2024-02-06","cited_by_count":30,"area":null},{"id":"2303.02242","title":"TrojText: Test-time Invisible Textual Trojan Insertion","created":"2023-03-03","cited_by_count":28,"area":null},{"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":"2503.04992","title":"Wanda++: Pruning Large Language Models via Regional Gradients","created":"2025-03-06","cited_by_count":26,"area":"inference"},{"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":"2505.22689","title":"SlimLLM: Accurate Structured Pruning for Large Language Models","created":"2025-05-28","cited_by_count":18,"area":null},{"id":"2307.00526","title":"TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition","created":"2023-07-02","cited_by_count":17,"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":"2505.24357","title":"ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration","created":"2025-05-30","cited_by_count":16,"area":"inference"},{"id":"2510.16292","title":"QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models","created":"2025-10-18","cited_by_count":16,"area":"mllm"},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2410.03090","title":"UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective","created":"2024-10-04","cited_by_count":15,"area":"inference"},{"id":"2211.09718","title":"Numerical Optimizations for Weighted Low-rank Estimation on Language Model","created":"2022-11-02","cited_by_count":14,"area":null},{"id":"2305.17235","title":"COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models","created":"2023-05-26","cited_by_count":14,"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":"2505.05829","title":"Accelerating Diffusion Transformer via Increment-Calibrated Caching with Channel-Aware Singular Value Decomposition","created":"2025-05-09","cited_by_count":12,"area":"diffusion"},{"id":"2602.03051","title":"SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression","created":"2026-02-03","cited_by_count":12,"area":"mechinterp"},{"id":"2306.14152","title":"Low-Rank Prune-And-Factorize for Language Model Compression","created":"2023-06-25","cited_by_count":11,"area":null},{"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":"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":"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":"2306.04169","title":"Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation","created":"2023-06-07","cited_by_count":9,"area":null},{"id":"2405.14105","title":"Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference","created":"2024-05-23","cited_by_count":9,"area":"inference"},{"id":"2406.09117","title":"PC-LoRA: Low-Rank Adaptation for Progressive Model Compression with Knowledge Distillation","created":"2024-06-13","cited_by_count":9,"area":"distill"},{"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":"2304.10891","title":"Transformer-Based Autonomous Driving Models and Deployment-Oriented Compression: A Survey","created":"2023-04-21","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":"2505.12942","title":"A3 : an Analytical Low-Rank Approximation Framework for Attention","created":"2025-05-19","cited_by_count":8,"area":"inference"},{"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":"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":"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":"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":"2505.20112","title":"ERC-SVD: Error-Controlled SVD for Large Language Model Compression","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2506.08436","title":"Olica: Efficient Structured Pruning of Large Language Models without Retraining","created":"2025-06-10","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":"2602.04852","title":"On State Reduction in Linear Attention","created":"2026-02-04","cited_by_count":6,"area":null},{"id":"2606.26650","title":"CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs","created":"2026-06-25","cited_by_count":6,"area":null},{"id":"2310.18882","title":"Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks","created":"2023-10-29","cited_by_count":5,"area":null},{"id":"2312.14647","title":"Towards Message Brokers for Generative AI: Survey, Challenges, and Opportunities","created":"2023-12-22","cited_by_count":5,"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":"2502.04043","title":"Probe-Free Low-Rank Activation Intervention","created":"2025-02-06","cited_by_count":5,"area":null},{"id":"2503.05936","title":"CASP: Compression of Large Multimodal Models Based on Attention Sparsity","created":"2025-03-07","cited_by_count":5,"area":"mllm"},{"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":"2511.11907","title":"KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference","created":"2025-11-14","cited_by_count":5,"area":"inference"},{"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":"2303.08343","title":"Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models","created":"2023-03-15","cited_by_count":4,"area":null},{"id":"2401.08505","title":"Harnessing Orthogonality to Train Low-Rank Neural Networks","created":"2024-01-16","cited_by_count":4,"area":null},{"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":"2412.06868","title":"Compression for Better: A General and Stable Lossless Compression Framework","created":"2024-12-09","cited_by_count":4,"area":null},{"id":"2501.14713","title":"FlexiGPT: Pruning and Extending Large Language Models with Low-Rank Weight Sharing","created":"2025-01-24","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":"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":"2312.13211","title":"DSFormer: Effective Compression of Text-Transformers by Dense-Sparse Weight Factorization","created":"2023-12-20","cited_by_count":3,"area":null},{"id":"2403.00625","title":"Bias Mitigation in Fine-tuning Pre-trained Models for Enhanced Fairness and Efficiency","created":"2024-03-01","cited_by_count":3,"area":null},{"id":"2410.17957","title":"MCUBERT: Memory-Efficient BERT Inference on Commodity Microcontrollers","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2412.06867","title":"Lossless Model Compression via Joint Low-Rank Factorization Optimization","created":"2024-12-09","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":"2502.16912","title":"When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?","created":"2025-02-24","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":"2510.05544","title":"Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM","created":"2025-10-07","cited_by_count":3,"area":"mllm"},{"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":"2604.02570","title":"WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models","created":"2026-04-02","cited_by_count":3,"area":"mllm"},{"id":"2605.08314","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","created":"2026-05-08","cited_by_count":3,"area":"inference"},{"id":"2310.04649","title":"Uncovering Model Processing Strategies with Non-Negative Per-Example Fisher Factorization","created":"2023-10-07","cited_by_count":2,"area":null},{"id":"2408.07196","title":"SeLoRA: Self-Expanding Low-Rank Adaptation of Latent Diffusion Model for Medical Image Synthesis","created":"2024-08-13","cited_by_count":2,"area":"diffusion"},{"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":"2503.21928","title":"An Efficient Training Algorithm for Models with Block-wise Sparsity","created":"2025-03-27","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":"2505.21987","title":"ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning","created":"2025-05-28","cited_by_count":2,"area":null}],"next_cursor":"100"}