{"total":243,"rows":[{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"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":"2407.21118","title":"Palu: Compressing KV-Cache with Low-Rank Projection","created":"2024-07-30","cited_by_count":64,"area":"inference"},{"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":"2506.01713","title":"SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning","created":"2025-06-02","cited_by_count":57,"area":"lr"},{"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":"2408.09632","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","created":"2024-08-19","cited_by_count":48,"area":null},{"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":"2406.09519","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":"2406.13035","title":"D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models","created":"2024-06-18","cited_by_count":31,"area":"inference"},{"id":"2502.17599","title":"MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference","created":"2025-02-24","cited_by_count":31,"area":"mllm"},{"id":"2506.23266","title":"Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging","created":"2025-06-29","cited_by_count":28,"area":"moe"},{"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":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16,"area":"agents"},{"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":"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":"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":"2505.20925","title":"Multi-objective Large Language Model Alignment with Hierarchical Experts","created":"2025-05-27","cited_by_count":13,"area":"alignment"},{"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":"2506.13771","title":"LittleBit: Ultra Low-Bit Quantization via Latent Factorization","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2508.05282","title":"Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning","created":"2025-08-07","cited_by_count":11,"area":"lr"},{"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":"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":"2605.17757","title":"OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization","created":"2026-05-18","cited_by_count":9,"area":"inference"},{"id":"2409.09808","title":"Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion","created":"2024-09-15","cited_by_count":8,"area":"ssm"},{"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":"2505.12942","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":"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":"2602.00038","title":"LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion","created":"2026-01-19","cited_by_count":8,"area":"alignment"},{"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":"2505.18413","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":"2508.09981","title":"LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit","created":"2025-08-13","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":"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":"2502.15304","title":"SVDq: 1.25-bit and 410x Key Cache Compression for LLM Attention","created":"2025-02-21","cited_by_count":6,"area":"inference"},{"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":"2503.05936","title":"CASP: Compression of Large Multimodal Models Based on Attention Sparsity","created":"2025-03-07","cited_by_count":5,"area":"mllm"},{"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":"2505.23966","title":"FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression","created":"2025-05-29","cited_by_count":5,"area":"inference"},{"id":"2507.05557","title":"Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS","created":"2025-07-08","cited_by_count":5,"area":"lr"},{"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":"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":"2603.04800","title":"MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models","created":"2026-03-05","cited_by_count":5,"area":"mllm"},{"id":"2603.17946","title":"CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention","created":"2026-03-18","cited_by_count":5,"area":"inference"},{"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":"2606.03465","title":"Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression","created":"2026-06-02","cited_by_count":4,"area":"lr"},{"id":"2606.09080","title":"Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric Taxonomy","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"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":"2510.05544","title":"Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM","created":"2025-10-07","cited_by_count":3,"area":"mllm"},{"id":"2510.14163","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":"2602.02599","title":"RAP: KV-Cache Compression via RoPE-Aligned Pruning","created":"2026-02-01","cited_by_count":3,"area":"inference"},{"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":"2604.02570","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"}],"next_cursor":"100"}