{"total":34,"rows":[{"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":"2412.04756","title":"ChatNVD: Advancing Cybersecurity Vulnerability Assessment with Large Language Models","created":"2024-12-06","cited_by_count":11,"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":"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":"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":"2501.15014","title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2412.14426","title":"All-in-One Tuning and Structural Pruning for Domain-Specific LLMs","created":"2024-12-19","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":"2505.11340","title":"DecompileBench: A Comprehensive Benchmark for Evaluating Decompilers in Real-World Scenarios","created":"2025-05-16","cited_by_count":4,"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":"2510.19389","title":"ARA: Adaptive Rank Allocation for Efficient Large Language Model SVD Compression","created":"2025-10-22","cited_by_count":3,"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":"2512.09946","title":"ELANA: A Simple Energy and Latency Analyzer for LLMs","created":"2025-12-07","cited_by_count":2,"area":null},{"id":"2602.08858","title":"FlattenGPT: Depth Compression for Transformer with Layer Flattening","created":"2026-02-09","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":"2503.06291","title":"IteRABRe: Iterative Recovery-Aided Block Reduction","created":"2025-03-08","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":"2507.03828","title":"IMPACT: Importance-Aware Activation Space Reconstruction","created":"2025-07-04","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":"2604.09406","title":"OASIS: Online Activation Subspace Learning for Memory-Efficient Training","created":"2026-04-10","cited_by_count":1,"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":"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":"2509.06836","title":"COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens","created":"2025-09-08","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":"2510.19385","title":"Beyond Uniform SVD:Dual-Level Optimization across Columns and Modules for LLM Compression","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2606.21847","title":"UniRank: Unified Rank Allocation for Low-Rank LLM Compression","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2607.01127","title":"$\\text{Log}_\\text{b}$Quant: Quantizing Language Models in Logarithmic Space","created":"2026-07-01","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},{"id":"2608.30226","title":"LaMoC: Loss-Aware Modular Compression for LLMs","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.33977","title":"GroupMask: Layer-Adaptive Group-wise Sparsity for Semi-Structured LLM Pruning","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.40127","title":"Learning Functional Subspaces for Neural Network Compression","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02882","title":"DyRA: Dynamic Residual Approximation for Efficient Matrix Multiplication in DNNs","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.05504","title":"The Functional Structure of Post-Compression Recovery in Low-Rank LLMs","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}