{"total":80,"rows":[{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656,"area":null},{"id":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127,"area":null},{"id":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86,"area":null},{"id":"2405.14917","title":"SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models","created":"2024-05-23","cited_by_count":63,"area":null},{"id":"2405.14852","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","created":"2024-05-23","cited_by_count":61,"area":null},{"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":"2410.19878","title":"Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies","created":"2024-10-24","cited_by_count":47,"area":null},{"id":"2406.06385","title":"Low-Rank Quantization-Aware Training for LLMs","created":"2024-06-10","cited_by_count":43,"area":null},{"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":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"area":null},{"id":"2406.03136","title":"Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models","created":"2024-06-05","cited_by_count":31,"area":null},{"id":"2406.16797","title":"Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs","created":"2024-06-24","cited_by_count":31,"area":null},{"id":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"id":"2407.10960","title":"Fast Matrix Multiplications for Lookup Table-Quantized LLMs","created":"2024-07-15","cited_by_count":29,"area":null},{"id":"2406.02913","title":"Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity","created":"2024-06-05","cited_by_count":28,"area":null},{"id":"2402.05147","title":"ApiQ: Finetuning of 2-Bit Quantized Large Language Model","created":"2024-02-07","cited_by_count":27,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2508.14896","title":"Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs","created":"2025-08-20","cited_by_count":23,"area":null},{"id":"2410.06040","title":"QERA: an Analytical Framework for Quantization Error Reconstruction","created":"2024-10-08","cited_by_count":22,"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":"2504.07448","title":"LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation","created":"2025-04-10","cited_by_count":19,"area":null},{"id":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2312.08583","title":"ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2405.16528","title":"LoQT: Low-Rank Adapters for Quantized Pretraining","created":"2024-05-26","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":"2505.20154","title":"UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2506.14530","title":"Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters","created":"2025-06-17","cited_by_count":11,"area":null},{"id":"2405.03637","title":"Collage: Light-Weight Low-Precision Strategy for LLM Training","created":"2024-05-06","cited_by_count":10,"area":null},{"id":"2505.21930","title":"Efficient Ensemble for Fine-tuning Language Models on Multiple Datasets","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2404.02837","title":"Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models","created":"2024-04-03","cited_by_count":9,"area":null},{"id":"2412.01129","title":"RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy","created":"2024-12-02","cited_by_count":9,"area":null},{"id":"2504.09223","title":"DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models","created":"2025-04-12","cited_by_count":9,"area":null},{"id":"2508.19432","title":"Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs","created":"2025-08-26","cited_by_count":9,"area":null},{"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":"2505.14742","title":"Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis","created":"2025-05-20","cited_by_count":7,"area":null},{"id":"2501.18475","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","created":"2025-01-30","cited_by_count":5,"area":null},{"id":"2502.13533","title":"Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2505.03802","title":"Balancing Fidelity and Plasticity: Aligning Mixed-Precision Fine-Tuning with Linguistic Hierarchies","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2508.03332","title":"Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models","created":"2025-08-05","cited_by_count":5,"area":null},{"id":"2602.22268","title":"AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning","created":"2026-02-25","cited_by_count":5,"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":"2510.24561","title":"LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2405.13155","title":"ReALLM: A general framework for LLM compression and fine-tuning","created":"2024-05-21","cited_by_count":3,"area":null},{"id":"2405.20202","title":"One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments","created":"2024-05-30","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":"2508.07697","title":"Semantic-Enhanced Time-Series Forecasting via Large Language Models","created":"2025-08-11","cited_by_count":3,"area":null},{"id":"2509.23410","title":"PATCH: Learnable Tile-level Hybrid Sparsity for LLMs","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2603.01376","title":"3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2407.05413","title":"SBoRA: Low-Rank Adaptation with Regional Weight Updates","created":"2024-07-07","cited_by_count":2,"area":null},{"id":"2503.08333","title":"1LoRA: Summation Compression for Very Low-Rank Adaptation","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2506.03230","title":"DiaBlo: Diagonal Blocks Are Sufficient For Finetuning","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.20251","title":"Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models","created":"2025-06-25","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":"2509.25214","title":"On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2512.13886","title":"OPTIMA: Optimal One-shot Pruning for LLMs via Quadratic Programming Reconstruction","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2502.11439","title":"An Efficient Sparse Fine-Tuning with Low Quantization Error via Neural Network Pruning","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2502.13811","title":"On the Duality between Gradient Transformations and Adapters","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2505.08793","title":"Onboard Optimization and Learning: A Survey","created":"2025-05-07","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":"2509.17428","title":"QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2510.24061","title":"FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic","created":"2025-10-28","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":"2603.08185","title":"SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization","created":"2026-03-09","cited_by_count":1,"area":null},{"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":"2606.01412","title":"GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2606.07116","title":"OffQ: Taming Structured Outliers in LLM Quantization by Offsetting","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2609.04526","title":"Scale-QLoRA: Code-Invariant Adapter Merging for Native 4-bit Microscaling LLMs","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2410.14713","title":"QuAILoRA: Quantization-Aware Initialization for LoRA","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2507.01806","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2509.01190","title":"Efficient Large Language Models with Zero-Shot Adjustable Acceleration","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2510.18650","title":"Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2512.23485","title":"FRoD: Full-Rank Efficient Fine-Tuning with Rotational Degrees for Fast Convergence","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2602.12609","title":"QuEPT: Quantized Elastic Precision Transformers with One-Shot Calibration for Multi-Bit Switching","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2605.05819","title":"HCInfer: An Efficient Inference System via Error Compensation for Resource-Constrained Devices","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.24969","title":"OSDTW: Optimal Shared Depth and Task Weighting for Long-Tailed Recognition","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2606.00494","title":"ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2607.08643","title":"BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.23816","title":"AQLoRA: A Zero-Search Recipe for Fast Quantized LoRA Fine-Tuning","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.25977","title":"When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2610.00928","title":"Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}