{"total":33,"rows":[{"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":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"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":"2412.17560","title":"GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference","created":"2024-12-23","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":"2505.18724","title":"LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2508.05571","title":"iFairy: the First 2-bit Complex LLM with All Parameters in $\\{\\pm1, \\pm i\\}$","created":"2025-08-07","cited_by_count":5,"area":null},{"id":"2508.16785","title":"Interpreting the Effects of Quantization on LLMs","created":"2025-08-22","cited_by_count":5,"area":null},{"id":"2510.16805","title":"Mixed-Precision Quantization for Language Models: Techniques and Prospects","created":"2025-10-19","cited_by_count":5,"area":null},{"id":"2603.01776","title":"FreeAct: Freeing Activations for LLM Quantization","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2412.12951","title":"FineGates: LLMs Finetuning with Compression using Stochastic Gates","created":"2024-12-17","cited_by_count":3,"area":null},{"id":"2409.11650","title":"Art and Science of Quantizing Large-Scale Models: A Comprehensive Overview","created":"2024-09-18","cited_by_count":2,"area":null},{"id":"2409.14595","title":"EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models","created":"2024-09-22","cited_by_count":2,"area":null},{"id":"2512.02901","title":"Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in $\\{\\pm 1, \\pm i\\}$","created":"2025-12-02","cited_by_count":2,"area":null},{"id":"2601.11113","title":"Differentially Private Subspace Fine-Tuning for Large Language Models","created":"2026-01-16","cited_by_count":2,"area":null},{"id":"2602.09169","title":"Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2605.25966","title":"Mapping the Schedule x Bit-Width Boundary in Sub-100M Quantisation-Aware Training","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2411.03934","title":"Interactions Across Blocks in Post-Training Quantization of Large Language Models","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2501.09849","title":"Coded Deep Learning: Framework and Algorithm","created":"2025-01-16","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":"2507.09616","title":"MLoRQ: Bridging Low-Rank and Quantization for Transformer Compression","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2608.20873","title":"In-Cell Learning: Language Models That Update Their Own Weights in Sequence Without Changing the File They Ship","created":"2026-08-21","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":"2609.39223","title":"QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs","created":"2026-09-30","cited_by_count":1,"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":"2605.10673","title":"Compander-Aligned Query Geometry for Quantized Zeroth-Order Optimization","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.20295","title":"Quant.npu: Enabling Efficient Mobile NPU Inference for on-device LLMs via Fully Static Quantization","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.00539","title":"GNMR: Runtime Stability Control for Low-Precision Large Language Model Training","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.04063","title":"LLM Compression with Jointly Optimizing Architectural and Quantization choices","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2608.20953","title":"Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.29667","title":"A Target-Centric Survey of Quantization-Aware Training","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.00049","title":"REAL-Q: E2E LLM Quantization via Dynamic Gradient Descent","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.36654","title":"Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}