{"total":23,"rows":[{"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":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127,"area":null},{"id":"2310.00034","title":"PB-LLM: Partially Binarized Large Language Models","created":"2023-09-29","cited_by_count":83,"area":null},{"id":"2403.00522","title":"VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks","created":"2024-03-01","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":"2405.17849","title":"I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models","created":"2024-05-28","cited_by_count":23,"area":null},{"id":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2309.09507","title":"Pruning Large Language Models via Accuracy Predictor","created":"2023-09-18","cited_by_count":5,"area":null},{"id":"2504.03717","title":"RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm","created":"2025-03-29","cited_by_count":5,"area":null},{"id":"2409.04833","title":"Achieving Peak Performance for Large Language Models: A Systematic Review","created":"2024-09-07","cited_by_count":4,"area":null},{"id":"2501.08598","title":"LlamaRestTest: Effective REST API Testing with Small Language Models","created":"2025-01-15","cited_by_count":4,"area":null},{"id":"2501.13331","title":"Qrazor: Reliable and Effortless 4-bit LLM Quantization by Significant Data Razoring","created":"2025-01-23","cited_by_count":4,"area":null},{"id":"2504.13932","title":"Enhancing Ultra-Low-Bit Quantization of Large Language Models Through Saliency-Aware Partial Retraining","created":"2025-04-14","cited_by_count":3,"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":"2602.02546","title":"D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2503.21782","title":"Mobile-VideoGPT: Fast and Accurate Model for Mobile Video Understanding","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2405.14597","title":"Integer Scale: A Free Lunch for Faster Fine-grained Quantization of LLMs","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2410.08791","title":"Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2511.07425","title":"An Evaluation of LLMs Inference on Popular Single-board Computers","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2602.00165","title":"Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2607.13735","title":"Constraint-Driven Model Optimization: An Industry Framework for Selecting Compression and Acceleration Techniques in Modern Machine Learning Systems","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.24173","title":"SandwichQuant: Which Parameters Matter Before and After Quantization?","created":"2026-08-25","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}],"next_cursor":null}