{"total":52,"rows":[{"id":"2402.14905","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","created":"2024-02-22","cited_by_count":223,"area":null},{"id":"2501.17116","title":"Optimizing Large Language Model Training Using FP4 Quantization","created":"2025-01-28","cited_by_count":56,"area":null},{"id":"2406.02924","title":"Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models","created":"2024-06-05","cited_by_count":40,"area":null},{"id":"2512.02010","title":"Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling","created":"2025-12-01","cited_by_count":35,"area":null},{"id":"2402.14866","title":"APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models","created":"2024-02-21","cited_by_count":34,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2312.09993","title":"LLaMAntino: LLaMA 2 Models for Effective Text Generation in Italian Language","created":"2023-12-15","cited_by_count":25,"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":"2312.01678","title":"Jellyfish: A Large Language Model for Data Preprocessing","created":"2023-12-04","cited_by_count":20,"area":null},{"id":"2403.20041","title":"Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs","created":"2024-03-29","cited_by_count":17,"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":"2403.10799","title":"Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment","created":"2024-03-16","cited_by_count":13,"area":null},{"id":"2405.00314","title":"Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey","created":"2024-05-01","cited_by_count":13,"area":null},{"id":"2407.08044","title":"RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2506.09397","title":"SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving","created":"2025-06-11","cited_by_count":13,"area":null},{"id":"2502.12346","title":"QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models","created":"2025-02-17","cited_by_count":11,"area":null},{"id":"2311.09550","title":"A Speed Odyssey for Deployable Quantization of LLMs","created":"2023-11-16","cited_by_count":10,"area":null},{"id":"2501.10658","title":"LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator","created":"2025-01-18","cited_by_count":9,"area":null},{"id":"2404.18255","title":"PatentGPT: A Large Language Model for Intellectual Property","created":"2024-04-28","cited_by_count":8,"area":null},{"id":"2405.13938","title":"eXmY: A Data Type and Technique for Arbitrary Bit Precision Quantization","created":"2024-05-22","cited_by_count":7,"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":"2501.04052","title":"RaZeR: Pushing the Limits of NVFP4 Quantization with Redundant Zero Remapping","created":"2025-01-06","cited_by_count":7,"area":null},{"id":"2410.12168","title":"COMET: Towards Partical W4A4KV4 LLMs Serving","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2502.16696","title":"Dynamic LLM Routing and Selection based on User Preferences: Balancing Performance, Cost, and Ethics","created":"2025-02-23","cited_by_count":6,"area":null},{"id":"2403.01384","title":"On the Compressibility of Quantized Large Language Models","created":"2024-03-03","cited_by_count":5,"area":null},{"id":"2408.08261","title":"mhGPT: A Lightweight Generative Pre-Trained Transformer for Mental Health Text Analysis","created":"2024-08-15","cited_by_count":5,"area":null},{"id":"2411.18065","title":"FlexiBit: Fully Flexible Precision Bit-parallel Accelerator Architecture for Arbitrary Mixed Precision AI","created":"2024-11-27","cited_by_count":5,"area":null},{"id":"2605.09825","title":"Pretraining large language models with MXFP4 on Native FP4 Hardware","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2606.11780","title":"What Limits Does Quantization Place on Dense Top-$k$ Retrieval? A Theoretical Study","created":"2026-06-10","cited_by_count":4,"area":null},{"id":"2401.07598","title":"MAPLE: Multilingual Evaluation of Parameter Efficient Finetuning of Large Language Models","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2507.17417","title":"A Comprehensive Evaluation on Quantization Techniques for Large Language Models","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2403.19591","title":"Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers","created":"2024-03-28","cited_by_count":2,"area":null},{"id":"2502.16627","title":"Energy-Efficient Transformer Inference: Optimization Strategies for Time Series Classification","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2601.00245","title":"Modern Neuromorphic AI: From Intra-Token to Inter-Token Processing","created":"2026-01-01","cited_by_count":2,"area":null},{"id":"2602.17681","title":"LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2603.08747","title":"Diagnosing FP4 inference: a layer-wise and block-wise sensitivity analysis of NVFP4 and MXFP4","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2608.01847","title":"FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2403.07339","title":"IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2505.16335","title":"FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2604.04523","title":"LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2405.05957","title":"OpenBA-V2: Reaching 77.3% High Compression Ratio with Fast Multi-Stage Pruning","created":"2024-05-09","cited_by_count":0,"area":null},{"id":"2407.00467","title":"VcLLM: Video Codecs are Secretly Tensor Codecs","created":"2024-06-29","cited_by_count":0,"area":null},{"id":"2409.02711","title":"Creating a Gen-AI based Track and Trace Assistant MVP (SuperTracy) for PostNL","created":"2024-09-04","cited_by_count":0,"area":null},{"id":"2506.21119","title":"Progtuning: Progressive Fine-tuning Framework for Transformer-based Language Models","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2511.21736","title":"R2Q: Towards Robust 2-Bit Large Language Models via Residual Refinement Quantization","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2512.15226","title":"Yes-MT's Submission to the Low-Resource Indic Language Translation Shared Task in WMT 2024","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2601.06724","title":"DS-CIM: Digital Stochastic Computing-In-Memory Featuring Accurate OR-Accumulation via Sample Region Remapping for Edge AI Models","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2603.28239","title":"A Switch-Centric In-Network Architecture for Accelerating LLM Inference in Shared-Memory Network","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.17745","title":"StatQAT: Statistical Quantizer Optimization for Deep Networks","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.15241","title":"Beyond the Leaderboard: Design Lessons for Trustworthy Multimodal VQA","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.12953","title":"Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2610.02511","title":"Post-Training Quantization of Autoregressive Weather Models","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}