{"total":39,"rows":[{"id":"2304.01089","title":"RPTQ: Reorder-based Post-training Quantization for Large Language Models","created":"2023-04-03","cited_by_count":116,"area":null},{"id":"2304.07493","title":"OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization","created":"2023-04-15","cited_by_count":92,"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":"2406.12930","title":"Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization","created":"2024-06-16","cited_by_count":28,"area":null},{"id":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"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":"2302.03213","title":"LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup","created":"2023-02-07","cited_by_count":20,"area":null},{"id":"2405.03103","title":"Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2408.06003","title":"LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference","created":"2024-08-12","cited_by_count":18,"area":null},{"id":"2411.11745","title":"BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration","created":"2024-11-18","cited_by_count":18,"area":null},{"id":"2411.15707","title":"Nimbus: Secure and Efficient Two-Party Inference for Transformers","created":"2024-11-24","cited_by_count":16,"area":null},{"id":"2502.18755","title":"M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type","created":"2025-02-26","cited_by_count":16,"area":null},{"id":"2505.06901","title":"Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-aware Cache Compression","created":"2025-05-11","cited_by_count":14,"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":"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":"2601.19213","title":"M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization","created":"2026-01-27","cited_by_count":8,"area":null},{"id":"2403.05465","title":"Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN Inference","created":"2024-03-08","cited_by_count":7,"area":null},{"id":"2508.15008","title":"Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications","created":"2025-08-20","cited_by_count":7,"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":"2412.10059","title":"Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity","created":"2024-12-13","cited_by_count":5,"area":null},{"id":"2505.10909","title":"Phi: Leveraging Pattern-based Hierarchical Sparsity for High-Efficiency Spiking Neural Networks","created":"2025-05-16","cited_by_count":5,"area":null},{"id":"2603.28765","title":"Adaptive Block-Scaled Data Types","created":"2026-03-30","cited_by_count":4,"area":null},{"id":"2307.11128","title":"Approximate Computing Survey, Part II: Application-Specific & Architectural Approximation Techniques and Applications","created":"2023-07-20","cited_by_count":3,"area":null},{"id":"2409.05227","title":"BBS: Bi-directional Bit-level Sparsity for Deep Learning Acceleration","created":"2024-09-08","cited_by_count":3,"area":null},{"id":"2511.06838","title":"P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2209.10778","title":"Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training","created":"2022-09-22","cited_by_count":2,"area":null},{"id":"2302.12510","title":"DyBit: Dynamic Bit-Precision Numbers for Efficient Quantized Neural Network Inference","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2406.16299","title":"Compensate Quantization Errors: Make Weights Hierarchical to Compensate Each Other","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2511.21910","title":"Platinum: Path-Adaptable LUT-Based Accelerator Tailored for Low-Bit Weight Matrix Multiplication","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2605.24144","title":"EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2305.17408","title":"AdaptGear: Accelerating GNN Training via Adaptive Subgraph-Level Kernels on GPUs","created":"2023-05-27","cited_by_count":1,"area":null},{"id":"2508.18850","title":"ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2601.20317","title":"VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2401.13714","title":"Value-Driven Mixed-Precision Quantization for Patch-Based Inference on Microcontrollers","created":"2024-01-24","cited_by_count":0,"area":null},{"id":"2407.15508","title":"Compensate Quantization Errors+: Quantized Models Are Inquisitive Learners","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2510.08449","title":"Hierarchical Spatial Algorithms for High-Resolution Image Quantization and Feature Extraction","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2605.20802","title":"ELSA: An ELastic SNN Inference Architecture for Efficient Neuromorphic Computing","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2608.03867","title":"Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.04724","title":"FlexPosit: Tunable Fractional Precision for LLM Inference Accelerators","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":null}