{"total":30,"rows":[{"id":"2206.00820","title":"NIPQ: Noise proxy-based Integrated Pseudo-Quantization","created":"2022-06-02","cited_by_count":35,"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":"2205.04711","title":"SmartSAGE: Training Large-scale Graph Neural Networks using In-Storage Processing Architectures","created":"2022-05-10","cited_by_count":13,"area":null},{"id":"2409.08290","title":"Reconsidering the Energy Efficiency of Spiking Neural Networks Inference from Analytical Perspectives","created":"2024-08-29","cited_by_count":13,"area":null},{"id":"2209.00606","title":"Sparse Attention Acceleration with Synergistic In-Memory Pruning and On-Chip Recomputation","created":"2022-09-01","cited_by_count":12,"area":null},{"id":"2204.03227","title":"Accelerating Attention through Gradient-Based Learned Runtime Pruning","created":"2022-04-07","cited_by_count":8,"area":null},{"id":"2209.08938","title":"Accelerating Neural Network Inference with Processing-in-DRAM: From the Edge to the Cloud","created":"2022-09-19","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":"2101.11748","title":"Rethinking Floating Point Overheads for Mixed Precision DNN Accelerators","created":"2021-01-27","cited_by_count":4,"area":null},{"id":"2112.12630","title":"A Survey of Near-Data Processing Architectures for Neural Networks","created":"2021-12-23","cited_by_count":4,"area":null},{"id":"2206.06022","title":"Machine Learning Training on a Real Processing-in-Memory System","created":"2022-06-13","cited_by_count":4,"area":null},{"id":"2401.12428","title":"CIM-MLC: A Multi-level Compilation Stack for Computing-In-Memory Accelerators","created":"2024-01-23","cited_by_count":3,"area":null},{"id":"2207.07886","title":"An Experimental Evaluation of Machine Learning Training on a Real Processing-in-Memory System","created":"2022-07-16","cited_by_count":2,"area":null},{"id":"2508.08822","title":"OISMA: On-the-fly In-memory Stochastic Multiplication Architecture for Matrix-Multiplication Workloads","created":"2025-08-12","cited_by_count":2,"area":null},{"id":"2604.18137","title":"AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization","created":"2026-04-20","cited_by_count":2,"area":null},{"id":"2103.03953","title":"ODIN: A Bit-Parallel Stochastic Arithmetic Based Accelerator for In-Situ Neural Network Processing in Phase Change RAM","created":"2021-03-05","cited_by_count":1,"area":null},{"id":"2105.12781","title":"ATRIA: A Bit-Parallel Stochastic Arithmetic Based Accelerator for In-DRAM CNN Processing","created":"2021-05-26","cited_by_count":1,"area":null},{"id":"2205.14664","title":"Heterogeneous Data-Centric Architectures for Modern Data-Intensive Applications: Case Studies in Machine Learning and Databases","created":"2022-05-29","cited_by_count":1,"area":null},{"id":"2301.06193","title":"RedBit: An End-to-End Flexible Framework for Evaluating the Accuracy of Quantized CNNs","created":"2023-01-15","cited_by_count":1,"area":null},{"id":"2304.01951","title":"TransPimLib: A Library for Efficient Transcendental Functions on Processing-in-Memory Systems","created":"2023-04-03","cited_by_count":1,"area":null},{"id":"2305.07376","title":"DAISM: Digital Approximate In-SRAM Multiplier-based Accelerator for DNN Training and Inference","created":"2023-05-12","cited_by_count":1,"area":null},{"id":"2407.12638","title":"ARTEMIS: A Mixed Analog-Stochastic In-DRAM Accelerator for Transformer Neural Networks","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2410.23082","title":"An Event-Based Digital Compute-In-Memory Accelerator with Flexible Operand Resolution and Layer-Wise Weight/Output Stationarity","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2511.17265","title":"DISCA: A Digital In-memory Stochastic Computing Architecture Using A Compressed Bent-Pyramid Format","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2411.06846","title":"OPTIMA: Design-Space Exploration of Discharge-Based In-SRAM Computing: Quantifying Energy-Accuracy Trade-Offs","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2411.19114","title":"PREBA: A Hardware/Software Co-Design for Multi-Instance GPU based AI Inference Servers","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2507.01429","title":"Hardware-software co-exploration with racetrack memory based in-memory computing for CNN inference in embedded systems","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2601.00434","title":"Time--to--Digital Converter (TDC)--Based Resonant Compute--in--Memory for INT8 CNNs with Layer--Optimized SRAM Mapping","created":"2026-01-01","cited_by_count":0,"area":null},{"id":"2601.22876","title":"Matterhorn: Masked Time-to-First-Spike Encoding by Reassigning the Silent State for Sparse and Energy-Efficient Spiking Transformers","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2606.02781","title":"CRAM-ER: Error-Resilient Spintronic Computational Random Access Memory for Scalable In-Memory Computation","created":"2026-06-01","cited_by_count":0,"area":null}],"next_cursor":null}