{"total":40,"rows":[{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2101.09336","title":"A Comprehensive Survey on Hardware-Aware Neural Architecture Search","created":"2021-01-22","cited_by_count":61,"area":null},{"id":"2112.01771","title":"Understanding Performance Problems in Deep Learning Systems","created":"2021-12-03","cited_by_count":12,"area":null},{"id":"2205.10364","title":"Learning to Reverse DNNs from AI Programs Automatically","created":"2022-05-20","cited_by_count":12,"area":null},{"id":"2202.09947","title":"Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation","created":"2022-02-21","cited_by_count":10,"area":null},{"id":"2104.05755","title":"Tensor Processing Primitives: A Programming Abstraction for Efficiency and Portability in Deep Learning & HPC Workloads","created":"2021-04-12","cited_by_count":9,"area":null},{"id":"2301.13062","title":"Operator Fusion in XLA: Analysis and Evaluation","created":"2023-01-30","cited_by_count":9,"area":null},{"id":"2307.04963","title":"DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization","created":"2023-07-11","cited_by_count":9,"area":null},{"id":"2309.15467","title":"Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey","created":"2023-09-27","cited_by_count":8,"area":null},{"id":"2210.01075","title":"Decompiling x86 Deep Neural Network Executables","created":"2022-10-03","cited_by_count":7,"area":null},{"id":"2210.04024","title":"Demand Layering for Real-Time DNN Inference with Minimized Memory Usage","created":"2022-10-08","cited_by_count":7,"area":null},{"id":"2301.01333","title":"oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation","created":"2023-01-03","cited_by_count":7,"area":null},{"id":"2204.09514","title":"Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems","created":"2022-04-18","cited_by_count":6,"area":null},{"id":"2301.04020","title":"Quant 4.0: Engineering Quantitative Investment with Automated, Explainable and Knowledge-driven Artificial Intelligence","created":"2022-12-13","cited_by_count":6,"area":null},{"id":"2404.17871","title":"Deep Learning Library Testing: Definition, Methods and Challenges","created":"2024-04-27","cited_by_count":5,"area":null},{"id":"2202.09888","title":"Benchmarking the Linear Algebra Awareness of TensorFlow and PyTorch","created":"2022-02-20","cited_by_count":3,"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":"2603.23566","title":"AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2204.01386","title":"Dressi: A Hardware-Agnostic Differentiable Renderer with Reactive Shader Packing and Soft Rasterization","created":"2022-04-04","cited_by_count":2,"area":null},{"id":"2210.13086","title":"Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2504.20198","title":"Leveraging Neural Graph Compilers in Machine Learning Research for Edge-Cloud Systems","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2602.19762","title":"Hexagon-MLIR: An AI Compilation Stack For Qualcomm's Neural Processing Units (NPUs)","created":"2026-02-23","cited_by_count":2,"area":null},{"id":"2104.04576","title":"Compiler Toolchains for Deep Learning Workloads on Embedded Platforms","created":"2021-03-08","cited_by_count":1,"area":null},{"id":"2204.11981","title":"End-to-end Mapping in Heterogeneous Systems Using Graph Representation Learning","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2212.08482","title":"Implementation of general formal translators","created":"2022-12-16","cited_by_count":1,"area":null},{"id":"2308.14364","title":"Target-independent XLA optimization using Reinforcement Learning","created":"2023-08-28","cited_by_count":1,"area":null},{"id":"2310.17408","title":"Tackling the Matrix Multiplication Micro-kernel Generation with Exo","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2403.13839","title":"depyf: Open the Opaque Box of PyTorch Compiler for Machine Learning Researchers","created":"2024-03-14","cited_by_count":1,"area":null},{"id":"2503.08700","title":"Real-Time Semantic Segmentation of Aerial Images Using an Embedded U-Net: A Comparison of CPU, GPU, and FPGA Workflows","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2505.04502","title":"Leveraging Simultaneous Usage of Edge GPU Hardware Engines for Video Face Detection and Recognition","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2605.29357","title":"PassNet: Scaling Large Language Models for Graph Compiler Pass Generation","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2609.10550","title":"Optimizing AI Inference Across the Deployment Stack","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2201.00194","title":"FamilySeer: Towards Optimized Tensor Codes by Exploiting Computation Subgraph Similarity","created":"2022-01-01","cited_by_count":0,"area":null},{"id":"2509.06402","title":"NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2510.24035","title":"GraphNet: A Large-Scale Computational Graph Dataset for Tensor Compiler Research","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2605.31500","title":"On Efficient Scaling of GNNs via IO-Aware Layers Implementations","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.28293","title":"Filling the Pareto-Optimal Front for Affordance Segmentation on Embedded Devices Using RGB-D Cameras","created":"2026-07-30","cited_by_count":0,"area":null}],"next_cursor":null}