{"list":"other","total":52,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2401.09670","title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving","created":"2024-01-18","cited_by_count":617},{"id":"2006.06762","title":"Ansor: Generating High-Performance Tensor Programs for Deep Learning","created":"2020-06-11","cited_by_count":201},{"id":"1805.08166","title":"Learning to Optimize Tensor Programs","created":"2018-05-21","cited_by_count":140},{"id":"2002.05786","title":"Deep Learning for Financial Applications : A Survey","created":"2020-02-09","cited_by_count":91},{"id":"2403.00579","title":"NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing","created":"2024-03-01","cited_by_count":52},{"id":"2207.04606","title":"SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning","created":"2022-07-11","cited_by_count":47},{"id":"2410.18038","title":"POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference","created":"2024-10-23","cited_by_count":47},{"id":"1908.03072","title":"TensorDIMM: A Practical Near-Memory Processing Architecture for Embeddings and Tensor Operations in Deep Learning","created":"2019-08-08","cited_by_count":43},{"id":"2207.04296","title":"TensorIR: An Abstraction for Automatic Tensorized Program Optimization","created":"2022-07-09","cited_by_count":38},{"id":"2411.01142","title":"NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM Inference","created":"2024-11-02","cited_by_count":37},{"id":"2012.03112","title":"A Modern Primer on Processing in Memory","created":"2020-12-05","cited_by_count":32},{"id":"2001.02319","title":"Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey","created":"2020-01-08","cited_by_count":30},{"id":"2205.13603","title":"Tensor Program Optimization with Probabilistic Programs","created":"2022-05-26","cited_by_count":30},{"id":"2308.11030","title":"Ramulator 2.0: A Modern, Modular, and Extensible DRAM Simulator","created":"2023-08-21","cited_by_count":30},{"id":"2001.08743","title":"Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation","created":"2020-01-23","cited_by_count":29},{"id":"2210.09603","title":"Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs","created":"2022-10-18","cited_by_count":28},{"id":"2109.14320","title":"Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottlenecks","created":"2021-09-29","cited_by_count":23},{"id":"2502.07578","title":"PIM Is All You Need: A CXL-Enabled GPU-Free System for Large Language Model Inference","created":"2025-02-11","cited_by_count":22},{"id":"1903.03988","title":"Processing Data Where It Makes Sense: Enabling In-Memory Computation","created":"2019-03-10","cited_by_count":21},{"id":"2010.04804","title":"A Tensor Compiler for Unified Machine Learning Prediction Serving","created":"2020-10-09","cited_by_count":20},{"id":"2502.15470","title":"PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System","created":"2025-02-21","cited_by_count":20},{"id":"2110.15238","title":"Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance","created":"2021-10-25","cited_by_count":18},{"id":"2104.07582","title":"SISA: Set-Centric Instruction Set Architecture for Graph Mining on Processing-in-Memory Systems","created":"2021-04-15","cited_by_count":17},{"id":"2503.06433","title":"Seesaw: High-throughput LLM Inference via Model Re-sharding","created":"2025-03-09","cited_by_count":15},{"id":"2308.00846","title":"Pathfinding Future PIM Architectures by Demystifying a Commercial PIM Technology","created":"2023-08-01","cited_by_count":14},{"id":"2503.18599","title":"Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization","created":"2025-03-24","cited_by_count":14},{"id":"2110.01709","title":"Benchmarking Memory-Centric Computing Systems: Analysis of Real Processing-in-Memory Hardware","created":"2021-10-04","cited_by_count":13},{"id":"2410.15008","title":"IANUS: Integrated Accelerator based on NPU-PIM Unified Memory System","created":"2024-10-19","cited_by_count":13},{"id":"1711.01177","title":"GRIM-Filter: Fast Seed Location Filtering in DNA Read Mapping Using Processing-in-Memory Technologies","created":"2017-11-02","cited_by_count":11},{"id":"2105.03725","title":"DAMOV: A New Methodology and Benchmark Suite for Evaluating Data Movement Bottlenecks","created":"2021-05-08","cited_by_count":10},{"id":"2009.07692","title":"GenASM: A High-Performance, Low-Power Approximate String Matching Acceleration Framework for Genome Sequence Analysis","created":"2020-09-16","cited_by_count":9},{"id":"2101.07557","title":"SynCron: Efficient Synchronization Support for Near-Data-Processing Architectures","created":"2021-01-19","cited_by_count":9},{"id":"2508.07227","title":"LP-Spec: Leveraging LPDDR PIM for Efficient LLM Mobile Speculative Inference with Architecture-Dataflow Co-Optimization","created":"2025-08-10","cited_by_count":9},{"id":"2507.10178","title":"Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving","created":"2025-07-14","cited_by_count":7},{"id":"2111.00680","title":"GNNear: Accelerating Full-Batch Training of Graph Neural Networks with Near-Memory Processing","created":"2021-11-01","cited_by_count":6},{"id":"2208.01243","title":"A Framework for High-throughput Sequence Alignment using Real Processing-in-Memory Systems","created":"2022-08-02","cited_by_count":5},{"id":"2301.07486","title":"CINM (Cinnamon): A Compilation Infrastructure for Heterogeneous Compute In-Memory and Compute Near-Memory Paradigms","created":"2022-12-25","cited_by_count":5},{"id":"2310.01893","title":"SimplePIM: A Software Framework for Productive and Efficient Processing-in-Memory","created":"2023-10-03","cited_by_count":5},{"id":"2407.16847","title":"SPLAT: A framework for optimised GPU code-generation for SParse reguLar ATtention","created":"2024-07-23","cited_by_count":5},{"id":"2504.16112","title":"HPU: High-Bandwidth Processing Unit for Scalable, Cost-effective LLM Inference via GPU Co-processing","created":"2025-04-18","cited_by_count":5},{"id":"2409.06204","title":"PIM-MMU: A Memory Management Unit for Accelerating Data Transfers in Commercial PIM Systems","created":"2024-09-10","cited_by_count":4},{"id":"2505.00458","title":"Memory-Centric Computing: Solving Computing's Memory Problem","created":"2025-05-01","cited_by_count":4},{"id":"2404.08871","title":"PID-Comm: A Fast and Flexible Collective Communication Framework for Commodity Processing-in-DIMM Devices","created":"2024-04-13","cited_by_count":3},{"id":"2501.09242","title":"Holistic Optimization Framework for FPGA Accelerators","created":"2025-01-16","cited_by_count":3},{"id":"1905.04376","title":"Enabling Practical Processing in and near Memory for Data-Intensive Computing","created":"2019-05-02","cited_by_count":2},{"id":"2211.10516","title":"PIM-tree: A Skew-resistant Index for Processing-in-Memory","created":"2022-11-18","cited_by_count":2},{"id":"2501.09902","title":"Multi-Dimensional Vector ISA Extension for Mobile In-Cache Computing","created":"2025-01-17","cited_by_count":2},{"id":"2305.13970","title":"Darwin: A DRAM-based Multi-level Processing-in-Memory Architecture for Data Analytics","created":"2023-05-23","cited_by_count":1},{"id":"2412.19630","title":"ATiM: Autotuning Tensor Programs for Processing-in-DRAM","created":"2024-12-27","cited_by_count":1}],"next_cursor":null}