{"total":168,"rows":[{"id":"2306.03078","title":"SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression","created":"2023-06-05","cited_by_count":367,"area":null},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322,"area":null},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242,"area":null},{"id":"2103.03098","title":"Accounting for Variance in Machine Learning Benchmarks","created":"2021-03-01","cited_by_count":201,"area":null},{"id":"2207.10062","title":"DataPerf: Benchmarks for Data-Centric AI Development","created":"2022-07-20","cited_by_count":90,"area":null},{"id":"2110.01406","title":"MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation","created":"2021-09-29","cited_by_count":88,"area":null},{"id":"2104.05158","title":"Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models","created":"2021-04-12","cited_by_count":78,"area":null},{"id":"2101.11714","title":"TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models","created":"2021-01-25","cited_by_count":58,"area":null},{"id":"2107.08147","title":"AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learning","created":"2021-07-16","cited_by_count":39,"area":null},{"id":"2406.15486","title":"SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention","created":"2024-06-17","cited_by_count":39,"area":null},{"id":"2403.12844","title":"MELTing point: Mobile Evaluation of Language Transformers","created":"2024-03-19","cited_by_count":36,"area":null},{"id":"2504.03360","title":"Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency","created":"2025-04-04","cited_by_count":34,"area":null},{"id":"2201.10095","title":"RecShard: Statistical Feature-Based Memory Optimization for Industry-Scale Neural Recommendation","created":"2022-01-25","cited_by_count":28,"area":null},{"id":"2304.04640","title":"NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems","created":"2023-04-10","cited_by_count":27,"area":null},{"id":"2309.11932","title":"A Machine Learning-oriented Survey on Tiny Machine Learning","created":"2023-09-21","cited_by_count":27,"area":null},{"id":"2105.09750","title":"Anchor-based Plain Net for Mobile Image Super-Resolution","created":"2021-05-20","cited_by_count":24,"area":null},{"id":"2210.01970","title":"Evaluate & Evaluation on the Hub: Better Best Practices for Data and Model Measurements","created":"2022-09-30","cited_by_count":22,"area":null},{"id":"2311.12833","title":"HPC-GPT: Integrating Large Language Model for High-Performance Computing","created":"2023-10-03","cited_by_count":22,"area":null},{"id":"2512.03024","title":"TokenPowerBench: Benchmarking the Power Consumption of LLM Inference","created":"2025-12-02","cited_by_count":22,"area":null},{"id":"2501.08219","title":"Characterizing LLM Inference Energy-Performance Tradeoffs across Workloads and GPU Scaling","created":"2025-01-14","cited_by_count":19,"area":null},{"id":"2505.22126","title":"SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Model","created":"2025-05-28","cited_by_count":19,"area":null},{"id":"2109.08957","title":"AI Accelerator Survey and Trends","created":"2021-09-18","cited_by_count":17,"area":null},{"id":"2310.18329","title":"Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices","created":"2023-10-19","cited_by_count":17,"area":null},{"id":"2401.16677","title":"T3: Transparent Tracking & Triggering for Fine-grained Overlap of Compute & Collectives","created":"2024-01-30","cited_by_count":16,"area":null},{"id":"2410.12032","title":"MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI","created":"2024-10-15","cited_by_count":16,"area":null},{"id":"2110.11466","title":"MLPerf HPC: A Holistic Benchmark Suite for Scientific Machine Learning on HPC Systems","created":"2021-10-21","cited_by_count":15,"area":null},{"id":"2211.08675","title":"XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse","created":"2022-11-16","cited_by_count":14,"area":null},{"id":"2410.02425","title":"LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services","created":"2024-10-03","cited_by_count":14,"area":null},{"id":"2311.03687","title":"Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models","created":"2023-11-07","cited_by_count":12,"area":null},{"id":"2302.06117","title":"The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment","created":"2023-02-13","cited_by_count":11,"area":null},{"id":"2109.01262","title":"On the Accuracy of Analog Neural Network Inference Accelerators","created":"2021-09-03","cited_by_count":10,"area":null},{"id":"2302.10872","title":"MP-Rec: Hardware-Software Co-Design to Enable Multi-Path Recommendation","created":"2023-02-21","cited_by_count":9,"area":null},{"id":"2310.04467","title":"Design Principles for Lifelong Learning AI Accelerators","created":"2023-10-05","cited_by_count":9,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2504.15465","title":"LithOS: An Operating System for Efficient Machine Learning on GPUs","created":"2025-04-21","cited_by_count":9,"area":null},{"id":"2603.16952","title":"Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies","created":"2026-03-16","cited_by_count":9,"area":null},{"id":"2212.03414","title":"DREAM: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloads","created":"2022-12-07","cited_by_count":8,"area":null},{"id":"2305.05843","title":"MoCA: Memory-Centric, Adaptive Execution for Multi-Tenant Deep Neural Networks","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2403.07953","title":"Enabling Unstructured Sparse Acceleration on Structured Sparse Accelerators","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2411.13055","title":"Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training","created":"2024-11-20","cited_by_count":8,"area":null},{"id":"2506.01774","title":"Greening AI-enabled Systems with Software Engineering: A Research Agenda for Environmentally Sustainable AI Practices","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2105.12676","title":"Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale","created":"2021-05-26","cited_by_count":7,"area":null},{"id":"2307.09701","title":"Efficiency Pentathlon: A Standardized Arena for Efficiency Evaluation","created":"2023-07-19","cited_by_count":7,"area":null},{"id":"2407.20421","title":"Event-based Optical Flow on Neuromorphic Processor: ANN vs. SNN Comparison based on Activation Sparsification","created":"2024-07-29","cited_by_count":7,"area":null},{"id":"2111.04779","title":"ML-EXray: Visibility into ML Deployment on the Edge","created":"2021-11-08","cited_by_count":6,"area":null},{"id":"2202.05048","title":"Quantune: Post-training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deployment","created":"2022-02-10","cited_by_count":6,"area":null},{"id":"2204.07288","title":"Characterizing the Efficiency vs. Accuracy Trade-off for Long-Context NLP Models","created":"2022-04-15","cited_by_count":6,"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":"2310.11096","title":"Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads","created":"2023-10-17","cited_by_count":6,"area":null},{"id":"2405.00790","title":"SCAR: Scheduling Multi-Model AI Workloads on Heterogeneous Multi-Chiplet Module Accelerators","created":"2024-05-01","cited_by_count":6,"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":"2301.04122","title":"Mystique: Enabling Accurate and Scalable Generation of Production AI Benchmarks","created":"2022-12-16","cited_by_count":5,"area":null},{"id":"2310.18481","title":"MOSEL: Inference Serving Using Dynamic Modality Selection","created":"2023-10-27","cited_by_count":5,"area":null},{"id":"2205.06287","title":"Adaptive Block Floating-Point for Analog Deep Learning Hardware","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2303.05016","title":"Performance Characterization of using Quantization for DNN Inference on Edge Devices: Extended Version","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2306.11426","title":"Exploring the Performance and Efficiency of Transformer Models for NLP on Mobile Devices","created":"2023-06-20","cited_by_count":4,"area":null},{"id":"2404.11788","title":"Understanding the Performance Horizon of the Latest ML Workloads with NonGEMM Workloads","created":"2024-04-17","cited_by_count":4,"area":null},{"id":"2406.13868","title":"SDQ: Sparse Decomposed Quantization for LLM Inference","created":"2024-06-19","cited_by_count":4,"area":null},{"id":"2411.17712","title":"Generative AI on the Edge: Architecture and Performance Evaluation","created":"2024-11-18","cited_by_count":4,"area":null},{"id":"2505.15622","title":"Benchmarking Energy and Latency in TinyML: A Novel Method for Resource-Constrained AI","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2511.16682","title":"Bench360: Benchmarking Local LLM Inference from 360 Degrees","created":"2025-11-12","cited_by_count":4,"area":null},{"id":"2603.23640","title":"LLM Inference at the Edge: Mobile, NPU, and GPU Performance Efficiency Trade-offs Under Sustained Load","created":"2026-03-24","cited_by_count":4,"area":null},{"id":"2104.08335","title":"Demystifying BERT: Implications for Accelerator Design","created":"2021-04-14","cited_by_count":3,"area":null},{"id":"2105.01353","title":"One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment","created":"2021-05-04","cited_by_count":3,"area":null},{"id":"2112.09780","title":"Exploring the Impact of Virtualization on the Usability of the Deep Learning Applications","created":"2021-12-17","cited_by_count":3,"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":"2204.05839","title":"The MIT Supercloud Workload Classification Challenge","created":"2022-04-12","cited_by_count":3,"area":null},{"id":"2204.13971","title":"Cost Effective MLaaS Federation: A Combinatorial Reinforcement Learning Approach","created":"2022-04-29","cited_by_count":3,"area":null},{"id":"2205.03347","title":"Zhuyi: Perception Processing Rate Estimation for Safety in Autonomous Vehicles","created":"2022-05-06","cited_by_count":3,"area":null},{"id":"2210.05889","title":"KAIROS: Building Cost-Efficient Machine Learning Inference Systems with Heterogeneous Cloud Resources","created":"2022-10-12","cited_by_count":3,"area":null},{"id":"2302.01382","title":"Mixed Precision Post Training Quantization of Neural Networks with Sensitivity Guided Search","created":"2023-02-02","cited_by_count":3,"area":null},{"id":"2306.04879","title":"Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization","created":"2023-06-08","cited_by_count":3,"area":null},{"id":"2309.07181","title":"The Grand Illusion: The Myth of Software Portability and Implications for ML Progress","created":"2023-09-12","cited_by_count":3,"area":null},{"id":"2309.10759","title":"A Blueprint for Precise and Fault-Tolerant Analog Neural Networks","created":"2023-09-19","cited_by_count":3,"area":null},{"id":"2311.09690","title":"CDMPP: A Device-Model Agnostic Framework for Latency Prediction of Tensor Programs","created":"2023-11-16","cited_by_count":3,"area":null},{"id":"2404.10386","title":"I/O in Machine Learning Applications on HPC Systems: A 360-degree Survey","created":"2024-04-16","cited_by_count":3,"area":null},{"id":"2409.19432","title":"MicroFlow: An Efficient Rust-Based Inference Engine for TinyML","created":"2024-09-28","cited_by_count":3,"area":null},{"id":"2501.12407","title":"The Streaming Batch Model for Efficient and Fault-Tolerant Heterogeneous Execution","created":"2025-01-16","cited_by_count":3,"area":null},{"id":"2503.09114","title":"Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edge","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2506.02032","title":"Towards Secure MLOps: Surveying Attacks, Mitigation Strategies, and Research Challenges","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2507.07031","title":"ZKTorch: Compiling ML Inference to Zero-Knowledge Proofs via Parallel Proof Accumulation","created":"2025-07-09","cited_by_count":3,"area":null},{"id":"2512.11588","title":"AI Benchmark Democratization and Carpentry","created":"2025-12-12","cited_by_count":3,"area":null},{"id":"2603.20174","title":"TinyML Enhances CubeSat Mission Capabilities","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2603.21493","title":"StreamingEval: A Unified Evaluation Protocol towards Realistic Streaming Video Understanding","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2606.14516","title":"Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results","created":"2026-06-12","cited_by_count":3,"area":null},{"id":"2608.29235","title":"Uncertainty-Aware Multimodal Anti-UAV Detection via Evidential Fusion and Conflict-Discounted Belief Aggregation","created":"2026-08-29","cited_by_count":3,"area":null},{"id":"2110.00459","title":"Characterizing Concurrency Mechanisms for NVIDIA GPUs under Deep Learning Workloads","created":"2021-10-01","cited_by_count":2,"area":null},{"id":"2210.04323","title":"Deep Learning Inference Frameworks Benchmark","created":"2022-10-09","cited_by_count":2,"area":null},{"id":"2402.07585","title":"Identifying architectural design decisions for achieving green ML serving","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2403.02327","title":"Model Lakes","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2404.15153","title":"Performance Characterization of Expert Router for Scalable LLM Inference","created":"2024-04-22","cited_by_count":2,"area":null},{"id":"2408.04104","title":"Hardware-Assisted Virtualization of Neural Processing Units for Cloud Platforms","created":"2024-08-07","cited_by_count":2,"area":null},{"id":"2409.12994","title":"Performance and Power: Systematic Evaluation of AI Workloads on Accelerators with CARAML","created":"2024-09-19","cited_by_count":2,"area":null},{"id":"2506.11441","title":"DPUV4E: High-Throughput DPU Architecture Design for CNN on Versal ACAP","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2511.05614","title":"An MLCommons Scientific Benchmarks Ontology","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2104.02188","title":"GPU Domain Specialization via Composable On-Package Architecture","created":"2021-04-05","cited_by_count":1,"area":null},{"id":"2105.03176","title":"ANNETTE: Accurate Neural Network Execution Time Estimation with Stacked Models","created":"2021-05-07","cited_by_count":1,"area":null},{"id":"2111.05231","title":"MLHarness: A Scalable Benchmarking System for MLCommons","created":"2021-11-09","cited_by_count":1,"area":null},{"id":"2202.11243","title":"MLProxy: SLA-Aware Reverse Proxy for Machine Learning Inference Serving on Serverless Computing Platforms","created":"2022-02-23","cited_by_count":1,"area":null},{"id":"2207.11434","title":"RIBBON: Cost-Effective and QoS-Aware Deep Learning Model Inference using a Diverse Pool of Cloud Computing Instances","created":"2022-07-23","cited_by_count":1,"area":null}],"next_cursor":"100"}