{"total":245,"rows":[{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522,"area":null},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220,"area":null},{"id":"2405.05465","title":"Vidur: A Large-Scale Simulation Framework For LLM Inference","created":"2024-05-08","cited_by_count":117,"area":null},{"id":"2103.05633","title":"Proof-of-Learning: Definitions and Practice","created":"2021-03-09","cited_by_count":84,"area":null},{"id":"2111.03452","title":"Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports","created":"2021-11-04","cited_by_count":80,"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":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2106.11872","title":"Randomness In Neural Network Training: Characterizing The Impact of Tooling","created":"2021-06-22","cited_by_count":59,"area":null},{"id":"2509.14279","title":"Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization","created":"2025-09-16","cited_by_count":56,"area":"lr"},{"id":"2105.11118","title":"Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads","created":"2021-05-24","cited_by_count":51,"area":null},{"id":"2509.07506","title":"Astra: A Multi-Agent System for GPU Kernel Performance Optimization","created":"2025-09-09","cited_by_count":51,"area":"agents"},{"id":"2401.06197","title":"Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications","created":"2024-01-11","cited_by_count":50,"area":null},{"id":"2204.12013","title":"Bamboo: Making Preemptible Instances Resilient for Affordable Training of Large DNNs","created":"2022-04-26","cited_by_count":49,"area":null},{"id":"2103.04514","title":"Nondeterminism and Instability in Neural Network Optimization","created":"2021-03-08","cited_by_count":48,"area":null},{"id":"2210.06659","title":"Structural Pruning via Latency-Saliency Knapsack","created":"2022-10-13","cited_by_count":41,"area":null},{"id":"2405.05751","title":"Mirage: A Multi-Level Superoptimizer for Tensor Programs","created":"2024-05-09","cited_by_count":41,"area":null},{"id":"2103.14835","title":"LiBRe: A Practical Bayesian Approach to Adversarial Detection","created":"2021-03-27","cited_by_count":40,"area":null},{"id":"2207.04296","title":"TensorIR: An Abstraction for Automatic Tensorized Program Optimization","created":"2022-07-09","cited_by_count":38,"area":null},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2102.06253","title":"Continuum: Simple Management of Complex Continual Learning Scenarios","created":"2021-02-11","cited_by_count":33,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2205.13603","title":"Tensor Program Optimization with Probabilistic Programs","created":"2022-05-26","cited_by_count":30,"area":null},{"id":"2102.00527","title":"A Runtime-Based Computational Performance Predictor for Deep Neural Network Training","created":"2021-01-31","cited_by_count":29,"area":null},{"id":"2105.09564","title":"Dual-side Sparse Tensor Core","created":"2021-05-20","cited_by_count":29,"area":null},{"id":"2210.09603","title":"Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs","created":"2022-10-18","cited_by_count":28,"area":null},{"id":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","cited_by_count":28,"area":null},{"id":"2202.04736","title":"Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets","created":"2022-02-09","cited_by_count":27,"area":null},{"id":"2201.12465","title":"Flashlight: Enabling Innovation in Tools for Machine Learning","created":"2022-01-29","cited_by_count":25,"area":null},{"id":"2603.24517","title":"AVO: Agentic Variation Operators for Autonomous Evolutionary Search","created":"2026-03-25","cited_by_count":24,"area":"agents"},{"id":"2202.02326","title":"Towards Training Reproducible Deep Learning Models","created":"2022-02-04","cited_by_count":23,"area":null},{"id":"2108.09454","title":"\"Adversarial Examples\" for Proof-of-Learning","created":"2021-08-21","cited_by_count":20,"area":null},{"id":"2309.01172","title":"FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs","created":"2023-09-03","cited_by_count":20,"area":null},{"id":"2110.01397","title":"RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging","created":"2021-09-30","cited_by_count":19,"area":null},{"id":"2104.00749","title":"Anytime Dense Prediction with Confidence Adaptivity","created":"2021-04-01","cited_by_count":18,"area":null},{"id":"2110.15238","title":"Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance","created":"2021-10-25","cited_by_count":18,"area":null},{"id":"2105.11010","title":"Post-Training Sparsity-Aware Quantization","created":"2021-05-23","cited_by_count":17,"area":null},{"id":"2109.13227","title":"TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device","created":"2021-09-27","cited_by_count":17,"area":null},{"id":"2110.10221","title":"The CoRa Tensor Compiler: Compilation for Ragged Tensors with Minimal Padding","created":"2021-10-19","cited_by_count":17,"area":null},{"id":"2106.08630","title":"HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning","created":"2021-06-16","cited_by_count":16,"area":null},{"id":"2101.08734","title":"Clairvoyant Prefetching for Distributed Machine Learning I/O","created":"2021-01-21","cited_by_count":14,"area":null},{"id":"2101.07948","title":"SparseDNN: Fast Sparse Deep Learning Inference on CPUs","created":"2021-01-20","cited_by_count":13,"area":null},{"id":"2103.15750","title":"Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design","created":"2021-03-25","cited_by_count":13,"area":null},{"id":"2111.06705","title":"A compact butterfly-style silicon photonic-electronic neural chip for hardware-efficient deep learning","created":"2021-11-11","cited_by_count":13,"area":null},{"id":"2210.13763","title":"Teal: Learning-Accelerated Optimization of WAN Traffic Engineering","created":"2022-10-25","cited_by_count":13,"area":null},{"id":"2301.00330","title":"Efficient On-device Training via Gradient Filtering","created":"2023-01-01","cited_by_count":13,"area":null},{"id":"2603.12440","title":"KernelFoundry: Hardware-aware evolutionary GPU kernel optimization","created":"2026-03-12","cited_by_count":13,"area":null},{"id":"2102.06365","title":"Dynamic Precision Analog Computing for Neural Networks","created":"2021-02-12","cited_by_count":12,"area":null},{"id":"2109.13604","title":"Real-Time Glaucoma Detection from Digital Fundus Images using Self-ONNs","created":"2021-09-28","cited_by_count":12,"area":null},{"id":"2208.13764","title":"Temporal Label Smoothing for Early Event Prediction","created":"2022-08-29","cited_by_count":12,"area":null},{"id":"2211.02206","title":"Soft Masking for Cost-Constrained Channel Pruning","created":"2022-11-04","cited_by_count":12,"area":null},{"id":"2311.02103","title":"Relax: Composable Abstractions for End-to-End Dynamic Machine Learning","created":"2023-11-01","cited_by_count":12,"area":null},{"id":"2312.11537","title":"FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices with A Simple Super-Resolution Pipeline","created":"2023-12-15","cited_by_count":12,"area":null},{"id":"2503.01868","title":"Systems and Algorithms for Convolutional Multi-Hybrid Language Models at Scale","created":"2025-02-25","cited_by_count":12,"area":null},{"id":"2102.13267","title":"LazyTensor: combining eager execution with domain-specific compilers","created":"2021-02-26","cited_by_count":11,"area":null},{"id":"2108.03917","title":"LatticeNet: Fast Spatio-Temporal Point Cloud Segmentation Using Permutohedral Lattices","created":"2021-08-09","cited_by_count":11,"area":null},{"id":"2306.00854","title":"Spatio-Angular Convolutions for Super-resolution in Diffusion MRI","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2603.10085","title":"KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization","created":"2026-03-10","cited_by_count":11,"area":"agents"},{"id":"2102.07511","title":"GradPIM: A Practical Processing-in-DRAM Architecture for Gradient Descent","created":"2021-02-15","cited_by_count":10,"area":null},{"id":"2107.01715","title":"Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction","created":"2021-07-04","cited_by_count":10,"area":null},{"id":"2108.11033","title":"GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity","created":"2021-08-25","cited_by_count":10,"area":"inference"},{"id":"2108.11976","title":"JUWELS Booster -- A Supercomputer for Large-Scale AI Research","created":"2021-06-30","cited_by_count":10,"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":"2403.08618","title":"SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness","created":"2024-03-13","cited_by_count":10,"area":"safety"},{"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":"2105.13482","title":"FastRIFE: Optimization of Real-Time Intermediate Flow Estimation for Video Frame Interpolation","created":"2021-05-27","cited_by_count":9,"area":null},{"id":"2202.10935","title":"EF-Train: Enable Efficient On-device CNN Training on FPGA Through Data Reshaping for Online Adaptation or Personalization","created":"2022-02-18","cited_by_count":9,"area":null},{"id":"2209.04161","title":"ApproxTrain: Fast Simulation of Approximate Multipliers for DNN Training and Inference","created":"2022-09-09","cited_by_count":9,"area":null},{"id":"2302.08687","title":"VEGETA: Vertically-Integrated Extensions for Sparse/Dense GEMM Tile Acceleration on CPUs","created":"2023-02-17","cited_by_count":9,"area":null},{"id":"2309.16318","title":"DeepPCR: Parallelizing Sequential Operations in Neural Networks","created":"2023-09-28","cited_by_count":9,"area":"diffusion"},{"id":"2407.05941","title":"Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edge","created":"2024-07-01","cited_by_count":9,"area":"inference"},{"id":"2502.19405","title":"Verde: Verification via Refereed Delegation for Machine Learning Programs","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2102.02638","title":"Autodidactic Neurosurgeon: Collaborative Deep Inference for Mobile Edge Intelligence via Online Learning","created":"2021-02-02","cited_by_count":8,"area":null},{"id":"2110.10811","title":"HALP: Hardware-Aware Latency Pruning","created":"2021-10-20","cited_by_count":8,"area":null},{"id":"2112.03444","title":"GPU-Based Homotopy Continuation for Minimal Problems in Computer Vision","created":"2021-12-07","cited_by_count":8,"area":null},{"id":"2202.00774","title":"Accelerating DNN Training with Structured Data Gradient Pruning","created":"2022-02-01","cited_by_count":8,"area":null},{"id":"2202.13403","title":"A Multimodal German Dataset for Automatic Lip Reading Systems and Transfer Learning","created":"2022-02-27","cited_by_count":8,"area":null},{"id":"2111.04949","title":"A Survey and Empirical Evaluation of Parallel Deep Learning Frameworks","created":"2021-11-09","cited_by_count":7,"area":null},{"id":"2203.02549","title":"Structured Pruning is All You Need for Pruning CNNs at Initialization","created":"2022-03-04","cited_by_count":7,"area":null},{"id":"2210.01075","title":"Decompiling x86 Deep Neural Network Executables","created":"2022-10-03","cited_by_count":7,"area":null},{"id":"2406.09465","title":"Optimal Kernel Orchestration for Tensor Programs with Korch","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2410.12707","title":"FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression","created":"2024-10-16","cited_by_count":7,"area":null},{"id":"2106.07228","title":"Automated Parking Space Detection Using Convolutional Neural Networks","created":"2021-06-14","cited_by_count":6,"area":null},{"id":"2504.14519","title":"SlimPipe: Memory-Thrifty and Efficient Pipeline Parallelism for Long-Context LLM Training","created":"2025-04-20","cited_by_count":6,"area":null},{"id":"2507.12933","title":"DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization","created":"2025-07-17","cited_by_count":6,"area":"diffusion"},{"id":"2604.01489","title":"CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe","created":"2026-04-01","cited_by_count":6,"area":"agents"},{"id":"2109.07419","title":"Union: A Unified HW-SW Co-Design Ecosystem in MLIR for Evaluating Tensor Operations on Spatial Accelerators","created":"2021-09-15","cited_by_count":5,"area":null},{"id":"2201.05587","title":"Transfer-Tuning: Reusing Auto-Schedules for Efficient Tensor Program Code Generation","created":"2022-01-14","cited_by_count":5,"area":null},{"id":"2311.08902","title":"On the Importance of Step-wise Embeddings for Heterogeneous Clinical Time-Series","created":"2023-11-15","cited_by_count":5,"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":"2108.05580","title":"perf4sight: A toolflow to model CNN training performance on Edge GPUs","created":"2021-08-12","cited_by_count":4,"area":null},{"id":"2110.05060","title":"Two-level Group Convolution","created":"2021-10-11","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":"2208.12392","title":"DiVa: An Accelerator for Differentially Private Machine Learning","created":"2022-08-26","cited_by_count":4,"area":null},{"id":"2305.07522","title":"SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving","created":"2023-05-12","cited_by_count":4,"area":null},{"id":"2305.19592","title":"Integrated multi-operand optical neurons for scalable and hardware-efficient deep learning","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2311.11390","title":"Addressing the speed-accuracy simulation trade-off for adaptive spiking neurons","created":"2023-11-19","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":"2506.12355","title":"QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm","created":"2025-06-14","cited_by_count":4,"area":null},{"id":"2507.05411","title":"AXLearn: Modular, Hardware-Agnostic Large Model Training","created":"2025-07-07","cited_by_count":4,"area":null},{"id":"2511.16964","title":"Optimizing PyTorch Inference with LLM-Based Multi-Agent Systems","created":"2025-11-21","cited_by_count":4,"area":"agents"}],"next_cursor":"100"}