{"total":426,"rows":[{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653,"area":"inference"},{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578,"area":"lr"},{"id":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479,"area":null},{"id":"2305.07759","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","created":"2023-05-12","cited_by_count":449,"area":null},{"id":"2406.16858","title":"EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees","created":"2024-06-24","cited_by_count":370,"area":"inference"},{"id":"2503.01840","title":"EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test","created":"2025-03-03","cited_by_count":331,"area":"inference"},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300,"area":"mechinterp"},{"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":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"area":null},{"id":"2306.12929","title":"Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing","created":"2023-06-22","cited_by_count":151,"area":null},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"area":null},{"id":"2104.13386","title":"Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems","created":"2021-04-27","cited_by_count":128,"area":null},{"id":"2205.02302","title":"Machine Learning Operations (MLOps): Overview, Definition, and Architecture","created":"2022-05-04","cited_by_count":128,"area":null},{"id":"2102.04170","title":"Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach","created":"2021-02-08","cited_by_count":110,"area":null},{"id":"2102.08124","title":"Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks","created":"2021-02-16","cited_by_count":103,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2111.14826","title":"Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation","created":"2021-11-29","cited_by_count":79,"area":null},{"id":"2108.04974","title":"SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)","created":"2021-08-11","cited_by_count":69,"area":null},{"id":"2201.00814","title":"Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space","created":"2022-01-03","cited_by_count":66,"area":null},{"id":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"area":null},{"id":"2103.05579","title":"hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices","created":"2021-03-09","cited_by_count":62,"area":null},{"id":"2103.03936","title":"Pufferfish: Communication-efficient Models At No Extra Cost","created":"2021-03-05","cited_by_count":61,"area":null},{"id":"2307.02764","title":"When Does Confidence-Based Cascade Deferral Suffice?","created":"2023-07-06","cited_by_count":60,"area":null},{"id":"2303.09875","title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","created":"2023-03-17","cited_by_count":53,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2205.13016","title":"BiT: Robustly Binarized Multi-distilled Transformer","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2406.03372","title":"Training of Physical Neural Networks","created":"2024-06-05","cited_by_count":49,"area":null},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47,"area":null},{"id":"2101.08940","title":"Hessian-Aware Pruning and Optimal Neural Implant","created":"2021-01-22","cited_by_count":45,"area":null},{"id":"2111.08446","title":"Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions","created":"2021-11-03","cited_by_count":43,"area":null},{"id":"2302.08469","title":"Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators","created":"2023-02-16","cited_by_count":43,"area":null},{"id":"2406.06385","title":"Low-Rank Quantization-Aware Training for LLMs","created":"2024-06-10","cited_by_count":43,"area":null},{"id":"2101.00178","title":"UnitedQA: A Hybrid Approach for Open Domain Question Answering","created":"2021-01-01","cited_by_count":42,"area":null},{"id":"2101.05108","title":"Fast convolutional neural networks on FPGAs with hls4ml","created":"2021-01-13","cited_by_count":42,"area":null},{"id":"2110.12724","title":"Instance-Conditional Knowledge Distillation for Object Detection","created":"2021-10-25","cited_by_count":42,"area":"distill"},{"id":"2111.03759","title":"MQBench: Towards Reproducible and Deployable Model Quantization Benchmark","created":"2021-11-05","cited_by_count":40,"area":null},{"id":"2302.01107","title":"A Survey on Efficient Training of Transformers","created":"2023-02-02","cited_by_count":39,"area":null},{"id":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"area":null},{"id":"2202.12002","title":"Rare Gems: Finding Lottery Tickets at Initialization","created":"2022-02-24","cited_by_count":34,"area":null},{"id":"2102.11289","title":"Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference","created":"2021-02-22","cited_by_count":31,"area":null},{"id":"2110.15456","title":"FAST: DNN Training Under Variable Precision Block Floating Point with Stochastic Rounding","created":"2021-10-28","cited_by_count":31,"area":null},{"id":"2105.10288","title":"Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices","created":"2021-05-21","cited_by_count":30,"area":null},{"id":"2206.01299","title":"Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees","created":"2022-06-02","cited_by_count":30,"area":null},{"id":"2106.02205","title":"Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators","created":"2021-06-04","cited_by_count":29,"area":null},{"id":"2406.00800","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","created":"2024-06-02","cited_by_count":28,"area":null},{"id":"2206.12755","title":"Training Your Sparse Neural Network Better with Any Mask","created":"2022-06-26","cited_by_count":26,"area":null},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2410.02703","title":"Selective Attention Improves Transformer","created":"2024-10-03","cited_by_count":26,"area":null},{"id":"2206.02915","title":"8-bit Numerical Formats for Deep Neural Networks","created":"2022-06-06","cited_by_count":25,"area":null},{"id":"2305.02538","title":"Cuttlefish: Low-Rank Model Training without All the Tuning","created":"2023-05-04","cited_by_count":25,"area":null},{"id":"2403.05894","title":"Frequency Attention for Knowledge Distillation","created":"2024-03-09","cited_by_count":24,"area":"distill"},{"id":"2203.11239","title":"DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization","created":"2022-03-21","cited_by_count":23,"area":null},{"id":"2210.03858","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","created":"2022-10-08","cited_by_count":23,"area":null},{"id":"2305.05750","title":"A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networks","created":"2023-05-09","cited_by_count":23,"area":null},{"id":"2310.07999","title":"LEMON: Lossless model expansion","created":"2023-10-12","cited_by_count":23,"area":"lr"},{"id":"2403.06408","title":"What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation","created":"2024-03-11","cited_by_count":23,"area":null},{"id":"2103.02200","title":"Formalizing Generalization and Robustness of Neural Networks to Weight Perturbations","created":"2021-03-03","cited_by_count":22,"area":null},{"id":"2209.13131","title":"Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances","created":"2022-09-27","cited_by_count":22,"area":null},{"id":"2106.01288","title":"Bottom-up and top-down approaches for the design of neuromorphic processing systems: Tradeoffs and synergies between natural and artificial intelligence","created":"2021-06-02","cited_by_count":21,"area":null},{"id":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","cited_by_count":21,"area":null},{"id":"2105.13649","title":"Pruning and Slicing Neural Networks using Formal Verification","created":"2021-05-28","cited_by_count":20,"area":null},{"id":"2103.16701","title":"Charged particle tracking via edge-classifying interaction networks","created":"2021-03-30","cited_by_count":19,"area":null},{"id":"2308.06689","title":"Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training","created":"2023-08-13","cited_by_count":19,"area":null},{"id":"2203.03996","title":"DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos","created":"2022-03-08","cited_by_count":18,"area":null},{"id":"2306.14052","title":"A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware","created":"2023-06-24","cited_by_count":18,"area":null},{"id":"2402.06323","title":"How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers","created":"2024-02-09","cited_by_count":18,"area":null},{"id":"2407.05694","title":"On the Limitations of Compute Thresholds as a Governance Strategy","created":"2024-07-08","cited_by_count":18,"area":null},{"id":"2112.14938","title":"Automatic Mixed-Precision Quantization Search of BERT","created":"2021-12-30","cited_by_count":16,"area":"distill"},{"id":"2205.12268","title":"Wavelet Feature Maps Compression for Image-to-Image CNNs","created":"2022-05-24","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":"2101.08430","title":"Generative Zero-shot Network Quantization","created":"2021-01-21","cited_by_count":15,"area":null},{"id":"2106.12912","title":"Information Bottleneck: Exact Analysis of (Quantized) Neural Networks","created":"2021-06-24","cited_by_count":15,"area":null},{"id":"2207.09387","title":"Green, Quantized Federated Learning over Wireless Networks: An Energy-Efficient Design","created":"2022-07-19","cited_by_count":15,"area":null},{"id":"2306.06446","title":"ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer","created":"2023-06-10","cited_by_count":15,"area":"moe"},{"id":"2311.01057","title":"Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO","created":"2023-11-02","cited_by_count":15,"area":null},{"id":"2402.04902","title":"L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models","created":"2024-02-07","cited_by_count":15,"area":null},{"id":"2405.14377","title":"CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization","created":"2024-05-23","cited_by_count":15,"area":null},{"id":"2412.19925","title":"HADES: Hardware Accelerated Decoding for Efficient Speculation in Large Language Models","created":"2024-12-27","cited_by_count":15,"area":"inference"},{"id":"2505.17505","title":"L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models","created":"2025-05-23","cited_by_count":15,"area":null},{"id":"2109.14710","title":"Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition","created":"2021-09-29","cited_by_count":14,"area":null},{"id":"2312.08583","title":"ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2410.13780","title":"Optimal Quantization for Matrix Multiplication","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2104.12046","title":"Quantization of Deep Neural Networks for Accurate Edge Computing","created":"2021-04-25","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":"2412.18934","title":"Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference","created":"2024-12-25","cited_by_count":13,"area":"inference"},{"id":"2308.13504","title":"A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance","created":"2023-08-25","cited_by_count":12,"area":null},{"id":"2311.15578","title":"Experimental Analysis of Large-scale Learnable Vector Storage Compression","created":"2023-11-27","cited_by_count":12,"area":null},{"id":"2403.07134","title":"COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization","created":"2024-03-11","cited_by_count":12,"area":null},{"id":"2508.06097","title":"Recurrent Deep Differentiable Logic Gate Networks","created":"2025-08-08","cited_by_count":12,"area":null},{"id":"2106.07172","title":"Energy-efficient Knowledge Distillation for Spiking Neural Networks","created":"2021-06-14","cited_by_count":11,"area":"distill"},{"id":"2110.13220","title":"Demystifying and Generalizing BinaryConnect","created":"2021-10-25","cited_by_count":11,"area":null},{"id":"2201.12965","title":"Inverse design of photonic devices with strict foundry fabrication constraints","created":"2022-01-31","cited_by_count":11,"area":null},{"id":"2206.09507","title":"Resource-Efficient Separation Transformer","created":"2022-06-19","cited_by_count":11,"area":null},{"id":"2206.12372","title":"QReg: On Regularization Effects of Quantization","created":"2022-06-24","cited_by_count":11,"area":null},{"id":"2209.10438","title":"A Measure of the Complexity of Neural Representations based on Partial Information Decomposition","created":"2022-09-21","cited_by_count":11,"area":null},{"id":"2502.08246","title":"Inference-time sparse attention with asymmetric indexing","created":"2025-02-12","cited_by_count":11,"area":null},{"id":"2505.01043","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2111.07911","title":"On the Tradeoff between Energy, Precision, and Accuracy in Federated Quantized Neural Networks","created":"2021-11-15","cited_by_count":10,"area":null},{"id":"2112.11540","title":"Mixed Precision of Quantization of Transformer Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":10,"area":null}],"next_cursor":"100"}