{"total":573,"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":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019,"area":null},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032,"area":null},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964,"area":null},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661,"area":null},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629,"area":null},{"id":"2112.00724","title":"RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs","created":"2021-12-01","cited_by_count":615,"area":null},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282,"area":null},{"id":"2102.09544","title":"Combinatorial optimization and reasoning with graph neural networks","created":"2021-02-18","cited_by_count":268,"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":"2111.14643","title":"Urban Radiance Fields","created":"2021-11-29","cited_by_count":263,"area":null},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242,"area":null},{"id":"2206.07137","title":"Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt","created":"2022-06-14","cited_by_count":236,"area":null},{"id":"2304.01433","title":"TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings","created":"2023-04-04","cited_by_count":202,"area":null},{"id":"2309.14322","title":"Small-scale proxies for large-scale Transformer training instabilities","created":"2023-09-25","cited_by_count":183,"area":null},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182,"area":null},{"id":"2102.11005","title":"LogME: Practical Assessment of Pre-trained Models for Transfer Learning","created":"2021-02-22","cited_by_count":172,"area":null},{"id":"2103.07579","title":"Revisiting ResNets: Improved Training and Scaling Strategies","created":"2021-03-13","cited_by_count":158,"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":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2312.03718","title":"Large Language Models in Law: A Survey","created":"2023-11-26","cited_by_count":128,"area":null},{"id":"2206.00133","title":"Pre-training via Denoising for Molecular Property Prediction","created":"2022-05-31","cited_by_count":124,"area":null},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118,"area":null},{"id":"2402.05862","title":"Let Your Graph Do the Talking: Encoding Structured Data for LLMs","created":"2024-02-08","cited_by_count":118,"area":null},{"id":"2106.11342","title":"Dive into Deep Learning","created":"2021-06-21","cited_by_count":111,"area":null},{"id":"2104.12325","title":"Efficient training of physics-informed neural networks via importance sampling","created":"2021-04-26","cited_by_count":110,"area":null},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107,"area":null},{"id":"2304.07493","title":"OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization","created":"2023-04-15","cited_by_count":92,"area":null},{"id":"2102.04432","title":"Colorization Transformer","created":"2021-02-08","cited_by_count":89,"area":null},{"id":"2103.05633","title":"Proof-of-Learning: Definitions and Practice","created":"2021-03-09","cited_by_count":84,"area":null},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84,"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":"2106.03517","title":"Top-KAST: Top-K Always Sparse Training","created":"2021-06-07","cited_by_count":79,"area":null},{"id":"2206.10558","title":"EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine","created":"2022-06-21","cited_by_count":62,"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":"2101.11714","title":"TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models","created":"2021-01-25","cited_by_count":58,"area":null},{"id":"2102.07952","title":"A Survey of Machine Learning for Computer Architecture and Systems","created":"2021-02-16","cited_by_count":53,"area":null},{"id":"2107.03436","title":"Tensor Methods in Computer Vision and Deep Learning","created":"2021-07-07","cited_by_count":52,"area":null},{"id":"2107.12422","title":"Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Framework","created":"2021-07-26","cited_by_count":52,"area":null},{"id":"2304.06793","title":"Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipeline","created":"2023-04-13","cited_by_count":52,"area":null},{"id":"2208.14286","title":"ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization","created":"2022-08-30","cited_by_count":51,"area":null},{"id":"2201.08904","title":"Description-Driven Task-Oriented Dialog Modeling","created":"2022-01-21","cited_by_count":50,"area":null},{"id":"2106.04217","title":"Dynamic Sparse Training for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":49,"area":null},{"id":"2112.00133","title":"PokeBNN: A Binary Pursuit of Lightweight Accuracy","created":"2021-11-30","cited_by_count":49,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2209.10797","title":"DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation","created":"2022-09-22","cited_by_count":48,"area":null},{"id":"2207.04606","title":"SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning","created":"2022-07-11","cited_by_count":47,"area":null},{"id":"2408.10914","title":"To Code, or Not To Code? Exploring Impact of Code in Pre-training","created":"2024-08-20","cited_by_count":47,"area":null},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45,"area":null},{"id":"2111.02625","title":"Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples","created":"2021-11-04","cited_by_count":40,"area":null},{"id":"2112.08429","title":"Torch.fx: Practical Program Capture and Transformation for Deep Learning in Python","created":"2021-12-15","cited_by_count":40,"area":null},{"id":"2102.10423","title":"An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks","created":"2021-02-20","cited_by_count":39,"area":null},{"id":"2107.06419","title":"FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks","created":"2021-07-13","cited_by_count":39,"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":"2203.08737","title":"Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey","created":"2022-03-16","cited_by_count":39,"area":null},{"id":"2302.01107","title":"A Survey on Efficient Training of Transformers","created":"2023-02-02","cited_by_count":39,"area":null},{"id":"2104.06272","title":"Podracer architectures for scalable Reinforcement Learning","created":"2021-04-13","cited_by_count":38,"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":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","cited_by_count":37,"area":null},{"id":"2110.06800","title":"SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems","created":"2021-10-13","cited_by_count":34,"area":null},{"id":"2110.13041","title":"Applications and Techniques for Fast Machine Learning in Science","created":"2021-10-25","cited_by_count":32,"area":null},{"id":"2103.06995","title":"Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking","created":"2021-03-11","cited_by_count":30,"area":null},{"id":"2104.13467","title":"An optical neural network using less than 1 photon per multiplication","created":"2021-04-27","cited_by_count":30,"area":null},{"id":"2106.10860","title":"Multiplying Matrices Without Multiplying","created":"2021-06-21","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":"2102.06960","title":"CrossLight: A Cross-Layer Optimized Silicon Photonic Neural Network Accelerator","created":"2021-02-13","cited_by_count":29,"area":null},{"id":"2110.11346","title":"Data-Driven Offline Optimization For Architecting Hardware Accelerators","created":"2021-10-20","cited_by_count":29,"area":null},{"id":"2203.08147","title":"Energy-Latency Attacks via Sponge Poisoning","created":"2022-03-14","cited_by_count":29,"area":null},{"id":"2108.09373","title":"Understanding Data Storage and Ingestion for Large-Scale Deep Recommendation Model Training","created":"2021-08-20","cited_by_count":28,"area":null},{"id":"2110.10545","title":"Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs","created":"2021-10-20","cited_by_count":28,"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":"2206.04459","title":"SDQ: Stochastic Differentiable Quantization with Mixed Precision","created":"2022-06-09","cited_by_count":28,"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":"2312.05328","title":"Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding","created":"2023-12-08","cited_by_count":28,"area":null},{"id":"2410.21680","title":"Revisiting Reliability in Large-Scale Machine Learning Research Clusters","created":"2024-10-29","cited_by_count":28,"area":null},{"id":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"area":null},{"id":"2102.06741","title":"Discovery of Options via Meta-Learned Subgoals","created":"2021-02-12","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":"2103.00543","title":"On the Utility of Gradient Compression in Distributed Training Systems","created":"2021-02-28","cited_by_count":26,"area":null},{"id":"2108.09457","title":"DeepEdgeBench: Benchmarking Deep Neural Networks on Edge Devices","created":"2021-08-21","cited_by_count":26,"area":null},{"id":"2110.09310","title":"Energon: Towards Efficient Acceleration of Transformers Using Dynamic Sparse Attention","created":"2021-10-18","cited_by_count":26,"area":null},{"id":"2309.16354","title":"Transformer-VQ: Linear-Time Transformers via Vector Quantization","created":"2023-09-28","cited_by_count":26,"area":null},{"id":"2107.00057","title":"Simple Training Strategies and Model Scaling for Object Detection","created":"2021-06-30","cited_by_count":25,"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":"2303.07470","title":"X-Former: In-Memory Acceleration of Transformers","created":"2023-03-13","cited_by_count":25,"area":null},{"id":"2103.01489","title":"Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search","created":"2021-03-02","cited_by_count":24,"area":null},{"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,"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":"2102.05610","title":"Searching for Fast Model Families on Datacenter Accelerators","created":"2021-02-10","cited_by_count":22,"area":null},{"id":"2103.00686","title":"Accelerating Recommendation System Training by Leveraging Popular Choices","created":"2021-03-01","cited_by_count":22,"area":null},{"id":"2105.01898","title":"CoSA: Scheduling by Constrained Optimization for Spatial Accelerators","created":"2021-05-05","cited_by_count":22,"area":null},{"id":"2501.14794","title":"Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference","created":"2025-01-11","cited_by_count":22,"area":null},{"id":"2207.03522","title":"TF-GNN: Graph Neural Networks in TensorFlow","created":"2022-07-07","cited_by_count":21,"area":null},{"id":"2306.15552","title":"A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms","created":"2023-06-27","cited_by_count":21,"area":null},{"id":"2102.06356","title":"A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes","created":"2021-02-12","cited_by_count":20,"area":null},{"id":"2108.13990","title":"Effective Sequence-to-Sequence Dialogue State Tracking","created":"2021-08-31","cited_by_count":20,"area":null},{"id":"2203.17008","title":"It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher","created":"2022-03-31","cited_by_count":20,"area":null},{"id":"2211.05612","title":"Power Grid Congestion Management via Topology Optimization with AlphaZero","created":"2022-11-10","cited_by_count":20,"area":null},{"id":"2305.10727","title":"Boost Vision Transformer with GPU-Friendly Sparsity and Quantization","created":"2023-05-18","cited_by_count":20,"area":null},{"id":"2105.12842","title":"A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators","created":"2021-05-26","cited_by_count":19,"area":null}],"next_cursor":"100"}