{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2311.18677","title":"Splitwise: Efficient generative LLM inference using phase splitting","created":"2023-11-30","cited_by_count":558},{"id":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"1602.01528","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","created":"2016-02-04","cited_by_count":295},{"id":"2310.19102","title":"Atom: Low-bit Quantization for Efficient and Accurate LLM Serving","created":"2023-10-29","cited_by_count":272},{"id":"2012.09852","title":"SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning","created":"2020-12-17","cited_by_count":234},{"id":"2307.08177","title":"Using an LLM to Help With Code Understanding","created":"2023-07-17","cited_by_count":228},{"id":"1907.10641","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","created":"2019-07-24","cited_by_count":204},{"id":"2209.13325","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","created":"2022-09-27","cited_by_count":181},{"id":"2010.03093","title":"WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization","created":"2020-10-07","cited_by_count":154},{"id":"2308.04623","title":"Accelerating LLM Inference with Staged Speculative Decoding","created":"2023-08-08","cited_by_count":151},{"id":"1708.04485","title":"SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks","created":"2017-05-23","cited_by_count":135},{"id":"1712.01507","title":"Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks","created":"2017-12-05","cited_by_count":109},{"id":"2002.10941","title":"A$^3$: Accelerating Attention Mechanisms in Neural Networks with Approximation","created":"2020-02-22","cited_by_count":101},{"id":"2401.11314","title":"CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs","created":"2024-01-20","cited_by_count":84},{"id":"2011.14203","title":"EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference","created":"2020-11-28","cited_by_count":70},{"id":"2007.08563","title":"FTRANS: Energy-Efficient Acceleration of Transformers using FPGA","created":"2020-07-16","cited_by_count":54},{"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},{"id":"2210.09573","title":"ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design","created":"2022-10-18","cited_by_count":41},{"id":"1610.06920","title":"Bit-pragmatic Deep Neural Network Computing","created":"2016-10-20","cited_by_count":32},{"id":"2209.09570","title":"Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design","created":"2022-09-20","cited_by_count":31},{"id":"2208.06118","title":"An Algorithm-Hardware Co-Optimized Framework for Accelerating N:M Sparse Transformers","created":"2022-08-12","cited_by_count":29},{"id":"2110.09310","title":"Energon: Towards Efficient Acceleration of Transformers Using Dynamic Sparse Attention","created":"2021-10-18","cited_by_count":26},{"id":"2302.14705","title":"AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers","created":"2023-02-28","cited_by_count":24},{"id":"1804.06508","title":"UCNN: Exploiting Computational Reuse in Deep Neural Networks via Weight Repetition","created":"2018-04-18","cited_by_count":20},{"id":"2107.07983","title":"S2TA: Exploiting Structured Sparsity for Energy-Efficient Mobile CNN Acceleration","created":"2021-07-16","cited_by_count":19},{"id":"2009.10976","title":"Procrustes: a Dataflow and Accelerator for Sparse Deep Neural Network Training","created":"2020-09-23","cited_by_count":18},{"id":"2209.00606","title":"Sparse Attention Acceleration with Synergistic In-Memory Pruning and On-Chip Recomputation","created":"2022-09-01","cited_by_count":12},{"id":"2305.12718","title":"HighLight: Efficient and Flexible DNN Acceleration with Hierarchical Structured Sparsity","created":"2023-05-22","cited_by_count":12},{"id":"2206.14550","title":"SALO: An Efficient Spatial Accelerator Enabling Hybrid Sparse Attention Mechanisms for Long Sequences","created":"2022-06-29","cited_by_count":10},{"id":"2407.10416","title":"SOFA: A Compute-Memory Optimized Sparsity Accelerator via Cross-Stage Coordinated Tiling","created":"2024-07-15","cited_by_count":9},{"id":"2501.10658","title":"LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator","created":"2025-01-18","cited_by_count":9},{"id":"2204.03227","title":"Accelerating Attention through Gradient-Based Learned Runtime Pruning","created":"2022-04-07","cited_by_count":8},{"id":"1606.05487","title":"YodaNN: An Architecture for Ultra-Low Power Binary-Weight CNN Acceleration","created":"2016-06-17","cited_by_count":7},{"id":"1512.04295","title":"Origami: A 803 GOp/s/W Convolutional Network Accelerator","created":"2015-12-14","cited_by_count":6},{"id":"2405.17025","title":"SWAT: Scalable and Efficient Window Attention-based Transformers Acceleration on FPGAs","created":"2024-05-27","cited_by_count":6},{"id":"2412.10059","title":"Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity","created":"2024-12-13","cited_by_count":5},{"id":"2503.19353","title":"QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition","created":"2025-03-25","cited_by_count":4},{"id":"2306.15887","title":"Beyond the Hype: Assessing the Performance, Trustworthiness, and Clinical Suitability of GPT3.5","created":"2023-06-28","cited_by_count":2},{"id":"1706.00504","title":"Dynamic Stripes: Exploiting the Dynamic Precision Requirements of Activation Values in Neural Networks","created":"2017-06-01","cited_by_count":1}],"next_cursor":null}