{"list":"other","total":55,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906},{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832},{"id":"1811.08886","title":"HAQ: Hardware-Aware Automated Quantization with Mixed Precision","created":"2018-11-21","cited_by_count":443},{"id":"2308.13137","title":"OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models","created":"2023-08-25","cited_by_count":424},{"id":"2307.13304","title":"QuIP: 2-Bit Quantization of Large Language Models With Guarantees","created":"2023-07-25","cited_by_count":414},{"id":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"id":"2402.04396","title":"QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks","created":"2024-02-06","cited_by_count":378},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251},{"id":"2401.06118","title":"Extreme Compression of Large Language Models via Additive Quantization","created":"2024-01-11","cited_by_count":232},{"id":"2209.13325","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","created":"2022-09-27","cited_by_count":181},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152},{"id":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127},{"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":"2206.09557","title":"LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models","created":"2022-06-20","cited_by_count":105},{"id":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97},{"id":"2304.07493","title":"OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization","created":"2023-04-15","cited_by_count":92},{"id":"2310.12321","title":"A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4","created":"2023-10-04","cited_by_count":81},{"id":"2402.11295","title":"OneBit: Towards Extremely Low-bit Large Language Models","created":"2024-02-17","cited_by_count":79},{"id":"2102.04503","title":"VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference","created":"2021-02-08","cited_by_count":64},{"id":"1612.00694","title":"ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA","created":"2016-12-01","cited_by_count":52},{"id":"2302.08007","title":"With Shared Microexponents, A Little Shifting Goes a Long Way","created":"2023-02-16","cited_by_count":50},{"id":"1711.02213","title":"Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks","created":"2017-11-06","cited_by_count":44},{"id":"2312.03414","title":"Compressed Context Memory For Online Language Model Interaction","created":"2023-12-06","cited_by_count":43},{"id":"2408.03675","title":"NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time","created":"2024-08-07","cited_by_count":43},{"id":"2407.01527","title":"KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches","created":"2024-07-01","cited_by_count":42},{"id":"1804.01526","title":"Training DNNs with Hybrid Block Floating Point","created":"2018-04-04","cited_by_count":40},{"id":"2309.02784","title":"Norm Tweaking: High-performance Low-bit Quantization of Large Language Models","created":"2023-09-06","cited_by_count":33},{"id":"2405.06001","title":"LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit","created":"2024-05-09","cited_by_count":33},{"id":"1610.06920","title":"Bit-pragmatic Deep Neural Network Computing","created":"2016-10-20","cited_by_count":32},{"id":"2110.15456","title":"FAST: DNN Training Under Variable Precision Block Floating Point with Stochastic Rounding","created":"2021-10-28","cited_by_count":31},{"id":"2406.12930","title":"Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization","created":"2024-06-16","cited_by_count":28},{"id":"2005.09904","title":"BiQGEMM: Matrix Multiplication with Lookup Table For Binary-Coding-based Quantized DNNs","created":"2020-05-20","cited_by_count":21},{"id":"2203.12758","title":"Mokey: Enabling Narrow Fixed-Point Inference for Out-of-the-Box Floating-Point Transformer Models","created":"2022-03-23","cited_by_count":19},{"id":"2210.15976","title":"BEBERT: Efficient and Robust Binary Ensemble BERT","created":"2022-10-28","cited_by_count":14},{"id":"2309.08186","title":"A Precision-Scalable RISC-V DNN Processor with On-Device Learning Capability at the Extreme Edge","created":"2023-09-15","cited_by_count":11},{"id":"2203.06673","title":"FlexBlock: A Flexible DNN Training Accelerator with Multi-Mode Block Floating Point Support","created":"2022-03-13","cited_by_count":10},{"id":"2206.02874","title":"Dissecting Tensor Cores via Microbenchmarks: Latency, Throughput and Numeric Behaviors","created":"2022-06-06","cited_by_count":10},{"id":"2403.14353","title":"DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video Analytics","created":"2024-03-21","cited_by_count":8},{"id":"2007.01530","title":"FPnew: An Open-Source Multi-Format Floating-Point Unit Architecture for Energy-Proportional Transprecision Computing","created":"2020-07-03","cited_by_count":7},{"id":"2407.18175","title":"Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers","created":"2024-07-25","cited_by_count":4},{"id":"2308.09511","title":"ResQ: Residual Quantization for Video Perception","created":"2023-08-18","cited_by_count":2}],"next_cursor":null}