{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"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":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255},{"id":"1902.06822","title":"Low-bit Quantization of Neural Networks for Efficient Inference","created":"2019-02-18","cited_by_count":193},{"id":"2012.15701","title":"BinaryBERT: Pushing the Limit of BERT Quantization","created":"2020-12-31","cited_by_count":178},{"id":"2310.10537","title":"Microscaling Data Formats for Deep Learning","created":"2023-10-16","cited_by_count":152},{"id":"2009.12812","title":"TernaryBERT: Distillation-aware Ultra-low Bit BERT","created":"2020-09-27","cited_by_count":148},{"id":"2210.06707","title":"Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer","created":"2022-10-13","cited_by_count":108},{"id":"2305.14152","title":"Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization","created":"2023-05-23","cited_by_count":100},{"id":"2402.10631","title":"BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation","created":"2024-02-16","cited_by_count":84},{"id":"2203.06390","title":"BiBERT: Accurate Fully Binarized BERT","created":"2022-03-12","cited_by_count":73},{"id":"2310.16836","title":"LLM-FP4: 4-Bit Floating-Point Quantized Transformers","created":"2023-10-25","cited_by_count":69},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60},{"id":"2407.00088","title":"T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge","created":"2024-06-25","cited_by_count":55},{"id":"2403.00579","title":"NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing","created":"2024-03-01","cited_by_count":52},{"id":"1908.03072","title":"TensorDIMM: A Practical Near-Memory Processing Architecture for Embeddings and Tensor Operations in Deep Learning","created":"2019-08-08","cited_by_count":43},{"id":"2111.02625","title":"Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples","created":"2021-11-04","cited_by_count":40},{"id":"2505.19115","title":"FP4 All the Way: Fully Quantized Training of LLMs","created":"2025-05-25","cited_by_count":40},{"id":"1910.04940","title":"Blink: Fast and Generic Collectives for Distributed ML","created":"2019-10-11","cited_by_count":36},{"id":"2409.01141","title":"Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching","created":"2024-09-02","cited_by_count":34},{"id":"2308.11030","title":"Ramulator 2.0: A Modern, Modular, and Extensible DRAM Simulator","created":"2023-08-21","cited_by_count":30},{"id":"2507.13575","title":"Apple Intelligence Foundation Language Models: Tech Report 2025","created":"2025-07-17","cited_by_count":28},{"id":"2405.17849","title":"I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models","created":"2024-05-28","cited_by_count":23},{"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":"2302.03213","title":"LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup","created":"2023-02-07","cited_by_count":20},{"id":"2411.09909","title":"AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference","created":"2024-11-15","cited_by_count":19},{"id":"2408.06003","title":"LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference","created":"2024-08-12","cited_by_count":18},{"id":"2110.04478","title":"Themis: A Network Bandwidth-Aware Collective Scheduling Policy for Distributed Training of DL Models","created":"2021-10-09","cited_by_count":16},{"id":"2101.05938","title":"KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization","created":"2021-01-15","cited_by_count":15},{"id":"2301.09830","title":"Optimus-CC: Efficient Large NLP Model Training with 3D Parallelism Aware Communication Compression","created":"2023-01-24","cited_by_count":15},{"id":"2403.06664","title":"Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System","created":"2024-03-11","cited_by_count":15},{"id":"1910.04877","title":"Bit Efficient Quantization for Deep Neural Networks","created":"2019-10-07","cited_by_count":14},{"id":"2308.00846","title":"Pathfinding Future PIM Architectures by Demystifying a Commercial PIM Technology","created":"2023-08-01","cited_by_count":14},{"id":"2110.01709","title":"Benchmarking Memory-Centric Computing Systems: Analysis of Real Processing-in-Memory Hardware","created":"2021-10-04","cited_by_count":13},{"id":"2410.15008","title":"IANUS: Integrated Accelerator based on NPU-PIM Unified Memory System","created":"2024-10-19","cited_by_count":13},{"id":"2410.16144","title":"1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs","created":"2024-10-21","cited_by_count":12},{"id":"2102.07511","title":"GradPIM: A Practical Processing-in-DRAM Architecture for Gradient Descent","created":"2021-02-15","cited_by_count":10},{"id":"2407.20021","title":"MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity","created":"2024-07-29","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":"2110.09195","title":"Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks","created":"2021-10-18","cited_by_count":8},{"id":"2412.19821","title":"Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models","created":"2024-12-15","cited_by_count":7},{"id":"2104.07699","title":"pLUTo: Enabling Massively Parallel Computation in DRAM via Lookup Tables","created":"2021-04-15","cited_by_count":6},{"id":"2310.01893","title":"SimplePIM: A Software Framework for Productive and Efficient Processing-in-Memory","created":"2023-10-03","cited_by_count":5},{"id":"2505.00458","title":"Memory-Centric Computing: Solving Computing's Memory Problem","created":"2025-05-01","cited_by_count":4},{"id":"2402.16731","title":"PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory Architectures","created":"2024-02-26","cited_by_count":3},{"id":"2404.08871","title":"PID-Comm: A Fast and Flexible Collective Communication Framework for Commodity Processing-in-DIMM Devices","created":"2024-04-13","cited_by_count":3},{"id":"2405.03967","title":"SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems","created":"2024-05-07","cited_by_count":2},{"id":"2503.05116","title":"Piccolo: Large-Scale Graph Processing with Fine-Grained In-Memory Scatter-Gather","created":"2025-03-07","cited_by_count":2},{"id":"2504.01948","title":"PIMDAL: Mitigating the Memory Bottleneck in Data Analytics using a Real Processing-in-Memory System","created":"2025-04-02","cited_by_count":1},{"id":"2507.17094","title":"PathWeaver: A High-Throughput Multi-GPU System for Graph-Based Approximate Nearest Neighbor Search","created":"2025-07-23","cited_by_count":1}],"next_cursor":null}