{"total":148,"rows":[{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906,"area":null},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526,"area":null},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278,"area":null},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2209.13325","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","created":"2022-09-27","cited_by_count":181,"area":null},{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167,"area":null},{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152,"area":"moe"},{"id":"2107.00910","title":"Learned Token Pruning for Transformers","created":"2021-07-02","cited_by_count":139,"area":"inference"},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2203.07259","title":"The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models","created":"2022-03-14","cited_by_count":115,"area":"inference"},{"id":"2110.05006","title":"Pre-trained Language Models in Biomedical Domain: A Systematic Survey","created":"2021-10-11","cited_by_count":87,"area":null},{"id":"2103.10619","title":"Scalable Vision Transformers with Hierarchical Pooling","created":"2021-03-19","cited_by_count":84,"area":null},{"id":"2402.10631","title":"BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation","created":"2024-02-16","cited_by_count":84,"area":"distill"},{"id":"2203.08243","title":"Unified Visual Transformer Compression","created":"2022-03-15","cited_by_count":79,"area":null},{"id":"2203.10705","title":"Compression of Generative Pre-trained Language Models via Quantization","created":"2022-03-21","cited_by_count":79,"area":null},{"id":"2303.08302","title":"ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation","created":"2023-03-15","cited_by_count":79,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2304.13013","title":"Stable and low-precision training for large-scale vision-language models","created":"2023-04-25","cited_by_count":75,"area":"mllm"},{"id":"2203.06390","title":"BiBERT: Accurate Fully Binarized BERT","created":"2022-03-12","cited_by_count":73,"area":null},{"id":"2111.05754","title":"Prune Once for All: Sparse Pre-Trained Language Models","created":"2021-11-10","cited_by_count":66,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2211.16056","title":"NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers","created":"2022-11-29","cited_by_count":61,"area":null},{"id":"2304.09145","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","created":"2023-04-18","cited_by_count":61,"area":null},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60,"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":"2306.00317","title":"FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization","created":"2023-06-01","cited_by_count":48,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2502.02631","title":"ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization","created":"2025-02-04","cited_by_count":46,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"area":null},{"id":"2210.05528","title":"Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems","created":"2022-10-11","cited_by_count":44,"area":null},{"id":"2105.12967","title":"Selective Knowledge Distillation for Neural Machine Translation","created":"2021-05-27","cited_by_count":43,"area":"distill"},{"id":"2105.11618","title":"TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference","created":"2021-05-25","cited_by_count":40,"area":"inference"},{"id":"2107.06419","title":"FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks","created":"2021-07-13","cited_by_count":39,"area":null},{"id":"2109.15082","title":"Towards Efficient Post-training Quantization of Pre-trained Language Models","created":"2021-09-30","cited_by_count":39,"area":null},{"id":"2105.13880","title":"Knowledge Inheritance for Pre-trained Language Models","created":"2021-05-28","cited_by_count":38,"area":null},{"id":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2107.13686","title":"AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models","created":"2021-07-29","cited_by_count":31,"area":null},{"id":"2403.12422","title":"Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization","created":"2024-03-19","cited_by_count":31,"area":null},{"id":"2406.03287","title":"SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms","created":"2024-06-05","cited_by_count":31,"area":null},{"id":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"id":"2403.07839","title":"MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric","created":"2024-03-12","cited_by_count":30,"area":"mllm"},{"id":"2208.05163","title":"Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization","created":"2022-08-10","cited_by_count":29,"area":null},{"id":"2110.08152","title":"Kronecker Decomposition for GPT Compression","created":"2021-10-15","cited_by_count":28,"area":null},{"id":"2201.06618","title":"VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer","created":"2022-01-17","cited_by_count":27,"area":null},{"id":"2410.16215","title":"Pre-training Distillation for Large Language Models: A Design Space Exploration","created":"2024-10-21","cited_by_count":27,"area":"distill"},{"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":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2112.02191","title":"NN-LUT: Neural Approximation of Non-Linear Operations for Efficient Transformer Inference","created":"2021-12-03","cited_by_count":25,"area":null},{"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":"2208.03646","title":"A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipelining","created":"2022-08-07","cited_by_count":22,"area":null},{"id":"2502.12913","title":"GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning","created":"2025-02-18","cited_by_count":21,"area":null},{"id":"2308.06744","title":"Token-Scaled Logit Distillation for Ternary Weight Generative Language Models","created":"2023-08-13","cited_by_count":20,"area":"distill"},{"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,"area":null},{"id":"2206.01859","title":"Extreme Compression for Pre-trained Transformers Made Simple and Efficient","created":"2022-06-04","cited_by_count":19,"area":"distill"},{"id":"2402.04744","title":"Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers","created":"2024-02-07","cited_by_count":18,"area":null},{"id":"2411.17691","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","created":"2024-11-26","cited_by_count":18,"area":null},{"id":"2306.16678","title":"BinaryViT: Pushing Binary Vision Transformers Towards Convolutional Models","created":"2023-06-29","cited_by_count":17,"area":null},{"id":"2308.15122","title":"SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillation","created":"2023-08-29","cited_by_count":17,"area":"distill"},{"id":"2403.02775","title":"EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs","created":"2024-03-05","cited_by_count":17,"area":null},{"id":"2111.11124","title":"Mesa: A Memory-saving Training Framework for Transformers","created":"2021-11-22","cited_by_count":16,"area":null},{"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,"area":"distill"},{"id":"2205.10036","title":"Exploring Extreme Parameter Compression for Pre-trained Language Models","created":"2022-05-20","cited_by_count":15,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2409.06669","title":"DA-MoE: Towards Dynamic Expert Allocation for Mixture-of-Experts Models","created":"2024-09-10","cited_by_count":15,"area":"moe"},{"id":"2103.11367","title":"ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques","created":"2021-03-21","cited_by_count":14,"area":null},{"id":"2106.01335","title":"On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers","created":"2021-06-02","cited_by_count":14,"area":null},{"id":"2210.15976","title":"BEBERT: Efficient and Robust Binary Ensemble BERT","created":"2022-10-28","cited_by_count":14,"area":null},{"id":"2406.12311","title":"Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2302.00956","title":"Resilient Binary Neural Network","created":"2023-02-02","cited_by_count":13,"area":null},{"id":"2405.00314","title":"Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey","created":"2024-05-01","cited_by_count":13,"area":null},{"id":"2201.08050","title":"TerViT: An Efficient Ternary Vision Transformer","created":"2022-01-20","cited_by_count":11,"area":null},{"id":"2209.07617","title":"Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2211.11014","title":"Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer Encoders","created":"2022-11-20","cited_by_count":11,"area":"distill"},{"id":"2506.13771","title":"LittleBit: Ultra Low-Bit Quantization via Latent Factorization","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2203.13483","title":"MKQ-BERT: Quantized BERT with 4-bits Weights and Activations","created":"2022-03-25","cited_by_count":10,"area":null},{"id":"2211.12707","title":"Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?","created":"2022-11-23","cited_by_count":10,"area":null},{"id":"2304.11954","title":"Spikingformer: A Key Foundation Model for Spiking Neural Networks","created":"2023-04-24","cited_by_count":10,"area":null},{"id":"2102.06366","title":"Confounding Tradeoffs for Neural Network Quantization","created":"2021-02-12","cited_by_count":9,"area":null},{"id":"2310.10944","title":"TEQ: Trainable Equivalent Transformation for Quantization of LLMs","created":"2023-10-17","cited_by_count":9,"area":null},{"id":"2203.00748","title":"E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models","created":"2022-03-01","cited_by_count":8,"area":null},{"id":"2207.09150","title":"On the Usability of Transformers-based models for a French Question-Answering task","created":"2022-07-19","cited_by_count":8,"area":null},{"id":"2305.09651","title":"Tailoring Instructions to Student's Learning Levels Boosts Knowledge Distillation","created":"2023-05-16","cited_by_count":8,"area":"distill"},{"id":"2310.05079","title":"Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?","created":"2023-10-08","cited_by_count":8,"area":null},{"id":"2606.13054","title":"TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization","created":"2026-06-11","cited_by_count":8,"area":"inference"},{"id":"2105.14636","title":"LEAP: Learnable Pruning for Transformer-based Models","created":"2021-05-30","cited_by_count":7,"area":null},{"id":"2210.05211","title":"A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2210.07171","title":"SQuAT: Sharpness- and Quantization-Aware Training for BERT","created":"2022-10-13","cited_by_count":7,"area":null},{"id":"2306.01841","title":"Binary and Ternary Natural Language Generation","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2302.11187","title":"Debiased Distillation by Transplanting the Last Layer","created":"2023-02-22","cited_by_count":6,"area":"distill"},{"id":"2303.05295","title":"Dynamic Stashing Quantization for Efficient Transformer Training","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2401.11851","title":"BETA: Binarized Energy-Efficient Transformer Accelerator at the Edge","created":"2024-01-22","cited_by_count":6,"area":null},{"id":"2409.15298","title":"Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model","created":"2024-09-04","cited_by_count":6,"area":null},{"id":"2502.00745","title":"BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts","created":"2025-02-02","cited_by_count":6,"area":"inference"},{"id":"2509.13765","title":"TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge","created":"2025-09-17","cited_by_count":6,"area":null}],"next_cursor":"100"}