{"total":300,"rows":[{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202,"area":null},{"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":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843,"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":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650,"area":null},{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578,"area":"lr"},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539,"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":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471,"area":null},{"id":"2406.16858","title":"EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees","created":"2024-06-24","cited_by_count":370,"area":"inference"},{"id":"2503.01840","title":"EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test","created":"2025-03-03","cited_by_count":331,"area":"inference"},{"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":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211,"area":null},{"id":"2307.04721","title":"Large Language Models as General Pattern Machines","created":"2023-07-10","cited_by_count":197,"area":null},{"id":"2310.08659","title":"LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models","created":"2023-10-12","cited_by_count":196,"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":"2302.07863","title":"Speculative Decoding with Big Little Decoder","created":"2023-02-15","cited_by_count":164,"area":"inference"},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162,"area":null},{"id":"2202.09061","title":"VLP: A Survey on Vision-Language Pre-training","created":"2022-02-18","cited_by_count":159,"area":"mllm"},{"id":"2403.05527","title":"GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM","created":"2024-03-08","cited_by_count":158,"area":"inference"},{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152,"area":"moe"},{"id":"2306.12929","title":"Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing","created":"2023-06-22","cited_by_count":151,"area":null},{"id":"2306.05817","title":"How Can Recommender Systems Benefit from Large Language Models: A Survey","created":"2023-06-09","cited_by_count":142,"area":null},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"area":null},{"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":"2105.06990","title":"BERT Busters: Outlier Dimensions that Disrupt Transformers","created":"2021-05-14","cited_by_count":112,"area":null},{"id":"2109.10686","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","created":"2021-09-22","cited_by_count":106,"area":null},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102,"area":null},{"id":"2103.13076","title":"Finetuning Pretrained Transformers into RNNs","created":"2021-03-24","cited_by_count":96,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"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":"2104.08500","title":"Vision Transformer Pruning","created":"2021-04-17","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":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2203.06390","title":"BiBERT: Accurate Fully Binarized BERT","created":"2022-03-12","cited_by_count":73,"area":null},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"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":"2102.04503","title":"VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference","created":"2021-02-08","cited_by_count":64,"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":"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":"2105.14444","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","created":"2021-05-30","cited_by_count":56,"area":null},{"id":"2210.07795","title":"EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning","created":"2022-10-14","cited_by_count":56,"area":"mllm"},{"id":"2410.13835","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","created":"2024-10-17","cited_by_count":56,"area":null},{"id":"2205.13016","title":"BiT: Robustly Binarized Multi-distilled Transformer","created":"2022-05-25","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":"2306.07050","title":"Revisiting Token Pruning for Object Detection and Instance Segmentation","created":"2023-06-12","cited_by_count":50,"area":"inference"},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2102.01386","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","created":"2021-02-02","cited_by_count":48,"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":"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":"2404.07947","title":"ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference","created":"2024-03-15","cited_by_count":45,"area":null},{"id":"2310.04064","title":"How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation","created":"2023-10-06","cited_by_count":44,"area":null},{"id":"2101.00234","title":"Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers","created":"2021-01-01","cited_by_count":43,"area":null},{"id":"2104.08682","title":"Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm","created":"2021-04-18","cited_by_count":40,"area":null},{"id":"2307.05908","title":"Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding","created":"2023-07-12","cited_by_count":40,"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":"2109.15082","title":"Towards Efficient Post-training Quantization of Pre-trained Language Models","created":"2021-09-30","cited_by_count":39,"area":null},{"id":"2109.03228","title":"Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression","created":"2021-09-07","cited_by_count":38,"area":null},{"id":"2404.03828","title":"Outlier-Efficient Hopfield Layers for Large Transformer-Based Models","created":"2024-04-04","cited_by_count":38,"area":null},{"id":"2201.07703","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","created":"2022-01-19","cited_by_count":37,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2111.04130","title":"NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework","created":"2021-11-07","cited_by_count":34,"area":null},{"id":"2206.08898","title":"SimA: Simple Softmax-free Attention for Vision Transformers","created":"2022-06-17","cited_by_count":32,"area":null},{"id":"2303.17951","title":"FP8 versus INT8 for efficient deep learning inference","created":"2023-03-31","cited_by_count":31,"area":null},{"id":"2402.04497","title":"The Fine-Grained Complexity of Gradient Computation for Training Large Language Models","created":"2024-02-07","cited_by_count":30,"area":null},{"id":"2106.02205","title":"Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators","created":"2021-06-04","cited_by_count":29,"area":null},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"area":null},{"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":"2106.00169","title":"Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation","created":"2021-06-01","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":"2310.10837","title":"Approximating Two-Layer Feedforward Networks for Efficient Transformers","created":"2023-10-16","cited_by_count":27,"area":null},{"id":"2405.18218","title":"FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models","created":"2024-05-28","cited_by_count":27,"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":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","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":"2205.10162","title":"FedAdapter: Efficient Federated Learning for Modern NLP","created":"2022-05-20","cited_by_count":25,"area":null},{"id":"2305.12129","title":"Lifting the Curse of Capacity Gap in Distilling Language Models","created":"2023-05-20","cited_by_count":25,"area":"moe"},{"id":"2402.13720","title":"Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding","created":"2024-02-21","cited_by_count":25,"area":"inference"},{"id":"2202.07101","title":"A Survey on Dynamic Neural Networks for Natural Language Processing","created":"2022-02-15","cited_by_count":24,"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":"2210.03858","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","created":"2022-10-08","cited_by_count":23,"area":null},{"id":"2310.05317","title":"Task-Adaptive Tokenization: Enhancing Long-Form Text Generation Efficacy in Mental Health and Beyond","created":"2023-10-09","cited_by_count":23,"area":null},{"id":"2103.02800","title":"Hardware Acceleration of Fully Quantized BERT for Efficient Natural Language Processing","created":"2021-03-04","cited_by_count":22,"area":null},{"id":"2310.11237","title":"Watermarking LLMs with Weight Quantization","created":"2023-10-17","cited_by_count":22,"area":"safety"},{"id":"2408.04585","title":"Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness","created":"2024-08-08","cited_by_count":22,"area":null},{"id":"2204.07780","title":"Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks","created":"2022-04-16","cited_by_count":21,"area":null},{"id":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","cited_by_count":21,"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":"2205.12694","title":"Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2103.16827","title":"Integer-only Zero-shot Quantization for Efficient Speech Recognition","created":"2021-03-31","cited_by_count":19,"area":null}],"next_cursor":"100"}