{"total":185,"rows":[{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245,"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":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"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":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177,"area":null},{"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":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2105.06990","title":"BERT Busters: Outlier Dimensions that Disrupt Transformers","created":"2021-05-14","cited_by_count":112,"area":null},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105,"area":null},{"id":"2308.06522","title":"SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models","created":"2023-08-12","cited_by_count":93,"area":null},{"id":"2103.10619","title":"Scalable Vision Transformers with Hierarchical Pooling","created":"2021-03-19","cited_by_count":84,"area":null},{"id":"2104.08500","title":"Vision Transformer Pruning","created":"2021-04-17","cited_by_count":79,"area":null},{"id":"2203.08243","title":"Unified Visual Transformer Compression","created":"2022-03-15","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":"2203.06390","title":"BiBERT: Accurate Fully Binarized BERT","created":"2022-03-12","cited_by_count":73,"area":null},{"id":"2406.16937","title":"A Complete Survey on LLM-based AI Chatbots","created":"2024-06-17","cited_by_count":71,"area":null},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70,"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":"2211.07349","title":"Finding Skill Neurons in Pre-trained Transformer-based Language Models","created":"2022-11-14","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":"2401.02038","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","created":"2024-01-04","cited_by_count":59,"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":"2205.11380","title":"Outliers Dimensions that Disrupt Transformers Are Driven by Frequency","created":"2022-05-23","cited_by_count":55,"area":null},{"id":"2401.15569","title":"Efficient Tuning and Inference for Large Language Models on Textual Graphs","created":"2024-01-28","cited_by_count":54,"area":"inference"},{"id":"2403.02991","title":"MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer","created":"2024-03-05","cited_by_count":54,"area":"inference"},{"id":"2108.04657","title":"Differentiable Subset Pruning of Transformer Heads","created":"2021-08-10","cited_by_count":47,"area":null},{"id":"2110.06696","title":"Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese","created":"2021-10-13","cited_by_count":45,"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":"2110.07038","title":"Towards Efficient NLP: A Standard Evaluation and A Strong Baseline","created":"2021-10-13","cited_by_count":44,"area":null},{"id":"2203.04466","title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","created":"2022-03-09","cited_by_count":41,"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":"2302.14623","title":"Fast as CHITA: Neural Network Pruning with Combinatorial Optimization","created":"2023-02-28","cited_by_count":40,"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":"2203.04570","title":"CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction","created":"2022-03-09","cited_by_count":39,"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":"2106.00149","title":"HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalization","created":"2021-05-31","cited_by_count":32,"area":null},{"id":"2203.01670","title":"A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation","created":"2022-03-03","cited_by_count":32,"area":"inference"},{"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":"2305.12132","title":"Can Public Large Language Models Help Private Cross-device Federated Learning?","created":"2023-05-20","cited_by_count":30,"area":null},{"id":"2205.01541","title":"Efficient Fine-Tuning of BERT Models on the Edge","created":"2022-05-03","cited_by_count":29,"area":null},{"id":"2205.11005","title":"Parameter-Efficient Sparsity for Large Language Models Fine-Tuning","created":"2022-05-23","cited_by_count":27,"area":null},{"id":"2108.07686","title":"Scaling Laws for Deep Learning","created":"2021-08-17","cited_by_count":26,"area":null},{"id":"2302.14705","title":"AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers","created":"2023-02-28","cited_by_count":24,"area":null},{"id":"2301.12017","title":"Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases","created":"2023-01-27","cited_by_count":23,"area":null},{"id":"2110.08190","title":"Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm","created":"2021-10-15","cited_by_count":21,"area":null},{"id":"2307.10780","title":"Learned Thresholds Token Merging and Pruning for Vision Transformers","created":"2023-07-20","cited_by_count":21,"area":"inference"},{"id":"2102.07804","title":"Scaling Up Exact Neural Network Compression by ReLU Stability","created":"2021-02-15","cited_by_count":19,"area":null},{"id":"2105.13792","title":"Early Exiting with Ensemble Internal Classifiers","created":"2021-05-28","cited_by_count":19,"area":null},{"id":"2108.12594","title":"Layer-wise Model Pruning based on Mutual Information","created":"2021-08-28","cited_by_count":19,"area":null},{"id":"2109.10164","title":"RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation","created":"2021-09-21","cited_by_count":19,"area":"distill"},{"id":"2110.15766","title":"NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM","created":"2021-10-28","cited_by_count":19,"area":null},{"id":"2202.04350","title":"pNLP-Mixer: an Efficient all-MLP Architecture for Language","created":"2022-02-09","cited_by_count":19,"area":null},{"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":"2305.17446","title":"Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models","created":"2023-05-27","cited_by_count":19,"area":null},{"id":"2310.05015","title":"Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models","created":"2023-10-08","cited_by_count":19,"area":null},{"id":"2106.04563","title":"XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation","created":"2021-06-08","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":"2112.14938","title":"Automatic Mixed-Precision Quantization Search of BERT","created":"2021-12-30","cited_by_count":16,"area":"distill"},{"id":"2210.16079","title":"Debiasing Masks: A New Framework for Shortcut Mitigation in NLU","created":"2022-10-28","cited_by_count":16,"area":null},{"id":"2507.07996","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","created":"2025-07-10","cited_by_count":16,"area":null},{"id":"2211.02738","title":"Intriguing Properties of Compression on Multilingual Models","created":"2022-11-04","cited_by_count":15,"area":null},{"id":"2310.17715","title":"Outlier Dimensions Encode Task-Specific Knowledge","created":"2023-10-26","cited_by_count":15,"area":null},{"id":"2103.11367","title":"ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques","created":"2021-03-21","cited_by_count":14,"area":null},{"id":"2106.02435","title":"You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient","created":"2021-06-04","cited_by_count":14,"area":null},{"id":"2107.00175","title":"Elbert: Fast Albert with Confidence-Window Based Early Exit","created":"2021-07-01","cited_by_count":14,"area":"inference"},{"id":"2204.10716","title":"Hierarchical Label-wise Attention Transformer Model for Explainable ICD Coding","created":"2022-04-22","cited_by_count":13,"area":null},{"id":"2206.10461","title":"An Automatic and Efficient BERT Pruning for Edge AI Systems","created":"2022-06-21","cited_by_count":13,"area":null},{"id":"2210.10041","title":"Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning","created":"2022-10-18","cited_by_count":13,"area":null},{"id":"2404.05621","title":"MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning","created":"2024-04-08","cited_by_count":13,"area":"mllm"},{"id":"2207.03677","title":"SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning","created":"2022-07-08","cited_by_count":12,"area":null},{"id":"2105.03343","title":"Adapting by Pruning: A Case Study on BERT","created":"2021-05-07","cited_by_count":11,"area":null},{"id":"2210.03923","title":"Sparse Teachers Can Be Dense with Knowledge","created":"2022-10-08","cited_by_count":11,"area":null},{"id":"2101.08890","title":"Distilling Large Language Models into Tiny and Effective Students using pQRNN","created":"2021-01-21","cited_by_count":10,"area":"distill"},{"id":"2204.11218","title":"Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training","created":"2022-04-24","cited_by_count":10,"area":null},{"id":"2206.02976","title":"Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm","created":"2022-06-07","cited_by_count":9,"area":null},{"id":"2212.07634","title":"Gradient-based Intra-attention Pruning on Pre-trained Language Models","created":"2022-12-15","cited_by_count":9,"area":"distill"},{"id":"2303.09266","title":"SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference","created":"2023-03-16","cited_by_count":9,"area":"inference"},{"id":"2312.00960","title":"The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models","created":"2023-12-01","cited_by_count":9,"area":null},{"id":"2606.06574","title":"Skip a Layer or Loop It? Learning Program-of-Layers in LLMs","created":"2026-06-04","cited_by_count":9,"area":null},{"id":"2110.10305","title":"When in Doubt, Summon the Titans: Efficient Inference with Large Models","created":"2021-10-19","cited_by_count":8,"area":null},{"id":"2111.00160","title":"DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models","created":"2021-10-30","cited_by_count":8,"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":"2301.07966","title":"Getting Away with More Network Pruning: From Sparsity to Geometry and Linear Regions","created":"2023-01-19","cited_by_count":8,"area":null},{"id":"2303.09663","title":"Efficient Computation Sharing for Multi-Task Visual Scene Understanding","created":"2023-03-16","cited_by_count":8,"area":null},{"id":"2312.05795","title":"Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroup","created":"2023-12-10","cited_by_count":8,"area":"mllm"},{"id":"2407.19126","title":"Greedy Output Approximation: Towards Efficient Structured Pruning for LLMs Without Retraining","created":"2024-07-26","cited_by_count":8,"area":null},{"id":"2103.01819","title":"The Rediscovery Hypothesis: Language Models Need to Meet Linguistics","created":"2021-03-02","cited_by_count":7,"area":null},{"id":"2201.08539","title":"AutoDistill: an End-to-End Framework to Explore and Distill Hardware-Efficient Language Models","created":"2022-01-21","cited_by_count":7,"area":null},{"id":"2205.02340","title":"Knowledge Distillation of Russian Language Models with Reduction of Vocabulary","created":"2022-05-04","cited_by_count":7,"area":"distill"},{"id":"2208.12866","title":"Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementation","created":"2022-08-26","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":"2310.13191","title":"Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models","created":"2023-10-19","cited_by_count":7,"area":null},{"id":"2311.08623","title":"DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Models","created":"2023-11-15","cited_by_count":7,"area":"inference"},{"id":"2104.11928","title":"Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation","created":"2021-04-24","cited_by_count":6,"area":"distill"},{"id":"2306.14393","title":"Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference","created":"2023-06-26","cited_by_count":6,"area":"inference"},{"id":"2406.01468","title":"Understanding Token Probability Encoding in Output Embeddings","created":"2024-06-03","cited_by_count":6,"area":null}],"next_cursor":"100"}