{"total":482,"rows":[{"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":"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":"2305.07759","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","created":"2023-05-12","cited_by_count":449,"area":null},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419,"area":null},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415,"area":null},{"id":"2201.05596","title":"DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale","created":"2022-01-14","cited_by_count":404,"area":"moe"},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310,"area":"inference"},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235,"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":"2207.00112","title":"Language model compression with weighted low-rank factorization","created":"2022-06-30","cited_by_count":195,"area":null},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177,"area":null},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170,"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":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"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":"2306.12929","title":"Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing","created":"2023-06-22","cited_by_count":151,"area":null},{"id":"2204.06487","title":"Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning","created":"2022-04-13","cited_by_count":149,"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":"2101.04731","title":"SEED: Self-supervised Distillation For Visual Representation","created":"2021-01-12","cited_by_count":134,"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":"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":"2103.13076","title":"Finetuning Pretrained Transformers into RNNs","created":"2021-03-24","cited_by_count":96,"area":null},{"id":"2210.01351","title":"Less is More: Task-aware Layer-wise Distillation for Language Model Compression","created":"2022-10-04","cited_by_count":93,"area":null},{"id":"2311.00430","title":"Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling","created":"2023-11-01","cited_by_count":90,"area":"distill"},{"id":"2307.02628","title":"SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference","created":"2023-07-05","cited_by_count":89,"area":"inference"},{"id":"2204.07154","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","created":"2022-04-14","cited_by_count":88,"area":null},{"id":"2212.06470","title":"Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining","created":"2022-12-13","cited_by_count":88,"area":null},{"id":"2104.02096","title":"Compressing Visual-linguistic Model via Knowledge Distillation","created":"2021-04-05","cited_by_count":86,"area":"distill"},{"id":"2111.12763","title":"Sparse is Enough in Scaling Transformers","created":"2021-11-24","cited_by_count":86,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"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,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2108.07969","title":"Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better","created":"2021-08-18","cited_by_count":79,"area":"distill"},{"id":"2203.10705","title":"Compression of Generative Pre-trained Language Models via Quantization","created":"2022-03-21","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":"2406.16937","title":"A Complete Survey on LLM-based AI Chatbots","created":"2024-06-17","cited_by_count":71,"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":"2402.12030","title":"Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs","created":"2024-02-19","cited_by_count":63,"area":"distill"},{"id":"2104.07163","title":"Annealing Knowledge Distillation","created":"2021-04-14","cited_by_count":61,"area":"distill"},{"id":"2109.05472","title":"Compute and Energy Consumption Trends in Deep Learning Inference","created":"2021-09-12","cited_by_count":61,"area":null},{"id":"2104.00769","title":"Keyword Transformer: A Self-Attention Model for Keyword Spotting","created":"2021-04-01","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":"2407.01885","title":"Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application","created":"2024-07-02","cited_by_count":56,"area":"distill"},{"id":"2101.00133","title":"NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned","created":"2021-01-01","cited_by_count":52,"area":null},{"id":"2306.09486","title":"FedMultimodal: A Benchmark For Multimodal Federated Learning","created":"2023-06-15","cited_by_count":51,"area":null},{"id":"2302.04089","title":"ZipLM: Inference-Aware Structured Pruning of Language Models","created":"2023-02-07","cited_by_count":49,"area":null},{"id":"2202.05749","title":"Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense","created":"2022-02-11","cited_by_count":47,"area":"safety"},{"id":"2112.12731","title":"ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-12-23","cited_by_count":46,"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":"2110.07038","title":"Towards Efficient NLP: A Standard Evaluation and A Strong Baseline","created":"2021-10-13","cited_by_count":44,"area":null},{"id":"2311.16567","title":"MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices","created":"2023-11-28","cited_by_count":42,"area":"diffusion"},{"id":"2402.09977","title":"Fast Vocabulary Transfer for Language Model Compression","created":"2024-02-15","cited_by_count":42,"area":null},{"id":"2109.04145","title":"PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition","created":"2021-09-09","cited_by_count":41,"area":null},{"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":"2107.08147","title":"AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learning","created":"2021-07-16","cited_by_count":39,"area":null},{"id":"2108.01250","title":"Your fairness may vary: Pretrained language model fairness in toxic text classification","created":"2021-08-03","cited_by_count":39,"area":null},{"id":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","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":"2204.07675","title":"MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation","created":"2022-04-15","cited_by_count":37,"area":"moe"},{"id":"2106.13474","title":"Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains","created":"2021-06-25","cited_by_count":36,"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":"2102.12459","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","created":"2021-02-24","cited_by_count":34,"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":"2504.03360","title":"Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency","created":"2025-04-04","cited_by_count":34,"area":null},{"id":"2109.08359","title":"Distilling Linguistic Context for Language Model Compression","created":"2021-09-17","cited_by_count":33,"area":"distill"},{"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":"2108.12659","title":"DKM: Differentiable K-Means Clustering Layer for Neural Network Compression","created":"2021-08-28","cited_by_count":31,"area":null},{"id":"2205.14443","title":"A Closer Look at Self-Supervised Lightweight Vision Transformers","created":"2022-05-28","cited_by_count":31,"area":null},{"id":"2207.06867","title":"Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models","created":"2022-07-14","cited_by_count":31,"area":"distill"},{"id":"2208.10160","title":"PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation","created":"2022-08-22","cited_by_count":31,"area":"distill"},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"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":"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":"2506.14728","title":"AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes","created":"2025-06-17","cited_by_count":30,"area":"agents"},{"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":"2205.01541","title":"Efficient Fine-Tuning of BERT Models on the Edge","created":"2022-05-03","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":"2105.05912","title":"MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation","created":"2021-05-12","cited_by_count":27,"area":"distill"},{"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":"2205.01500","title":"Meta Learning for Natural Language Processing: A Survey","created":"2022-05-03","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":"2305.10010","title":"AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression","created":"2023-05-17","cited_by_count":26,"area":"distill"},{"id":"2308.13894","title":"FwdLLM: Efficient FedLLM using Forward Gradient","created":"2023-08-26","cited_by_count":26,"area":null},{"id":"2407.19409","title":"LLAVADI: What Matters For Multimodal Large Language Models Distillation","created":"2024-07-28","cited_by_count":26,"area":"mllm"},{"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":"2202.13758","title":"Logical Fallacy Detection","created":"2022-02-28","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":"2302.09632","title":"HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers","created":"2023-02-19","cited_by_count":25,"area":"distill"},{"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":"2305.16597","title":"Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models","created":"2023-05-26","cited_by_count":25,"area":null},{"id":"2308.14363","title":"Mobile Foundation Model as Firmware","created":"2023-08-28","cited_by_count":25,"area":null}],"next_cursor":"100"}