{"total":47,"rows":[{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162,"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":"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":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"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":"2104.01767","title":"WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach","created":"2021-04-05","cited_by_count":69,"area":null},{"id":"2109.05472","title":"Compute and Energy Consumption Trends in Deep Learning Inference","created":"2021-09-12","cited_by_count":61,"area":null},{"id":"2305.14928","title":"Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4","created":"2023-05-24","cited_by_count":45,"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":"2305.13246","title":"Interactive Natural Language Processing","created":"2023-05-22","cited_by_count":31,"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":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26,"area":null},{"id":"2107.07445","title":"AutoBERT-Zero: Evolving BERT Backbone from Scratch","created":"2021-07-15","cited_by_count":21,"area":null},{"id":"2201.08542","title":"Can Model Compression Improve NLP Fairness","created":"2022-01-21","cited_by_count":20,"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":"2203.03073","title":"ILDAE: Instance-Level Difficulty Analysis of Evaluation Data","created":"2022-03-07","cited_by_count":17,"area":null},{"id":"2203.01178","title":"DCT-Former: Efficient Self-Attention with Discrete Cosine Transform","created":"2022-03-02","cited_by_count":12,"area":null},{"id":"2302.06117","title":"The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment","created":"2023-02-13","cited_by_count":11,"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":"2105.14636","title":"LEAP: Learnable Pruning for Transformer-based Models","created":"2021-05-30","cited_by_count":7,"area":null},{"id":"2305.17154","title":"On convex decision regions in deep network representations","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2305.07804","title":"Improving Small Language Models on PubMedQA via Generative Data Augmentation","created":"2023-05-12","cited_by_count":6,"area":null},{"id":"2211.05927","title":"Optimal Condition Training for Target Source Separation","created":"2022-11-11","cited_by_count":5,"area":null},{"id":"2306.05809","title":"Interactive Explanation with Varying Level of Details in an Explainable Scientific Literature Recommender System","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2204.07289","title":"Identifying and Measuring Token-Level Sentiment Bias in Pre-trained Language Models with Prompts","created":"2022-04-15","cited_by_count":4,"area":null},{"id":"2303.01509","title":"EPAM: A Predictive Energy Model for Mobile AI","created":"2023-03-02","cited_by_count":4,"area":null},{"id":"2409.13521","title":"A Survey on Moral Foundation Theory and Pre-Trained Language Models: Current Advances and Challenges","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2502.18153","title":"SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2106.05822","title":"GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures","created":"2021-06-10","cited_by_count":2,"area":null},{"id":"2109.02572","title":"Enhancing Natural Language Representation with Large-Scale Out-of-Domain Commonsense","created":"2021-09-06","cited_by_count":2,"area":null},{"id":"2112.15051","title":"Does QA-based intermediate training help fine-tuning language models for text classification?","created":"2021-12-30","cited_by_count":2,"area":null},{"id":"2207.10702","title":"Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing","created":"2022-07-21","cited_by_count":2,"area":null},{"id":"2303.13745","title":"EdgeTran: Co-designing Transformers for Efficient Inference on Mobile Edge Platforms","created":"2023-03-24","cited_by_count":2,"area":null},{"id":"2304.11520","title":"Processing Natural Language on Embedded Devices: How Well Do Transformer Models Perform?","created":"2023-04-23","cited_by_count":2,"area":null},{"id":"2110.02054","title":"NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models","created":"2021-08-29","cited_by_count":1,"area":null},{"id":"2309.01576","title":"A Comparative Analysis of Pretrained Language Models for Text-to-Speech","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2310.13990","title":"A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification","created":"2023-10-21","cited_by_count":1,"area":null},{"id":"2507.20419","title":"Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2604.09437","title":"AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2208.00929","title":"giMLPs: Gate with Inhibition Mechanism in MLPs","created":"2022-08-01","cited_by_count":0,"area":null},{"id":"2504.17449","title":"HMI: Hierarchical Knowledge Management for Efficient Multi-Tenant Inference in Pretrained Language Models","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2512.00323","title":"Comparative Analysis of 47 Context-Based Question Answer Models Across 8 Diverse Datasets","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2608.14658","title":"pico-type: A 1.5M-Parameter Byte-Level Multi-Head Content Classifier","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.11334","title":"E-CONAN (Entailment, CONtradition And Neutral) Benchmarks: Arabic Textual Entailment and Natural Inference Datasets","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.33530","title":"E-CONAN (Entailment, CONtradition And Neutral) Diagnostics Dataset Investigating Linguistic Phenomena in Arabic Natural Language Understanding","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}