{"total":27,"rows":[{"id":"2309.14316","title":"Physics of Language Models: Part 3.1, Knowledge Storage and Extraction","created":"2023-09-25","cited_by_count":270,"area":null},{"id":"2206.12562","title":"PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance","created":"2022-06-25","cited_by_count":79,"area":null},{"id":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"area":null},{"id":"2105.12002","title":"Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization","created":"2021-05-25","cited_by_count":56,"area":null},{"id":"2303.04222","title":"SemEval-2023 Task 10: Explainable Detection of Online Sexism","created":"2023-03-07","cited_by_count":48,"area":null},{"id":"2205.10475","title":"DeepStruct: Pretraining of Language Models for Structure Prediction","created":"2022-05-21","cited_by_count":45,"area":null},{"id":"2212.08136","title":"Efficient Long Sequence Modeling via State Space Augmented Transformer","created":"2022-12-15","cited_by_count":37,"area":null},{"id":"2204.06644","title":"METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals","created":"2022-04-13","cited_by_count":20,"area":null},{"id":"2211.16742","title":"Protein Language Models and Structure Prediction: Connection and Progression","created":"2022-11-30","cited_by_count":17,"area":null},{"id":"2202.02664","title":"No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models","created":"2022-02-06","cited_by_count":15,"area":null},{"id":"2110.08419","title":"Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding","created":"2021-10-16","cited_by_count":12,"area":null},{"id":"2111.02570","title":"CLUES: Few-Shot Learning Evaluation in Natural Language Understanding","created":"2021-11-04","cited_by_count":9,"area":null},{"id":"2104.04886","title":"Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach","created":"2021-04-11","cited_by_count":7,"area":null},{"id":"2204.06625","title":"CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharing","created":"2022-04-13","cited_by_count":6,"area":null},{"id":"2205.11416","title":"The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains","created":"2022-05-23","cited_by_count":6,"area":null},{"id":"2104.05847","title":"Targeted Adversarial Training for Natural Language Understanding","created":"2021-04-12","cited_by_count":5,"area":null},{"id":"2107.05377","title":"A Flexible Multi-Task Model for BERT Serving","created":"2021-07-12","cited_by_count":4,"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":"2109.05178","title":"College Student Retention Risk Analysis From Educational Database using Multi-Task Multi-Modal Neural Fusion","created":"2021-09-11","cited_by_count":1,"area":null},{"id":"2109.07048","title":"ARCH: Efficient Adversarial Regularized Training with Caching","created":"2021-09-15","cited_by_count":1,"area":null},{"id":"2310.07347","title":"Fast-ELECTRA for Efficient Pre-training","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2105.05535","title":"OCHADAI-KYOTO at SemEval-2021 Task 1: Enhancing Model Generalization and Robustness for Lexical Complexity Prediction","created":"2021-05-12","cited_by_count":0,"area":null},{"id":"2106.05221","title":"Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning","created":"2021-06-08","cited_by_count":0,"area":null},{"id":"2206.03025","title":"OCHADAI at SemEval-2022 Task 2: Adversarial Training for Multilingual Idiomaticity Detection","created":"2022-06-07","cited_by_count":0,"area":null},{"id":"2305.07475","title":"Comprehensive Solution Program Centric Pretraining for Table-and-Text Hybrid Numerical Reasoning","created":"2023-05-12","cited_by_count":0,"area":null},{"id":"2405.04513","title":"Switchable Decision: Dynamic Neural Generation Networks","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2510.04044","title":"Quantization Range Estimation for Convolutional Neural Networks","created":"2025-10-05","cited_by_count":0,"area":null}],"next_cursor":null}