{"total":40,"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":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177,"area":null},{"id":"2109.04312","title":"MATE: Multi-view Attention for Table Transformer Efficiency","created":"2021-09-09","cited_by_count":54,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47,"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":"2107.06569","title":"Importance-based Neuron Allocation for Multilingual Neural Machine Translation","created":"2021-07-14","cited_by_count":23,"area":null},{"id":"2102.01670","title":"Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization","created":"2021-02-02","cited_by_count":22,"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":"2310.14848","title":"Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Survey","created":"2023-10-23","cited_by_count":18,"area":null},{"id":"2407.05694","title":"On the Limitations of Compute Thresholds as a Governance Strategy","created":"2024-07-08","cited_by_count":18,"area":null},{"id":"2103.13678","title":"Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation","created":"2021-03-25","cited_by_count":15,"area":null},{"id":"2209.05948","title":"Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems","created":"2022-09-13","cited_by_count":13,"area":null},{"id":"2105.01303","title":"Personalized Algorithm Generation: A Case Study in Learning ODE Integrators","created":"2021-05-04","cited_by_count":9,"area":null},{"id":"2305.04507","title":"FedZKP: Federated Model Ownership Verification with Zero-knowledge Proof","created":"2023-05-08","cited_by_count":9,"area":null},{"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":"2110.15225","title":"Pruning Attention Heads of Transformer Models Using A* Search: A Novel Approach to Compress Big NLP Architectures","created":"2021-10-28","cited_by_count":6,"area":null},{"id":"2205.00199","title":"Cracking White-box DNN Watermarks via Invariant Neuron Transforms","created":"2022-04-30","cited_by_count":6,"area":null},{"id":"2211.01542","title":"Continual Learning of Neural Machine Translation within Low Forgetting Risk Regions","created":"2022-11-03","cited_by_count":6,"area":null},{"id":"2101.12016","title":"Baseline Pruning-Based Approach to Trojan Detection in Neural Networks","created":"2021-01-22","cited_by_count":5,"area":null},{"id":"2211.04256","title":"Bridging Fairness and Environmental Sustainability in Natural Language Processing","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2305.06085","title":"FedSOV: Federated Model Secure Ownership Verification with Unforgeable Signature","created":"2023-05-10","cited_by_count":4,"area":null},{"id":"2110.04252","title":"LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time","created":"2021-10-08","cited_by_count":3,"area":null},{"id":"2112.02346","title":"Logic Shrinkage: Learned FPGA Netlist Sparsity for Efficient Neural Network Inference","created":"2021-12-04","cited_by_count":3,"area":null},{"id":"2110.03298","title":"End-to-End Supermask Pruning: Learning to Prune Image Captioning Models","created":"2021-10-07","cited_by_count":2,"area":null},{"id":"2510.22767","title":"TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2106.10002","title":"Recurrent Stacking of Layers in Neural Networks: An Application to Neural Machine Translation","created":"2021-06-18","cited_by_count":1,"area":null},{"id":"2210.00743","title":"An Embarrassingly Simple Approach for Intellectual Property Rights Protection on Recurrent Neural Networks","created":"2022-10-03","cited_by_count":1,"area":null},{"id":"2302.04045","title":"Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models","created":"2023-02-08","cited_by_count":1,"area":null},{"id":"2407.03883","title":"Protecting Deep Learning Model Copyrights with Adversarial Example-Free Reuse Detection","created":"2024-07-04","cited_by_count":1,"area":null},{"id":"2408.14055","title":"HAPM -- Hardware Aware Pruning Method for CNN hardware accelerators in resource constrained devices","created":"2024-08-26","cited_by_count":1,"area":null},{"id":"2101.07415","title":"ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces","created":"2021-01-19","cited_by_count":0,"area":null},{"id":"2102.01194","title":"A Statistician Teaches Deep Learning","created":"2021-01-29","cited_by_count":0,"area":null},{"id":"2205.08199","title":"Sharp asymptotics on the compression of two-layer neural networks","created":"2022-05-17","cited_by_count":0,"area":null},{"id":"2310.19232","title":"Adapter Pruning using Tropical Characterization","created":"2023-10-30","cited_by_count":0,"area":null},{"id":"2607.25529","title":"Are the High-weight Neurons the Important Ones in Image Classification Neural Networks?","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.03480","title":"Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.19042","title":"FedASAP: Activation Statistics-driven Structured Adaptive Pruning for Efficient Personalized Federated Learning for Lesion Segmentation on brain MRI","created":"2026-07-20","cited_by_count":0,"area":null}],"next_cursor":null}