{"total":22,"rows":[{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234,"area":null},{"id":"2202.00155","title":"Fortuitous Forgetting in Connectionist Networks","created":"2022-02-01","cited_by_count":39,"area":null},{"id":"2105.14556","title":"Diversifying Dialog Generation via Adaptive Label Smoothing","created":"2021-05-30","cited_by_count":25,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2310.03295","title":"Can pre-trained models assist in dataset distillation?","created":"2023-10-05","cited_by_count":12,"area":null},{"id":"2104.03618","title":"MRI-based Alzheimer's disease prediction via distilling the knowledge in multi-modal data","created":"2021-04-08","cited_by_count":9,"area":null},{"id":"2210.05185","title":"Meta-Learning with Self-Improving Momentum Target","created":"2022-10-11","cited_by_count":9,"area":null},{"id":"2309.08035","title":"Interpretability-Aware Vision Transformer","created":"2023-09-14","cited_by_count":8,"area":null},{"id":"2410.17020","title":"LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization","created":"2024-10-22","cited_by_count":8,"area":null},{"id":"2110.06961","title":"Language Modelling via Learning to Rank","created":"2021-10-13","cited_by_count":7,"area":null},{"id":"2203.02651","title":"Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning","created":"2022-03-05","cited_by_count":5,"area":null},{"id":"2110.07879","title":"Advances and Challenges in Deep Lip Reading","created":"2021-10-15","cited_by_count":4,"area":null},{"id":"2310.07838","title":"Towards the Fundamental Limits of Knowledge Transfer over Finite Domains","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2507.22094","title":"Scaling and Distilling Transformer Models for sEMG","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2108.10197","title":"Deploying a BERT-based Query-Title Relevance Classifier in a Production System: a View from the Trenches","created":"2021-08-23","cited_by_count":2,"area":null},{"id":"2404.15678","title":"Retrieval and Distill: A Temporal Data Shift-Free Paradigm for Online Recommendation System","created":"2024-04-24","cited_by_count":1,"area":null},{"id":"2411.00907","title":"On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performance","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2501.04211","title":"CURing Large Models: Compression via CUR Decomposition","created":"2025-01-08","cited_by_count":1,"area":null},{"id":"2511.04760","title":"When Data Falls Short: Grokking Below the Critical Threshold","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2306.15918","title":"On information captured by neural networks: connections with memorization and generalization","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2308.01098","title":"Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2411.12098","title":"Federated Contrastive Learning of Graph-Level Representations","created":"2024-11-18","cited_by_count":0,"area":null}],"next_cursor":null}