{"total":8,"rows":[{"id":"2210.07558","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","created":"2022-10-14","cited_by_count":233,"area":null},{"id":"2207.01426","title":"Dynamic Contrastive Distillation for Image-Text Retrieval","created":"2022-07-04","cited_by_count":14,"area":null},{"id":"2205.15683","title":"Why are NLP Models Fumbling at Elementary Math? A Survey of Deep Learning based Word Problem Solvers","created":"2022-05-31","cited_by_count":9,"area":null},{"id":"2305.12449","title":"Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter","created":"2023-05-21","cited_by_count":8,"area":null},{"id":"2205.14570","title":"MiniDisc: Minimal Distillation Schedule for Language Model Compression","created":"2022-05-29","cited_by_count":5,"area":null},{"id":"2112.07327","title":"Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models","created":"2021-12-14","cited_by_count":2,"area":null},{"id":"2210.05230","title":"From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models","created":"2022-10-11","cited_by_count":1,"area":null},{"id":"2310.07911","title":"Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention","created":"2023-10-11","cited_by_count":1,"area":null}],"next_cursor":null}