Model Merging

DeepME: Deep Mixture Experts for Large-scale Image Classification IJCAI 2021 Deep Multi-Task Learning for Joint Localization, Perception, and Prediction CVPR 2021 EndTimes at SemEval-2021 Task 7: Detecting and Rating Humor and Offense with BERT and Ensembles SemEval 2021 Ensembling With a Fixed Parameter Budget: When Does It Help and Why? ACML 2021 Free-rider Attacks on Model Aggregation in Federated Learning AISTATS 2021 Global explanations with decision rules: a co-learning approach UAI 2021 IAPUCP at SemEval-2021 Task 1: Stacking Fine-Tuned Transformers is Almost All You Need for Lexical Complexity Prediction SemEval 2021 Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic SemEval 2021 Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling ICML 2021 Meta-Learning Sparse Implicit Neural Representations NeurIPS 2021 MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection SemEval 2021 Model Linkage Selection for Cooperative Learning JMLR 2021 Neural networks with late-phase weights ICLR 2021 One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking CVPR 2021 PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation Interspeech 2021 ReCAM@IITK at SemEval-2021 Task 4: BERT and ALBERT based Ensemble for Abstract Word Prediction SemEval 2021 Revisiting Pretraining with Adapters ACL 2021 SRPOL DIALOGUE SYSTEMS at SemEval-2021 Task 5: Automatic Generation of Training Data for Toxic Spans Detection SemEval 2021 Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers EMNLP 2021 THiFly_Queens at SemEval-2021 Task 9: Two-stage Statement Verification with Adaptive Ensembling and Slot-based Operation SemEval 2021 Towards Reusable Network Components by Learning Compatible Representations AAAI 2021 TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness NeurIPS 2021 Two Heads are Better than One? Verification of Ensemble Effect in Neural Machine Translation EMNLP 2021 Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation EMNLP 2021 UTNLP at SemEval-2021 Task 5: A Comparative Analysis of Toxic Span Detection using Attention-based, Named Entity Recognition, and Ensemble Models SemEval 2021