Model Merging

XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts ACL 2024 ZipIt! Merging Models from Different Tasks without Training ICLR 2024 A Comparative Study on the Impact of Model Compression Techniques on Fairness in Language Models ACL 2023 Adam-Smith at SemEval-2023 Task 4: Discovering Human Values in Arguments with Ensembles of Transformer-based Models SemEval 2023 Adapter Pruning using Tropical Characterization EMNLP 2023 AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models EACL 2023 AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR Parsing ACL 2023 An Empirical Study of Multimodal Model Merging EMNLP 2023 Bag of Tricks for In-Distribution Calibration of Pretrained Transformers EACL 2023 Batch Model Consolidation: A Multi-Task Model Consolidation Framework CVPR 2023 Bayesian Federated Neural Matching That Completes Full Information AAAI 2023 Bidirectional Learning for Offline Model-based Biological Sequence Design ICML 2023 CMA-ES for Post Hoc Ensembling in AutoML: A Great Success and Salvageable Failure AutoML 2023 Composing Parameter-Efficient Modules with Arithmetic Operation NeurIPS 2023 CO-Net: Learning Multiple Point Cloud Tasks at Once with A Cohesive Network ICCV 2023 CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model EMNLP 2023 Darwinian Model Upgrades: Model Evolving with Selective Compatibility AAAI 2023 Differentiable Model Selection for Ensemble Learning IJCAI 2023 DREAM: Deployment of Recombination and Ensembles in Argument Mining EMNLP 2023 Editing models with task arithmetic ICLR 2023 Efficient Low-rank Backpropagation for Vision Transformer Adaptation NeurIPS 2023 Exploiting Diversity of Automatic Transcripts from Distinct Speech Recognition Techniques for Children’s Speech Interspeech 2023 Exploring All-In-One Knowledge Distillation Framework for Neural Machine Translation EMNLP 2023 From Perception to Programs: Regularize, Overparameterize, and Amortize ICML 2023 Gemel: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge NSDI 2023