weight averaging

Modality-Balanced Collaborative Distillation for Multi-Modal Domain Generalization AAAI 2026 Scaling Up Temporal Domain Generalization via Temporal Experts Averaging EMNLP 2025 Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averaging WACV 2025 Towards Machine Unlearning for Paralinguistic Speech Processing Interspeech 2025 FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler ICML 2024 Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning ACL 2024 Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning ICLR 2024 Universal Test-Time Adaptation Through Weight Ensembling, Diversity Weighting, and Prior Correction WACV 2024 WARM: On the Benefits of Weight Averaged Reward Models ICML 2024 WATT: Weight Average Test Time Adaptation of CLIP NeurIPS 2024 Where Do Large Learning Rates Lead Us? NeurIPS 2024 AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models EACL 2023 CFA: Class-Wise Calibrated Fair Adversarial Training CVPR 2023 Data augmentation alone can improve adversarial training ICLR 2023 Domain Aligned Prefix Averaging for Domain Generalization in Abstractive Summarization ACL 2023 Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models ICML 2023 Lookaround Optimizer: k steps around, 1 step average NeurIPS 2023 Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization ICML 2023 PlayGround Low Resource Machine Translation System for the 2023 AmericasNLP Shared Task ACL 2023 Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models ICCV 2023 Rehearsal-Free Online Continual Learning for Automatic Speech Recognition Interspeech 2023 Should Under-parameterized Student Networks Copy or Average Teacher Weights? NeurIPS 2023 Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions ICLR 2023 Continual Test-Time Domain Adaptation CVPR 2022 Diverse Weight Averaging for Out-of-Distribution Generalization NeurIPS 2022