exponential moving average

Adaptive Momentum and EMA-weighted Modeling for Imbalanced Label Distribution Learning AAAI 2026 Batch Loss Score for Dynamic Data Pruning CVPR 2026 Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Diffusion Transformers CVPR 2026 KVSmooth: Mitigating Hallucination in Multi-modal Large Language Models through Key-Value Smoothing CVPR 2026 Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation CVPR 2026 Robust Pseudo-Labeling via Decoupled Class-Aware Filtering and Dynamic Category Correction AAAI 2026 YNU-HPCC at SemEval-2026 Task 9: Hybrid Augmentation and Regularization Strategies for Multilingual Polarization Type Classification SemEval 2026 Dual-Rate Dynamic Teacher for Source-Free Domain Adaptive Object Detection ICCV 2025 How to set AdamW’s weight decay as you scale model and dataset size ICML 2025 Large Continual Instruction Assistant ICML 2025 Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection CVPR 2025 Object-Centric Pretraining via Target Encoder Bootstrapping ICLR 2025 The AdEMAMix Optimizer: Better, Faster, Older ICLR 2025 Adam with model exponential moving average is effective for nonconvex optimization NeurIPS 2024 Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression ICLR 2024 Friendly Sharpness-Aware Minimization CVPR 2024 Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length NeurIPS 2024 OD-DETR: Online Distillation for Stabilizing Training of Detection Transformer IJCAI 2024 Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning NeurIPS 2024 Self-Supervised Speaker Verification with Mini-Batch Prediction Correction Interspeech 2024 Stabilizing Zero-Shot Prediction: A Novel Antidote to Forgetting in Continual Vision-Language Tasks NeurIPS 2024 Unraveling Batch Normalization for Realistic Test-Time Adaptation AAAI 2024 A Probabilistic Framework for Lifelong Test-Time Adaptation CVPR 2023 Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers ICML 2023 BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning ICML 2023