training instability

Residual Koopman Spectral Profiling for Predicting and Preventing Transformer Training Instability UAI 2026 Scale Regularization for Stable Low-Rank Adaptation AAAI 2026 A Proactive Reliability Metric for Detecting Failures in Language Model Training EMNLP 2025 Instability in Downstream Task Performance During LLM Pretraining EMNLP 2025 Taming LLMs with Gradient Grouping ACL 2025 The Four Color Theorem for Cell Instance Segmentation ICML 2025 Variance Sensitivity Induces Attention Entropy Collapse and Instability in Transformers EMNLP 2025 YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model ACL 2025 Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression ICLR 2024 Small-scale proxies for large-scale Transformer training instabilities ICLR 2024 Measuring and Mitigating Local Instability in Deep Neural Networks ACL 2023 On the Training Instability of Shuffling SGD with Batch Normalization ICML 2023 A Loss Curvature Perspective on Training Instabilities of Deep Learning Models ICLR 2022 Gradient Normalization for Generative Adversarial Networks ICCV 2021 Nondeterminism and Instability in Neural Network Optimization ICML 2021 Understanding the Difficulty of Training Transformers EMNLP 2020