learning dynamics

Annotation Entropy Predicts Per-Example Learning Dynamics in LoRA Fine-Tuning ACL 2026 Dynamics-Aware Preference Optimization for Vision-Language Models CVPR 2026 Emergent Fast-Slow Dynamics in Multi-Agent Q-Learning for Networked Stochastic Games AAAI 2026 On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD AAAI 2026 The Search for Stability: Learning Dynamics of Strategic Publishers with Initial Documents (Abstract Reprint) AAAI 2026 A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language ICLR 2025 Beyond Surprisal: A Dual Metric Framework for Lexical Skill Acquisition in LLMs COLING 2025 Data Drives Unstable Hierarchical Generalization in LMs EMNLP 2025 Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient ICLR 2025 Exploring Forgetting in Large Language Model Pre-Training ACL 2025 How Gradient descent balances features: A dynamical analysis for two-layer neural networks ICLR 2025 Investigating ReLoRA: Effects on the Learning Dynamics of Small Language Models EMNLP 2025 Learning a Single Index Model from Anisotropic Data with Vanilla Stochastic Gradient Descent AISTATS 2025 Learning Dynamics in Continual Pre-Training for Large Language Models ICML 2025 Learning Dynamics of LLM Finetuning ICLR 2025 Monitoring Primitive Interactions During the Training of DNNs AAAI 2025 Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training ICLR 2025 Swing-by Dynamics in Concept Learning and Compositional Generalization ICLR 2025 Synchronization in Learning in Periodic Zero-Sum Games Triggers Divergence from Nash Equilibrium AAAI 2025 Three Mechanisms of Feature Learning in a Linear Network ICLR 2025 To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions ICLR 2025 Towards Memorization Estimation: Fast, Formal and Free ICML 2025 Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks ICML 2025 Action Space Design in Reinforcement Learning for Robot Motor Skills CoRL 2024 A distributional simplicity bias in the learning dynamics of transformers NeurIPS 2024