training dynamics

Debiased Sample Selection for Learning with Noisy Labels CVPR 2026 Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models AAAI 2026 Learning from Evolving Training Dynamics: An Entropy-Maximizing Data Curation Strategy for LLM Supervised Post-Training ACL 2026 Neural Tangent Kernels Under Stochastic Data Augmentation AAAI 2026 On the Hidden Objective Biases of Group-based Reinforcement Learning ACL 2026 Scaling and Transferability of Annealing Strategies in Large Language Model Training AAAI 2026 SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe ACL 2026 Understanding, Accelerating, and Improving MeanFlow Training CVPR 2026 When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks COLT 2026 Analyzing Offensive Language Dataset Insights from Training Dynamics and Human Agreement Level COLING 2025 An Analysis for Reasoning Bias of Language Models with Small Initialization ICML 2025 A Proactive Reliability Metric for Detecting Failures in Language Model Training EMNLP 2025 A Theoretical Analysis of Self-Supervised Learning for Vision Transformers ICLR 2025 Beyond Conventional Metrics: using Entropic Triangles to Explain Balancing Methods in Acoustic Scene Classification Interspeech 2025 Capturing the Temporal Dependence of Training Data Influence ICLR 2025 Common Ground, Diverse Roots: The Difficulty of Classifying Common Examples in Spanish Varieties COLING 2025 Convergence and Divergence of Language Models under Different Random Seeds EMNLP 2025 Data Drives Unstable Hierarchical Generalization in LMs EMNLP 2025 Does SGD really happen in tiny subspaces? ICLR 2025 DynClean: Training Dynamics-based Label Cleaning for Distantly-Supervised Named Entity Recognition NAACL 2025 Exploring smaller batch sizes for a high-performing BabyLM model architecture EMNLP 2025 FTFT: Efficient and Robust Fine-Tuning by Transferring Training Dynamics COLING 2025 Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training ACL 2025 How Distributed Collaboration Influences the Diffusion Model Training? A Theoretical Perspective ICML 2025 Hypernym Bias: Unraveling Deep Classifier Training Dynamics through the Lens of Class Hierarchy AISTATS 2025