NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
72 results for “keyword:"learning dynamics"” in ICLR 2027. 11 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]On Delayed Learning in Reinforcement Learning with Verifiable Rewards: Provable Laws of Feedback and Recovery
[PDF]Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention▲5103.00
[PDF]Compiled Agency: Coding Agents as Game AI Researchers — from a Roguelike to StarCraft II and Civilization▲9.2k2.67
[PDF]Neural Succession: A Mesoscopic Theory of Invasion, Coexistence, and Stabilization in Continual Learning▼1.2k1.67
[PDF]Multi-Token Prediction and Alternative Tokenization Improve Learning Latent Multi-Hop Graph Search at Scale▲153.33
[PDF]A Framework for Analyzing DNN Representation Quality: Dynamics of Interaction Generalizability▼71.25
[PDF]Same Fit, Different Damage: Learning Order and Functional Dependence in Noisy-Label Memorization▼5.8k2.33
[PDF]Overtopping in LLMs: Spiking-Like Causal Control and the Limits of Static Intervention▼5.8k2.33
[PDF]Fine-Tuning on Self-Generated and Reward-Weighted Data: Learning Dynamcis, Convergence Rates, and Benefits of Off-Policyness▲153.33
[PDF]Generalization and Memorization along the Learning Trajectory of Neural Language Models: A Geometric Account of Categorization▼1351.33
Withdrawn or desk rejected (11)
[PDF]Generalized Residual Closure: General Learning Dynamics for Stability–Plasticity CompatibilityWithdrawn2.00
[PDF]From Class Means to Margins: Predicting Hidden-Unit Placement in Width-One NetworksWithdrawn1.00
[PDF]A PHYSICAL THEORY OF BACKPROPAGATION: EXACT GRADIENTS FROM THE LEAST-ACTION PRINCIPLEWithdrawn1.67
[PDF]When Does DPO Add Value over Continued SFT? Evidence from Correction-Preservation FrontiersWithdrawn1.50
[PDF]Cortico-cerebellar modularity as an architectural inductive bias for efficient temporal learningWithdrawn1.67