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
138 results for “keyword:"training dynamics"” in ICLR 2027. 35 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Weight Decay and Neuron Condensation: A Three-Stage Analysis of Two-Layer ReLU Networks▲2623.67
[PDF]Eigenbases Without Eigenvalues: Exact Amplification Laws for Spectral Preconditioning on Rank-Deficient Gradient Flows▲6.1k2.00
[PDF]Implicit Low-Rank Training Dynamics in Directly Parameterized Lipschitz-Bounded deep Networks▲5103.00
[PDF]Future Data Allocation Shapes Repetition-History Persistence in Language Model Pretraining▲5.7k2.00
[PDF]When Prediction Chooses the Representation: Learning Dynamics and Planning in World Models▼4.3k2.00
[PDF]Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate▲3.9k1.67
[PDF]Towards Characterizing Spiking Neural Networks: An Empirical Study of Loss Landscapes and Diffusion Dynamics▼1.2k1.67
[PDF]A Theoretical Analysis of Sparse Mixture-of-Experts Routing via Compatibility Optimal Transport
[PDF]High-Dimensional Dynamics of Mixture-of-Experts: Phase Transitions, Routing, and Specialization▼4.5k2.67
[PDF]Persistent Depth Ordering amid Shifting Block-Bypass Responses in Language Model Pretraining▲6.1k2.00
Withdrawn or desk rejected (35)
[PDF]Tracing How Backdoors Are Learned: Poisoned Sample Detection via Information-Trajectory DistortionWithdrawn1.33
[PDF]Data-Weight Directions Rotate Along Training: Horizon-Matched Attribution for GUI TrajectoriesWithdrawn1.33
[PDF]Learning to Be Fooled: pretraining grows knowledge but keeps the scar of framing susceptibilityDesk rejected
[PDF]Before the Breakthrough: Bottleneck Crossings as Precursors in Long-Horizon Agent RLWithdrawn2.00