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
30 results for “keyword:"loss landscape"” in ICLR 2027. 3 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Quadratic integrate-and-fire neurons exhibit less fragmented loss landscapes and outperform leaky integrate-and-fire neurons in spike-based gradient descent▼4.3k2.00
[PDF]Back to the Weights: Training-Free Model Enhancement via Training Trajectory Extrapolation▼1.2k1.67
[PDF]Which Geometry Predicts Generalization Depends on What You Vary — Activation or Optimizer▲3952.67
[PDF]A Two-Scalar Law for Activation Functions: How Peak Slope and Peak Curvature Govern Adversarial Robustness▼1.2k1.67
[PDF]The Geometry Behind the Barrier: Fisher Geometry and Linear Mode Connectivity in Wide Neural Networks▼5.8k2.33
[PDF]When Are Spectral Modes Causal? Identification Before Intervention in Learning Dynamics▼4.3k2.00
[PDF]Predicting characteristic learning rate based on second-moment-shaped stochastic mobility▼1.2k3.00