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
70 results for “keyword:"adam"” in ICLR 2027. 8 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]A DEAFENING SILENCE: CATASTROPHIC FORGETTING LIVES IN THE OUTPUT EMBEDDINGS OF TOKENS THE DATA NEVER SPEAKS▼4.5k2.67
[PDF]Logarithmic Activation Clocks in Diagonal Linear Networks: When SGD Does and Does Not Follow Lasso▼1351.33
[PDF]Regularized Regression for Hadamard Manifold-Valued Data: Finite-Sample Bounds and Tangent-Space Sparsity▲6.1k2.00
[PDF]Attainment Is Not Stationarity: Objective and Optimizer Sources of Behavioral Drift after Safety Alignment▼4.3k2.00
[PDF]Identity-Exact Multi-Bias Activations: Breaking Optimization Symmetry Without Changing the Pretrained Function▼1351.33
[PDF]The Clocks of Composition: Built by the Signal, Lost to Weight Decay, Kept by Rehearsal▼1.2k1.67
[PDF]SAT-LLM: Conversion-Aware Fine-Tuning of Large Language Models for Low-Latency Spiking Deployment▼1.2k1.67
[PDF]Adam as Magnitude-Weighted Sign Descent: Dimension-Free Convergence under Weak Assumptions▲153.33
[PDF]The Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive Consolidation▼4.3k2.00
[PDF]Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimization▼4.5k2.67
[PDF]Sharp Heterogeneity Barriers for Adam: Basis-Aware Convergence and High-Dimensional Divergence▲4002.67
[PDF]Hadamizer: Spatio-Temporally Adaptive Hadamard Rotation for Low-Precision Distributed Optimization▼1351.33
[PDF]Muon–Adam Training for Overparameterized Neural Networks: Convergence and Generalization▼4.3k2.00
Withdrawn or desk rejected (8)
[PDF]Beyond Estimator Moments: Minimal Information for Predicting Zeroth-Order Adam's ResponseDesk rejected
[PDF]When Is Optimizer Memory Federable? Adaptive Synchronization in Federated LearningWithdrawn2.00