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
116 results for “keyword:"optimizer"” in ICLR 2027. 20 withdrawn or desk rejected listed apart.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]From Spectral Measurement to Feedback Collapse: The Limits of Adaptive Orthogonal Optimization▼4.3k2.00
[PDF]Which Updates Erase What the Base Model Knew? Optimizer-Conditioned Attribution of Reasoning-Support Loss in RLVR▼5.8k2.33
[PDF]Attainment Is Not Stationarity: Objective and Optimizer Sources of Behavioral Drift after Safety Alignment▼4.3k2.00
[PDF]Not All Blocks Need Full Momentum: Sharpness-Aware Memory-Efficient Optimization for Transformers▼4.3k2.00
[PDF]Optimizer-dependent training dynamics converge to the same one-third optimal data scaling▲3.0k2.33
[PDF]Towards 1:4 semi-structured 75% sparsity via Cannistraci-Hebb N:M dynamic sparse-to-sparse training▼1351.33
[PDF]Scaling Feedback Alone Is Not Scaling Supervision: From Prediction Quality to Decision Quality in Reward Learning▼1351.33
[PDF]ChromaMuon: Spectral Optimizer Diagnostics and Design with Retained Newton–Schulz Coordinates▼1.2k1.67
[PDF]Spectral-Driven Adaptive-Rank Optimizer for Large Language Model Reinforcement Learning with Verifiable Rewards▲3.0k2.33
[PDF]Decoupled Polynomial State-Space Iterations for Matrix Polar Approximation, with an Application to Muon▼4.3k2.00
Withdrawn or desk rejected (20)
[PDF]Training-Loss Guarantees for Muon with Finite-Step Newton-Schulz OrthogonalizationWithdrawn1.67
[PDF]Restoring Inputs Is Not Restoring Learning: Sparse Restoration in Multimodal TrainingDesk rejected1.67
[PDF]OPTScientist: Toward Recursive Self-Improving Agents via Automated Optimizer DiscoveryWithdrawn1.33