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
101 results for “keyword:"update"” in ICLR 2027. 26 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Links Are Tokens as Nodes Are: Incidence-Graph Transformers with Editable Walk Encodings for Link Prediction▼4.3k2.00
[PDF]Persistent-State Activation Beyond Utility: Scale Representation and Evidence for Non-Compensatory Control▲11.00
[PDF]Rank Collapse Is Recoverable, Growing Is Not: Out-of-Sample Early Warning for Value Divergence in High-UTD Soft Actor-Critic▼1.2k1.67
[PDF]VAD-TTRL: Propose, Verify, Reinforce for Label-Free Test-Time Video Anomaly Detection and Understanding▼5.8k2.33
[PDF]When Can Old Evaluations Certify a New Model? Matching Label-Complexity Bounds Under Evaluator-Residual Drift▼4.5k2.67
[PDF]Symmetry-Restoring Rectified Update Rules for Hopfield Neural Networks: Dynamics, Theorems, and Hamming-Distance Awareness▼1.2k1.67
[PDF]When Do Stale Updates Help? Forecasting, Participation Weighting, and Step Scale in Federated Learning▼4.3k2.00
[PDF]Does Better Estimation Imply Better Selection? A Decision-Theoretic Audit of LLM Agent Updates▼1351.33
[PDF]Parameter-State Evaluation Graphs: Structure and Prediction in Finite-Horizon Adaptation▼5.8k2.33
[PDF]Nonasymptotic P Theory for Neural Networks with Applications to Small-to-Large Generalization▲3.0k2.33
[PDF]Event-Driven Parameter Dynamics for Spatiotemporal Parameter-Update Application in Deep Learning▼4.3k2.00
[PDF]Emergent, Coordinate-Specific Structure in Dense Parameter Updates for Continual Learning▲11.00
Withdrawn or desk rejected (26)
[PDF]AGOZO: Activation-Guided Orthogonalized Zeroth-Order Optimization for LLM Fine-TuningWithdrawn1.33