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
131 results for “keyword:"looped"” in ICLR 2027. 10 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models▲1.9k3.67
[PDF]Mimir: A Sub-2B Hierarchical Reasoning Model Trained on Permissible Data Punches Above Its Weight Class▼1.2k1.67
[PDF]Shared Weights, Selected Computations: How Looped Transformers Route What Each Loop Does▼4.3k2.00
[PDF]Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models▼4.5k2.67
[PDF]Beyond the Training Horizon: Mechanisms and Limits of Length Generalization in Looped Transformers▲13k2.33
[PDF]What Does Another Loop Buy? Attention Reallocation Tracks the Marginal Value of Test-Time Compute in Looped Transformers▲3952.67
[PDF]How Much Can Loops Replace Parameters? Sharp Storage–Computation Frontiers for Looped Neural Networks▼1.2k3.00
Withdrawn or desk rejected (10)
[PDF]Same Head, Different Calls? Auditing Functional Role Claims in Looped TransformersWithdrawn1.33
[PDF]Same Answer, Different Futures: Judging Latent States by Their Continuations in Looped TransformersDesk rejected
[PDF]The Loop Records Where It Slipped: Verifying Execution Slips in Looped Language ModelsDesk rejected