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
27 results for “keyword:"compute allocation"” in ICLR 2027. 13 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Time-Series Foundation Models Anchor to Corrupted Context: A Diagnosis, a Blind Fix, and the Limits of Fixing▼5.8k2.33
[PDF]Supervise What You Certify: Stop-Harm Prediction for Early Stopping in Reasoning Models▼5.8k2.33
[PDF]MARS: Multi-Evidence Adaptive Search with State-Preserving Control for Repository-Level Program Repair▼4.3k2.00
[PDF]Verification as a Budget: Posterior-Separation Scheduling for Self-Evolving Agent Skills▼4.3k2.00
Withdrawn or desk rejected (13)
[PDF]Where to Think, What to Explore: Hierarchical Agentic Reasoning and Exploration for Coding AgentsDesk rejected1.00
[PDF]Endogenous Signals Fail to Allocate: Per-Token Compute Value Is Real, Transient, and Not LearnableWithdrawn1.33
[PDF]Which Questions Are Worth Thinking About? Cross-Developer Transfer of Thinking ValueWithdrawn1.75
[PDF]Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy OptimizationWithdrawn1.67
[PDF]The Sampling Ceiling: Why Test-Time Self-Consistency Saturates and an Oracle Rule for Allocating SamplesWithdrawn1.33