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
191 results for “keyword:"budget"” in ICLR 2027. 48 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Tree-based Adaptive Block Elimination with Exemplar Sampling for Best Arm Identification▼4.3k2.00
[PDF]Where Does Attention Mass Live? A Matched-Budget Study of Query-Adaptive Attention Sparsification for Decoder LMs▼1361.33
[PDF]Epistemic Debt in Coding Agents: Repaying Unsupported Assumptions in Repository-Level Software Engineering▼5.8k2.33
[PDF]Rewards for budget-aware multi-turn agents that dynamically adapt to arbitrary test-time constraints▲3952.67
[PDF]Reliable Evidence Path Selection in Graph-Based RAG via Fuzzy Evidence-Guided Reasoning▼4.3k2.00
[PDF]Termination Calibration Recovers Answers That Reasoning Models Compute but Never Express▼4.5k2.67
[PDF]Oracle Coverage Can Reverse Rankings: Finite-Budget Identification in Test-Time Scaling▲3952.67
Withdrawn or desk rejected (48)
[PDF]Evidence-Budgeted Light Transport Representation Learning: Wall-Reflected Screen Content RecoveryWithdrawn1.33
[PDF]What Does a Copyright Budget Certify? An Exact Threshold for Per-Token Meters, and a Length-Independent Certificate for SelectionWithdrawn1.67
[PDF]What to Try, Where to Try It: Online Adaptive Search Policies for Machine Learning Agents.Withdrawn1.33
[PDF]What Data Makes World Models Better Manipulation Planners? Beyond Successful Demonstrations with Diverse Action ExperienceWithdrawn1.00