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
34 results for “keyword:"best of n"” in ICLR 2027. 13 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Do RTL Verifiers Lie? Measuring Proxy-Reward Overoptimization in LLM Hardware Design▼4.5k2.67
[PDF]Curbing the Winner’s Curse: Reward Aggregation Mitigates Inference-Time Reward Hacking▼4.3k2.00
[PDF]Design yield is a tail functional: why distributional metrics cannot rank generative designers▲6.1k2.00
[PDF]Reading Is Not Verifying: Auditing Relation-Conditioned Evaluators for Selection and Guidance▲3952.67
[PDF]How Far Can Reasoning Alone Take You? Graph-Based Candidate Selection for Test-Time Scaling on Code▲3952.67
[PDF]Whether or Where? Tail Calibration Signals Finite-Budget Reward Hacking in Best-of-N Selection▼1.2k1.67
Withdrawn or desk rejected (13)
[PDF]Auditing Reward-Model Selection on Tool Trajectories: Identification, Policy Utility, and Natural TransferWithdrawn1.67
[PDF]What Does a Copyright Budget Certify? An Exact Threshold for Per-Token Meters, and a Length-Independent Certificate for SelectionWithdrawn1.67