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
289 results for “keyword:"loop"” in ICLR 2027. 54 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]LoopLUT: 3D Lookup Tables with Progressive Region Refinement for Real-Time 4K Image Enhancement▼5.8k2.33
[PDF]The Correction Budget: When Test-Time Refinement Can and Cannot Fix World-Model Rollouts▼1601.50
[PDF]Recurrent Refinement Moves Candidate-Quality Readability Earlier and Stabilizes Its Coordinates▼1.2k1.67
[PDF]WAM-Bench: A Closed-Loop Benchmark for Open-Ended Instruction Following in Autonomous Driving▲4.7k3.25
[PDF]Learning from Recurrence: Internalizing Depth-Induced Preferences in Looped Language Models▲3.0k2.33
Withdrawn or desk rejected (54)
[PDF]The Verifier-Bit Ledger: A Leakage Ceiling and an Executable Audit for Verifier-in-the-Loop ReasoningWithdrawn1.67
[PDF]Sequential Group-Relative Test-Time Adaptation for LLM-planner on a Closed-loop Single Driving TimelineWithdrawn2.00
[PDF]Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action ModelsDesk rejected2.00
[PDF]Same Head, Different Calls? Auditing Functional Role Claims in Looped TransformersWithdrawn1.33
[PDF]SceneFactory-3D: Physical Grounded Counterfactual Simulation for Closed-Loop Traffic EvaluationWithdrawn1.67