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289 results for “keyword:"loop"” in ICLR 2027. 54 withdrawn or desk rejected listed apart.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]Measure Once, Steer with Many: Context Contamination and Composite Control for Persona Drift in LLMs▼5.8k2.33
[PDF]Recursive Hypercompression: Phase Transitions from Self-Improvement to Self-Deterioration▼5.8k2.33
[PDF]Beyond Token-Average Loss: Rebalancing Control and Binding in Agent Policy Distillation▼1.2k1.67
[PDF]SEAM: Shared-Expert Adaptation Masked by Closed-Loop Scores in Reward Fine-Tuned Diffusion Planners▲3.0k2.33
[PDF]When Better Classifiers Make Worse Tuners: IonTrapBench and History-Gated Stopping for Closed-Loop Mass Spectrometer Tuning▼1351.33
[PDF]Optimizing Human-in-the-Loop Systems under Dynamic Trust: An Adherence-Aware Reinforcement Learning Framework▲3.0k2.33
[PDF]Deep Cognition: A Transparent, Fine-Grained Multi-Agent Deep Research System for Human-Agent Collaboration▼4.3k2.00
[PDF]Representation Sufficiency for Closed-Loop Control: Decision Risk and the Occupancy Bridge▼1.2k1.67
[PDF]MetaGround: Physics-Grounded Conditional Diffusion for Nonlinear Metamaterial Inverse Design▼1351.33
[PDF]Robust Steerability: Closed-Loop Control of Language Model Representations Under Distribution Shift▼4.5k2.67
[PDF]Data-Anchored Response Spaces for Closed-Loop Neural Components in Non-Differentiable Numerical Simulators▼1.2k1.67
[PDF]Offline Imitation Error as a Model-Selection Proxy Under Distribution Shift: Evidence from Real-Camera Active PTZ Control▼5.8k2.33
[PDF]Spectral Signatures And Emergent Equivariance In Looped Transformers For In-Context Dynamical-System Prediction▼4.3k2.00
[PDF]JaxNaviSim: A GPU-Accelerated, Data-Driven Simulator and Learning Benchmark for Maritime Navigation▼3.7k2.25
[PDF]PRELUDE: ANTICIPATING LANDING POINTS AT RACKET-SHUTTLE CONTACT VIA CONTEXT- ADAPTIVE MULTIMODAL GATING▼1.2k1.67
[PDF]Reliable and Efficient Agent Loops for Reinforcement Learning on Software Engineering Tasks▲6.1k2.00
Withdrawn or desk rejected (54)
[PDF]When Memory Hurts: Causal Measurement and Joint Read–Write Control in Long-Horizon AgentsWithdrawn1.00
[PDF]Beyond Fixed Benchmarks: Measuring Data-Scaling Behavior of Autonomous-Driving Planners on the Physical AI Autonomous Vehicles DatasetWithdrawn1.75
[PDF]Prompt-Attributable Feasibility Violations of Medium-Weight LLM-Based Control of a Cascaded Five-Reservoir SystemWithdrawn1.33
[PDF]Where Refinement Pays: Measuring and Allocating Sampling Compute in Flow-Matching Manipulation PoliciesWithdrawn2.00