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
142 results for “keyword:"surrogate"” in ICLR 2027. 19 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]What Does a Thermal Surrogate Lose Without the Flow Field? Forecasting Valve-Induced Transients in Liquid-Cooled Datacenters with Graph Neural ODEs▼4.3k2.00
[PDF]LGO: A LOCAL GEOMETRY BRANCH FOR AUGMENTING NEURAL OPERATORS IN 3D INDOOR AIRFLOW PREDICTION▲9.2k2.67
[PDF]Spike-BiST: Bidirectional Stabilization of Spike Representation and Surrogate Gradient for Multi-Agent Reinforcement Learning▲9.2k2.67
[PDF]Decision-Aware Residual Calibration: Bridging the Prediction–Decision Gap in Electromagnetic Design with Sparse Feedback▲5.7k2.00
[PDF]Geometry-Aware Error Diagnosis for Data Acquisition and Training Strategy Selection in Graph Neural Network▼1.2k1.67
[PDF]From Noisy Neural Black Boxes to Concise Physical Formulas: Structure-Constrained Exact Formula Recovery▼1.2k1.67
[PDF]MUFI: Hidden-State Transfer for Multi-Fidelity Mesh PDE Surrogates via Coarse Propagation and Fine Decoding▼4.5k2.67
[PDF]MetaGround: Physics-Grounded Conditional Diffusion for Nonlinear Metamaterial Inverse Design▼1361.33
[PDF]When High Surrogate Scores Mislead: Pairwise Ranking Reliability for Offline Model-Based Optimization▼4.5k2.67
[PDF]Applied but Not Received: Designing Effective Surrogate Gradients for Spiking Neural Networks▼4.5k2.67
[PDF]Better Reconstruction, Worse Transfer: Probing Representation Geometry in Cross-Reynolds Generalisation▼1361.33
[PDF]Data-Anchored Response Spaces for Closed-Loop Neural Components in Non-Differentiable Numerical Simulators▼1.2k1.67
[PDF]PROBE HORIZON IS NOT PREDICTABLE MEMORY: MEASURING THE HISTORY A SURROGATE NEEDS ON A COMPLETE CONNECTOME MODEL▼1.2k1.67
[PDF]Estimation of Long-Term Dose-Response via Longitudinal Surrogacy under Time-Varying Confounders▼1.2k1.67
[PDF]Robust to the Wrong Attacker: Separating Model from Attacker in Graph Transformer Robustness▼4.3k2.00
[PDF]Knowing When Not to Answer: Self-Assessed Measurability and the Limits of Physics Transfer▼1361.33
[PDF]CA-MFPD: Covariance-Aware Multi-Fidelity Posterior Distillation under Scarce High-Fidelity Data▲13k2.33
[PDF]SI-HGN: Structure-Informed Hypergraph Networks for Virtual Perturbation-Based Effective Connectivity Inference▼5.8k2.33
[PDF]EG-Opt: Efficient Learning for Nonlinear Programming via Explicit Gradients from Sample-Calibrated Linear Surrogates▼5.8k2.33
[PDF]Does Known Physics Help Neural PDE Models? Only When It's Non-Redundant and Resolvable▲3.0k2.33
[PDF]Poisson-GENERIC Neural Operators: Exact Metriplectic Structure in Function Space via Casimir Entropies▼5.8k2.33
[PDF]FLOATBench: A Tabular Dataset and Benchmark for Fatigue Prediction on Floating Offshore Wind Turbine Towers▼4.5k2.25
[PDF]LITE: Layer-Wise Intermediate Token-Dropping for Efficient Structured-Grid PDE Emulation▼4.5k2.67
[PDF]ArrivalFM-OTA: A Large-Scale Benchmark for Physical Representation Learning in Analog Circuit Design▼4.3k2.00
[PDF]Gauss–Newton is Blind to Embedded Saddles: Value-Trained Surrogates as a Derivative Oracle for Amortized Inversion▼1361.33
Withdrawn or desk rejected (19)
[PDF]Partition-of-Unity Adapters for Efficient Local Refinement of Implicit PDE RepresentationsWithdrawn2.00
[PDF]GLASS: A Glass-Box, Loop-Verified Method for Analog Circuit Sizing with Symbolic PriorsWithdrawn2.00
[PDF]GeoPI-LNODE: Geometry Conditioned Physics Informed Latent Neural ODEs for Long-Horizon PredictionWithdrawn1.67
[PDF]Diversify and Agree: Reliable Surrogate Expansion for Transferable Adversarial Attacks on MLLMsWithdrawn2.00