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
45 results for “keyword:"extrapolation"” in ICLR 2027. 15 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Distance Does Not Predict Competence: A Two-Axis Decomposition of Out-of-Distribution Failure▼4.3k2.00
[PDF]MetaGround: Physics-Grounded Conditional Diffusion for Nonlinear Metamaterial Inverse Design▼1351.33
[PDF]Reading the Tea Leaves, Again: Can Large Language Models Predict Language Model Training Runs?▼4.5k2.25
[PDF]FLOATBench: A Tabular Dataset and Benchmark for Fatigue Prediction on Floating Offshore Wind Turbine Towers▼4.5k2.25
[PDF]FUSED BUT NOT RELATIVE: LOW-RANK ATTENTION BIASES SILENTLY DROP TRANSLATION INVARIANCE▼4.3k2.00
[PDF]Back to the Weights: Training-Free Model Enhancement via Training Trajectory Extrapolation▼1.2k1.67
[PDF]PASL-U: PHYSICS-AWARE SOURCE RECOVERY WITH TEMPERATURE-PARAMETERIZED OPERATORS FOR GUIDED-WAVE DAMAGE LOCALIZATION▼1.3k1.75
[PDF]Chemical-Support-Resolved Evaluation of Model-Selection Stability under Molecular Extrapolation▲3.0k2.33
[PDF]Amortized Physics-Informed Learning via Generative Initialization of Radial Basis Functions▲5.4k3.00
[PDF]Computation Persists, Routing Degrades: A Mechanistic Analysis of Transformer Length Extrapolation▼4.3k2.00
[PDF]ATMA: Long-Context Language Modeling via Polar Attention and Gated-Delta Compression Memory▼1351.33
[PDF]Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design▲3.0k2.33
[PDF]Support-Compiled Feature Folding: More Evidence at Lower Memory Across Tabular Foundation Models▼4.3k2.00
[PDF]DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models▲5103.00
Withdrawn or desk rejected (15)
[PDF]GRE-GS: Geometry Repair and Gaussian Extrapolation for Sparse-View 3D Gaussian SplattingWithdrawn1.67
[PDF]Not All Recurrence Is Created Equal: Depth Sensitivity Differs Between Recurrence Dimensions of a Single CheckpointWithdrawn1.33
[PDF]Predicting What Happens Next: Next-Event Training and Evaluation for Temporal Knowledge Graph ExtrapolationWithdrawn1.67
[PDF]FieldNet: A Source-Free Normalizer for Any Transition, and Closed-Form Under Time HomogeneityWithdrawn1.33
[PDF]Beyond Positional Adaptation: Calibrating Attention for Image Resolution ExtrapolationWithdrawn1.67
[PDF]TailCast: Release-Order Tail Extrapolation for Frozen Time-Series Foundation ModelsWithdrawn1.33