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
1,304 results for “keyword:"prediction"” in ICLR 2027. 359 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Post-Selection-Valid Conformal Guarantees over Continuous Preferences for Multi-Objective Reinforcement Learning▼1.2k3.00
[PDF]EnzyFuse: Cross-View Interaction over Spatial Neighborhoods for Catalytic Residue Prediction▲2743.00
[PDF]Beyond Static Annotation Matching: A Temporal Benchmark for Free-Form Protein Function Prediction▼4.3k2.00
[PDF]Molecular Uncertainty Gradients: Exact Decomposition of Predictive Variance Onto Molecular Substructures▼12k1.67
[PDF]When Does Coarse-to-Fine Forecasting Help? An Exact Error Decomposition and a Checkable Criterion▼1.2k1.67
[PDF]Geometry-Aware Error Diagnosis for Data Acquisition and Training Strategy Selection in Graph Neural Network▼1.2k1.67
[PDF]OmniCens: Self-Improving Distillation for Multimodal Classification of Millions of Profiles▲11.00
[PDF]The Rate Measure: How Far Linearisation Governs Training, and Why That Horizon Cannot Be Read▲11.00
[PDF]Conformal Non-Coverage Risk Control (CNCRC): Pairwise Cost-Weighted Nonconformity Scores for Risk-Aware Prediction Sets▼1361.33
[PDF]Predict What Joint Actions Can Control: Goal-Progress Prediction for Post-Training Residual Selection▼5.8k2.33
[PDF]Retro-Forge: A Multi-Step Pairwise Retrosynthesis Framework for Solid-State Materials Synthesis▲3.0k2.33
[PDF]A Model-Agnostic Physics-Guided Adapter for Few-Shot Transfer of Coastal Flood Prediction Models to Unseen Regions▼1.2k1.67
[PDF]A Stereochemistry-Aware Vector–Scalar Framework for Enzyme–Substrate Specificity Prediction▼4.5k2.67
[PDF]PerturbBridge: Reference-Process Design for Heterogeneity-Aware Single-Cell Perturbation Prediction▼5.9k2.50
[PDF]Does My LLM Obey Me? Falsification-Based Attribution Tests for Prompt-Based Behavioral Conditioning▼1361.33
[PDF]Where to Go and How to Move: Goal–Motion Latent Flow for Multimodal Trajectory Prediction▼4.3k2.00
[PDF]Reweight, Do Not Re-calibrate: Reusing the Same Encoder-Predictor Pair (World Model) When the Policy or Query Changes▼1361.33
[PDF]Calibrated Pessimism in Offline Reinforcement Learning: Auditing Support-Conditioned Reliability and Control Transfer▲11.00
[PDF]Better Reconstruction, Worse Transfer: Probing Representation Geometry in Cross-Reynolds Generalisation▼1361.33
Withdrawn or desk rejected (359)
[PDF]What Should I Try Next? Decision-Relevant Counterfactual Information Gain for Active World ModelsWithdrawn1.00
[PDF]Defect Responses in Visual World Models: Long-Horizon Propagation, Gradient Interaction, and Planning OutcomesWithdrawn1.33
[PDF]Beyond Tokens: Read and Predict N-gram Spans with a Shared Dictionary for Genomic Foundation ModelsWithdrawn
[PDF]The Normalization Landscape in Continual Learning: Resolving Moving-Average Breakdown and Subspace Interference for Buffer-Free Edge IntelligenceWithdrawn
[PDF]Probing Interaction Awareness in Trajectory Prediction with Counterfactual PerturbationsDesk rejected
[PDF]Auto-JEPA: A Latent World Model of Continuous Intent for End-to-End Autonomous DrivingWithdrawn1.67