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
227 results for “keyword:"scientific machine learning"” in ICLR 2027. 41 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]A Robust In-Context Model for Conservation Laws: Injecting Context into Flux Neural Operators via Recurrent Vision Transformers▼4.3k2.00
[PDF]EvoTrace: Learning to Evolve Scientific Hypotheses from Trajectories of Agentic Symbolic Regression▲3.0k2.33
[PDF]PARA: Patch-based Adaptive multi-Resolution, time-Advancing and scale-equivariant neural PDE solver▲5103.00
[PDF]Differentiate the Evaluator: Co-Searching Programs and Parameters with Exact Gradients▼4.3k2.00
[PDF]Where Should Observations Enter? Dual-Path Integration for Continuing Sensing with Recurrent Gaussian States▼5.9k2.50
[PDF]HotPOT: Operator Transformer with Heterogeneous Physics Experts for Large-Scale PDE Pre-training▲6.1k2.00
[PDF]Physics-Aligned Finite Maps: Recasting Physics-Constrained Generation as Next-State Prediction▲9.2k2.67
[PDF]Principal-Part Decomposition for Neural Operator Learning of Dirichlet-to-Neumann Maps▲3.0k2.33
Withdrawn or desk rejected (41)
[PDF]Exploration-NFT: Reinforcing Protein Dynamics Generators for Persistent Conformational ExplorationWithdrawn2.00
[PDF]Learning Iteration Schedules, Not Inverses: Zero-Shot Amortized Neural Preconditioning for Large-Scale Linear SystemsDesk rejected
[PDF]Symbol-conditioned Adaptive Fourier Operator Transformer for Large-Scale PDE Pre-TrainingWithdrawn1.67
[PDF]Residual Geometry Shapes Downstream Correction Work for Learned Warm Starts in Nonsmooth PDE SolversWithdrawn1.67
[PDF]Conditioning Without Guidance: When the Observation Is Already a Diffusion MarginalWithdrawn1.75