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
589 results for “keyword:"discovery"” in ICLR 2027. 123 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]NeSyF: Neural-Symbolic Feedback for Joint Network Dynamics Prediction and Governing Equation Discovery▼1.2k1.67
[PDF]Anchored Residual Integration with Structure-regularized Adaptation for Generalized Category Discovery▲5.4k3.00
[PDF]MGDEval: A Curated Multi-Endpoint Benchmark for Generalization in Molecular Glue Degrader Activity Prediction▲3.0k2.33
[PDF]FieldForge: A Pretraining and Post-Training Framework for Flow-Based Crystal Generation▼4.3k2.00
[PDF]EnergyRetro: Bridging Bond Energetics and Reaction Knowledge for Multi-Step Retrosynthesis▼1.2k1.67
[PDF]Differentiable Latent-Tree Causal Discovery via Triplet Branch-Point Objectives and Three-Terminal Root Identification▲5103.00
[PDF]PLI-CLIP: Learning Transferable Protein–Ligand Interaction Representations from Natural Language Supervision▼11k2.33
[PDF]One Observation, One Identity: Joint Association and Truth Discovery for Remote-Sensing Agents▲3952.67
[PDF]Disentangling Invariant Structures from Parameter Variations for Parameterized Equation Discovery▼4.5k2.67
[PDF]What-Where Transformer: Concurrent Representation and Localization in a Slot-Centric Visual Backbone▲3.9k1.67
[PDF]CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists▲1.7k3.33
[PDF]Faithful Rules Are Not Enough: Boolean Surrogates for Deep RL and an Audit of Their Concepts▼4.5k2.67
[PDF]Learning to Outgrow a Theory: Experimental Discovery Beyond the Initial Hypothesis Space▲143.33
[PDF]The complexity of understanding: Formalizing Concept Discovery in Mechanistic Interpretability▼1.2k1.67
[PDF]Reject-to-Protect: Dynamic Decision-Aware Adversarial Training for Selective Molecular Prediction▼1.2k3.00
[PDF]CreativeBench2.0: Benchmarking Creative Method Discovery and Foresight Toward Recursive Self-Improvement▼4.5k2.67
[PDF]MELD: Recursive Self-Improvement via Hierarchical Coordination for Multi-Agent Scientific Discovery▲9.2k2.67
[PDF]F2: Offline Reinforcement Learning for Hamiltonian Simulation via Free-Fermionic Subroutine Compilation▼1.2k1.67
Withdrawn or desk rejected (123)
[PDF]ViGa-SR: LLM-based Evolutionary Search for Symbolic Regression with Visual Priors Guidance from Multimodal Representation of DataWithdrawn1.33