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
33,657 results for “keyword:"a"” in ICLR 2027. 8,406 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Heterogeneous Socialized Learning: Enabling Individual Growth Across Diverse Model Architectures▼1.2k1.67
[PDF]TRUER: Test-Time Reward Correction Using an Error-Aware Rectifier for Reinforcement Learning▲6.0k2.00
[PDF]How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits▲4743.00
[PDF]Multimodal Fusion on the Boolean Lattice: From Local Context Dependence to Global Higher-Order Interactions▼1.2k3.00
[PDF]Invariant Last-Iterate Convergence for Optimistic Counterfactual Regret Minimization in Solving Perturbed Extensive Form Games▼4.3k2.00
[PDF]When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders▼1.2k3.00
[PDF]Misled by the Few: A Mechanistic Analysis of Demonstration Conflicts in In-Context Rule Inference▼4.3k2.00
[PDF]Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach▼4.3k2.00
[PDF]ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement▲9.3k2.67
[PDF]Benign Safety Is Not a Robustness Certificate: Evidence of a Structural Evaluation Gap Across Attack Conditions▲31.00
[PDF]Non-Equilibrium Diffusion Pseudo-labelling and Relative Preference Optimisation for Unsupervised Camouflaged Object Detection▼4.5k2.67
[PDF]DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models▼5.9k2.33
[PDF]Dream2Discern: Learning from Hard Latent Variants for Runtime Failure Prediction in Multi-Agent Systems▲3332.67
[PDF]Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts▼5.9k2.33
Withdrawn or desk rejected (8,406)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33
[PDF]Same-Checkpoint Intervention on Pre- and Post-Context States in Entity-Local Temporal EncodersWithdrawn1.33
[PDF]Pulse2View: Same-Sensor Cross-View Pre-Training for Patient-Level Multi-Disease Classification from Wearable PPGWithdrawn1.67