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
7,676 results for “keyword:"ai"” in ICLR 2027. 1,833 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Safety and Reasoning Vulnerabilities in Self-Rewarding Test-Time Reinforcement Learning▼4.3k2.00
[PDF]QuMix: Query-Guided Mixed-Precision KV-Cache Quantization for Block Diffusion Language Models▲3.0k2.33
[PDF]HADBN: Learnable Hierarchical Aggregated Dynamic Brain Networks for Interpretable Brain Disorder Diagnosis▼1361.33
[PDF]ReconAgent: An Agentic Framework for Evidence-Coupled Sparse-View Indoor Surface Reconstruction
[PDF]From Registered Models to Authorized Actions: Zero-Knowledge LLM Agents with Model Binding and Private Tool-Call Authorization▲3.0k2.50
[PDF]Uncertainty-Aware Neural Algorithmic Reasoning: Learning to Execute Algorithms over Belief-Valued Graphs▼4.3k2.00
[PDF]What Must Be Learned to Adapt? Decision-Directed Identification Under Environment Shift▼4.3k2.00
[PDF]Not All Observations Are Equal: Guiding Derivative-Free Ensembles via Uncertainty Contraction▼4.3k2.00
[PDF]Beyond Decision Agreement: Evaluating Reinforcement Learning Policy Behavior and Outcomes in Power-System Balancing▼1.2k1.67
[PDF]Task-conditioned probing of instruction-tuned multimodal LLMs: Region-specific brain alignment patterns under naturalistic stimuli▲3.0k2.33
[PDF]Temporal Predictive Multiplicity: Equally Accurate Time Series Models Yield Different Forecast Trajectories▼1361.33
[PDF]Environment Diversity Drives Zero-Shot Generalisation of Predictive Spatial Representations▼4.3k2.00
[PDF]AUDIO-COMPASS: REFERENCE-FREE COMPONENT-WISE EVALUATOR FOR AUDIO–TEXT SEMANTIC ALIGNMENT▲3.0k2.33
[PDF]Rapid Mixing Is Not Enough: Hardness of Action-Conditioned Predictive Representation Optimization▼5.9k2.33
[PDF]STARPlan: Stable Topology-Aligned Representations for Autoregressive Vector Floorplan Generation▼4.3k2.17
[PDF]Brain alignment of reasoning and action representations from vision–language and action models during naturalistic gameplay▲3892.67
[PDF]Towards 1:4 semi-structured 75% sparsity via Cannistraci-Hebb N:M dynamic sparse-to-sparse training▼1361.33
Withdrawn or desk rejected (1,833)
[PDF]Everything in Moderation: Interior Per-Domain Coverage Optima and Gap-Preserving Fixed-Budget Alignment in Multi-Domain Mid-TrainingDesk rejected
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected