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
7,679 results for “keyword:"ai"” in ICLR 2027. 1,830 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams▲2623.67
[PDF]HARPS: Mitigating Multimodal Hallucinations via Head-Selective and Adaptive Perceptual Sink Reweighting▼3.7k2.25
[PDF]Reference-Image-Guided Relation Editing via Token Bottlenecking and Semantic Shift Alignment▲3952.67
[PDF]One Model, Many Minds: Strategy-Diversified Reasoning Is a Cross-Model Ensemble in Disguise▲11k2.00
[PDF]The Statistical Origins of Model Collapse: Resampling, Retention, and Exact Variance Recursions▲3.0k2.33
[PDF]One Fuzzer, Many Reasoners: Adaptive Neuro-Symbolic Fuzzing with Reliability-Calibrated and Context-Gated Guidance▼1361.33
[PDF]Decoding Beyond Hemodynamic Delay: Delay-Coupled Graph Dynamics for fMRI-to-Image Reconstruction▼4.3k2.00
[PDF]TEMPORALLY CONSISTENT ROUTING: A TRAINING- TIME OBJECTIVE FOR CACHE-EFFICIENT MIXTURE-OF- EXPERTS▲6.1k2.00
[PDF]Normalize-Then-Precondition: A Hierarchical Approach to Marginal Scale and Interaction Geometry for LLM Training▲13k2.33
[PDF]Normative Rewriting on the Reading Axis: How to Evade Chinese AI-Text Detectors While Preserving Quality▼1361.33
[PDF]How Much Reward Does Self-Evolution Need? Pairwise Validation Without Task-Reward Feedback▼4.3k2.00
[PDF]From Grammar Deltas to Token Masks: Incremental Constrained Decoding under Runtime Grammar Evolution▲14k3.00
[PDF]DFPO:Enhancing Robustness and Generalization for Robust RL through Distributional Value Flow Modeling in LLM Post-Training▼4.3k2.00
[PDF]Offline Scores Overestimate Online Oversight: Timely Interception of LLM Agents with Causal-Cone Monitoring▼4.3k2.00
[PDF]DELTA: Detecting and Localizing Generated Video Content through Generative Latent Differences▲3.0k2.33
[PDF]When Is Reuse Superiority Licensed? Evidence Separation for Heterogeneous Offline Experience Reuse▼1.2k1.67
[PDF]Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models▲3.0k2.50
[PDF]Continuous-Time Latent Belief-State Dynamics with Query-Conditioned Uncertainty for Knowledge Tracing▼1.2k1.67
Withdrawn or desk rejected (1,830)
[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