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
7,677 results for “keyword:"ai"” in ICLR 2027. 1,832 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ShellElastic: Scalable Elastic Pretraining with Simultaneous Maximal Updates and Hyperparameter Transfer▼1.2k3.00
[PDF]ReCoNav: Reliable Constrained Long-Horizon Vision-and-Language Navigation via a Determination Engine▲6.1k2.00
[PDF]When Evaluation Changes the Conclusion: Measuring the Reliability of Small RL Gains in Reasoning LLMs▼4.3k2.00
[PDF]From Prediction to Compensation: Neural Operators for Event-Triggered Sliding-Mode PDE Control▼1.2k1.67
[PDF]Mapping and Matching Joint Learning for Unpaired Unsupervised Visible-Infrared Person Re-Identification▲2623.67
[PDF]Emergent Depth-Wise Specialization in a Unified Embodied Model: From Semantic Understanding through Visual Foresight to Action▲3922.67
[PDF]Understanding the Weight Averaging Mechanism in LLM Training for Post-Training Quantization▲5103.00
[PDF]Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes▼4.3k2.00
[PDF]Context Rot in Agent Trajectories: Evolving-State Maintenance Is the Hidden Bottleneck of Long-Context Agents▲3.9k1.67
[PDF]From Search to Research: Exploring Search Scaling in Autonomous Quantitative Factor Mining▼1.2k1.67
[PDF]A Theoretical Analysis of Sparse Mixture-of-Experts Routing via Compatibility Optimal Transport
Withdrawn or desk rejected (1,832)
[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