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7,677 results for “keyword:"ai"” in ICLR 2027. 1,832 withdrawn or desk rejected listed apart.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]Per-Layer Routing over Heterogeneous Experts for Shortest-Path Neural Algorithmic Reasoning▼4.3k2.00
[PDF]Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy▼5.8k2.33
[PDF]Depth is Degree: Test-Time-Training Updates Are Polynomial Filters, and Learned Step Sizes Only Choose the Coefficients▼1361.33
[PDF]Neopep: Reinforcement Learning From Machine-Learned Force Field Energy for Non-Canonical Peptide Structure Prediction▲3.0k2.33
[PDF]RiVaT-Fuse: Reliability-Calibrated Variational Tensor Fusion with Matrix-Valued Trust for Multimodal Prediction under Modality Uncertainty▼4.3k2.00
[PDF]Logic Density Pruning: Mitigating Overthinking via Step-Level Chain of Thought Compression▼1.2k1.67
[PDF]TS-Edit: A Model Editing Framework for Adversarial Defense in Time-Series Foundation Models▼1361.33
[PDF]Out of Step with Evidence: Task Progress State Mismatch in Long-Horizon Tool-Use Agents▼1.2k1.67
[PDF]Spectral Unit Tests for Predictive Representation Models: A Fault Atlas and Its Scope Conditions▲3922.67
[PDF]Context-Robust: Context-Informed Activation Calibration for Mixture-of-Experts Language Models▲14k3.00
[PDF]Placebo Audits Quantify Audit-Specific Acceptance under Adaptive Reuse of Verifier Tests▼5.8k2.33
[PDF]Knowing When Not to Answer: Self-Assessed Measurability and the Limits of Physics Transfer▼1361.33
[PDF]One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness▲3.0k2.33
[PDF]Finale: Reconstructing Local Supervision with Terminal-Anchored Replay for End-to-End Web Agents▲5.4k3.00
[PDF]Effects of Token-level Loss Reweighting on Long-Range Recall in Chunked Training of Mamba-2▼1.2k1.67
[PDF]Auditing the Auditor: Ground-Truth Controls for Natural-Language Explanations of LLM Activations▼4.3k2.00
Withdrawn or desk rejected (1,832)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