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7,679 results for “keyword:"ai"” in ICLR 2027. 1,830 withdrawn or desk rejected listed apart.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]You Only Need 2/3 of the Chosen Experts: An Empirical Study of Dynamic Expert Pruning in Fine-Grained MoE LLMs▼4.3k2.00
[PDF]CookBench: Can Digital Agents Actually Cook? A Multimodal Benchmark for Long-Horizon Embodied Planning▼5.9k2.50
[PDF]ResiSparse: Residual-Informed Exact-or-Approximate Sparse Attention for Efficient Video Generation▼12k1.67
[PDF]When Should the Teacher Move? Temporal Coupling and Stability in Self On-Policy Distillation▼4.3k2.00
[PDF]Vision Pretraining for Time-Series Forecasting Depends on More Than Undirected Grid Topology▼1361.33
[PDF]Beyond Retrieval and Fine-tuning: Learning from Scientific Execution Experience for Self-Improving Agents▼4.5k2.25
[PDF]When Better Prediction Makes Worse Generation: Teacher-Domain Alignment in Knowledge Distillation▼4.5k2.67
[PDF]X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning▼5.8k2.33
[PDF]RecAgent: Reinforcing Referring Expression Comprehension through Agentic Tool-Augmentation▼5.8k2.33
[PDF]Agents Recognize Source Inconsistency but Rarely Act on It: Decision-Time Mediation for Grounded Resolution▲14k3.00
[PDF]SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown▼5.8k2.33
Withdrawn or desk rejected (1,830)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