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
27 results for “keyword:"dag"” in ICLR 2027. 4 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Offline Imitation Error as a Model-Selection Proxy Under Distribution Shift: Evidence from Real-Camera Active PTZ Control▼5.8k2.33
[PDF]Evaluating the Ability of Large Language Models to Generate Structured Curricula for Human Learners▼5.8k2.33
[PDF]ConcepTensor:A Probabilistic Relational Representation Architecture for DAGs Embedded in High-Dimensional Tensors▲11.00
[PDF]Provable Guarantees for Learning Pure Latent High-dimensional Structural Equation Models▼4.3k2.00
[PDF]Revisiting AdaGrad in Stochastic Convex Optimization: Last Iterates, High Probability, and Lower Bounds▼5.8k2.33
[PDF]Beyond Problem-Solving: A Multi-Agent Framework and Pedagogically-Aligned Benchmark for Evaluating LLMs’ Educational Question Generation▼1361.33
[PDF]Support Selection Beyond Smooth DAG Exactness: Completion Geometry, Score Margins, and Selective Certificates▼5.8k2.33
[PDF]ScaffoldBench: A Dynamic Benchmark for Evaluating Pedagogical Scaffolding and ZPD Alignment in Large Language Models▼4.3k2.00
[PDF]Learning Time-Varying Directed Graphs via Convex TV-Regularized Optimization and DAG Projection▼1.2k1.67
Withdrawn or desk rejected (4)
[PDF]OmniEduBench: A Chinese Dataset for Evaluating Subject Knowledge and Pedagogical JudgmentWithdrawn1.67