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
922 results for “area:"other topics in machine learning (i.e., none of the above)"” in ICLR 2027. 219 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]SPARK: Unifying Structure-Aware Path-Prefix-Conditioned Tree Search and Graph-Grounded Generation for Knowledge Graph Question Answering▼5.8k2.33
[PDF]OR-Diffusion: Structural Data Synthesis and Hierarchical Verification for Optimization Modeling▼4.3k2.00
[PDF]UniRel: Relation-Centric Knowledge Graph Question Answering with RL-Tuned LLM Reasoning▲3942.67
[PDF]LIFT: A Lifecycle-aware Interaction Factorization Transformer for Unified Retrieval and Ranking▲3942.67
[PDF]MM-DAGNN: Modality-Disentangled Adaptive Graph Neural Networks for Multimodal E-commerce Recommendation▲11.00
[PDF]Ranking and Partitioning of Attention Heads for Sparse and Continual Reinforcement Learning Fine-tuning▲6.1k2.00
[PDF]Complementary Evidence Reasoning over Structured and Unstructured Electronic Health Records▼5.8k2.33
[PDF]PROBABILISTIC EVALUATION OF LARGE LANGUAGE MODELS WITH AMORTIZED BAYESIAN RELIABILITY ESTIMATION▲11.00
[PDF]COARSE-GRAINING RECURSIVE COMPUTATION: CONTINUATION-RELATIVE INTERFACES AND FAILURE MODES▼1361.33
[PDF]Similar Choices, Different Attention: Cross-Modal Associations in Humans and Vision-Language Models▼4.5k2.67
[PDF]Beyond Global Clusters: Objective-Specific User Clustering for Multi-Objective Bandits▼5.8k2.33
[PDF]CNLVerifier: A Controlled-Natural-Language Verifier for LLM-Driven Mathematical Reasoning▼4.3k2.00
[PDF]When Does Orthogonal Training Help Model Merging? Operator-Relative Disentanglement in Task Arithmetic▼1361.33
[PDF]You Don't Need the Whole Meta-Dataset: Budgeted Model Evaluation on Unseen and Unlabeled Data▼4.3k2.00
[PDF]From External Information to Forecast Adjustment: LLM-Based Constraint Modeling and Reflection Acceleration▼1361.33
[PDF]Which Model Should Be Chosen? Joint Performance Estimation and Ranking of Black-Box Models on Unlabeled Data▼4.5k2.67
Withdrawn or desk rejected (219)
[PDF]"The Whole Is Greater Than the Sum of Its Parts”: A Multi-Teacher CoT Distillation FrameworkDesk rejected
[PDF]Local Look-Ahead Ensembling: Do We Really Need a Second Network for Learning with Noisy Labels?Desk rejected
[PDF]Activation Density in Transformer Feed-Forward Networks Is Set by the Nonlinearity, Not the WidthWithdrawn2.00