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
154 results for “keyword:"aggregation"” in ICLR 2027. 45 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]MechLeash-FL: Mechanistic Leashing of Latent Features for Federated Learning under Feature Skew▲432.80
[PDF]COFARL: COPULA-CONDITIONED FEATURE AGGRE- GATION FOR SEQUENTIAL RECOMMENDATION WITH DEEP REINFORCEMENT LEARNING▼1.2k1.67
[PDF]TRACE: Lightweight Infrared Small Moving Target Detection under Heavy Noise with Temporal Templates and Neighborhood Evidence▼4.3k2.00
[PDF]RecastPrune: Rethinking Token Selection and Information Retention in Visual Token Pruning▼1.2k1.67
[PDF]Depth-Aware Visual Manipulation Relationship Reasoning with Gated Decoder-Layer Aggregation▼4.3k2.00
[PDF]VerdictGS: Views as Noisy Annotators for Query-Time Open-Vocabulary Gaussian Splatting Segmentation▲5103.00
[PDF]Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction▲5103.00
[PDF]Equal Exposure, Different Decisions: Reference Selection and Early Stopping for Pairwise LLM Judges▲14k2.50
[PDF]SoccerCanon: A challenging Benchmark and the Case for Stitching Vision Experts over VLMs▲3.0k2.33
[PDF]Dimension-wise Distributionally Robust Optimization for Multimodal Learning via Adaptive Aggregation▲4002.67
[PDF]Mitigating Hidden Undesirable Behaviors from LLM Fine-Tuning via Consensus Distillation▲11k2.00
[PDF]PRISM: Progressive Resolution with Independent Section Mapping for Scalable User Profiling▲11.00
[PDF]What Do Hypergraph Benchmarks Measure? Feature Paths, Evaluation Protocols, and Modular Constraints▼1351.33
[PDF]Understanding Feature Learning in Graph Contrastive Learning: Neighborhood Correlation and Theory-Guided Augmentation▲9.2k2.67
Withdrawn or desk rejected (45)
[PDF]Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer ScienceWithdrawn1.67
[PDF]FedSHIELD: Adversarial Honeypot-Guided Behavioral Client Screening for Robust Federated LearningDesk rejected1.33