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
578 results for “keyword:"composition"” in ICLR 2027. 171 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]HiERA: Hierarchical Domain-aware Reusable Adaptation for Continual Personalization of EEG Foundation Models▼1.2k1.67
[PDF]DecoVAE: Decomposing Predictable Dynamics and Uncertainty for Efficient Probabilistic Time Series Forecasting▼5.8k2.33
[PDF]The Parallel-Decoding Score of Masked Diffusion Language Models Is Not a Mutual Information▲13k2.33
[PDF]Where Massive Activations Come From: Causal Evidence from MLP Geometry in Large Language Models▲3952.67
[PDF]SURE-Tagger: Structured Speech Representations for Compositional Evaluation and Targeted Data Selection▲5.4k3.00
[PDF]PSDN: Physics-Guided Self-Supervised Dual-Stream Network for Ultrasound Image Denoising▲3.0k2.33
[PDF]Aligning without Homogenizing: Jointly Explainable Common-Specific Decomposition for Multi-Modal Object Re-Identification▼4.3k2.00
[PDF]Feature Extraction Advantage of Graph Transformers: Primal-Dual Decomposition and Reconstruction-Risk Analysis▲14k3.20
[PDF]Wave Physics as Representation: Tensor-Structured Neural Reconstruction for Ocean Acoustic Fields▲13k2.33
[PDF]DualKT: Dual-Timescale Knowledge Tracing via Orthogonal Decomposition and Target-Conditioned Fusion▼4.3k2.00
[PDF]HarnessWeaver: Continual Self-Improvement through Task-Conditioned Harness Composition and Model Routing▼4.3k2.00
[PDF]ReDU-IR: Reconstructible Feature Decomposition and State Complementary Updating for All-in-One Blind Image Restoration▲5103.00
[PDF]Improving Entity-Configuration Generalization in Real-Time Strategy Games with Task Hypergraph Representation▲3.0k2.33
[PDF]AdjuvantChart: Benchmarking Multi-Panel Relational Understanding in Real-World Scientific Charts▼4.3k2.00
[PDF]From Prompts to Question Graphs: Structure-Aware Evaluation and Selection of Text-to-Image Models▼4.3k2.00
[PDF]Weights Read and Write Features: Scalable Parameter Decomposition Grounded in Activation Space▲3952.67
[PDF]When Prompt Experts Disagree: Diagnosing Open-World Decisions in Federated Vision–Language Models▼1611.50
Withdrawn or desk rejected (171)
[PDF]TFAG-OVD: Training-Free Attribute-Guided Open-Vocabulary Detection via LLM Semantic CompositionWithdrawn1.67
[PDF]TYPED AMPLITUDE COMPOSITION FOR REUSABLE INFERENCE: SEMANTICS, ERROR BOUNDS, AND EXACT CORRECTIONWithdrawn
[PDF]Graphs are Evidence, Not CircuitsDesk rejected