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578 results for “keyword:"composition"” in ICLR 2027. 171 withdrawn or desk rejected listed apart.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]Learning Structured Sparsity for Large Models: Bridging Model Compressibility and Efficient Inference▼4.5k2.67
[PDF]The Circle Was Hiding a Helix: Helical Reduced Representations for Exact Vector Symbolic Binding▼71.25
[PDF]Sequential Functional Structured Tucker Compression for Large Language Model Attentions▼5.8k2.33
[PDF]When Is Component Sensitivity Compositional? A Causal Study of Neural Resource Allocation▼4.3k2.00
[PDF]Compositional Context Encoding for Out-of-Distribution Generalization in Modular World Models▼1361.33
[PDF]Samples, Sources, Space: Decomposing Data Scale in Spatially Structured Representation Learning of Human Brain Microarchitecture▼13k2.00
[PDF]PhySGA: A Physics-Space Grounded Agentic Framework for Generalizable and Interactive 3D Composition▲5103.00
[PDF]Stable States as Block-Uniform Flips of the Symbolic Centroid in Binary Hopfield Neural Networks▼4.3k2.00
[PDF]Pressure–Vorticity–Reaction Graph Networks: Structured Topological Memory and Safe Learned Dynamics▲11.00
[PDF]Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning▼4.5k2.67
[PDF]What Can a Leaderboard Certify? Compositional Controllability for Fair Evaluation and Training of Biomedical Literature-Review Agents▼1.3k1.80
[PDF]VQ-PACT: Learning Compositional Temporal Grammars for Text-Controlled Time Series Generation▲3.0k2.33
[PDF]After the Second Bell: Can Audio-Language Models Reason with Temporally Grounded Events?▼1.3k1.80
[PDF]DivOPD: Spread Wide, Look Close for Asynchronous On-Policy Distillation of Multi-turn Agents▲43.67
Withdrawn or desk rejected (171)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