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
815 results for “keyword:"transformers"” in ICLR 2027. 171 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Beyond the Training Horizon: Mechanisms and Limits of Length Generalization in Looped Transformers▲13k2.33
[PDF]SCA-DETR: Structured Cross-Scale Attention for Detection Transformers with Hierarchical Backbones▼4.3k2.00
[PDF]Residual-Aware Neural Spectral Capacity: Allocating Capacity across the Network from Architecture Specification Alone▲2843.00
[PDF]Frequency-Aware Attention: Tokenizer-Induced Self-Information as an Architectural Inductive Bias▼4.3k2.00
[PDF]Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression▲1.7k3.33
[PDF]SimPlex-GT: Node-to-Cluster Attention for Graph Learning under Mixed Homophily and Heterophily▼1361.33
[PDF]Algorithmic Capture, Computational Complexity, and Inductive Bias of Infinite Transformers▼4.3k2.00
[PDF]Quantitative Generalization Bounds for Multi-Layer Transformers: A Few Long Strings can Beat Many Short Ones▲143.33
[PDF]Hidden Reasoning Must Leak, but Need Not Be Readable: Fundamental Opportunities and Limits for Chain-of-Thought Monitoring▼1.2k3.00
Withdrawn or desk rejected (171)
[PDF]Decoupling Temporal Action Ownership and Actor Geometry for Spatio-Temporal Action LocalizationWithdrawn1.33
[PDF]Same Head, Different Calls? Auditing Functional Role Claims in Looped TransformersWithdrawn1.33