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
1,103 results for “keyword:"transform"” in ICLR 2027. 230 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals▲3952.67
[PDF]Normalization removal at scale: RMSNorm-to-affine transition in GPT-OSS-style MoE transformers▼1361.33
[PDF]Learning How to Localize Change Points: In-Context Adaptation across Change Mechanisms▲3.0k2.33
[PDF]Beyond Firing Less: Activity Objectives Shape Population Organization in a Spike-Driven Transformer▼4.3k2.00
[PDF]Colinearity Decay: Training Quantization-Friendly Transformers via Decoupled Weight-Space Regularization▼5.8k2.33
[PDF]LoCoFormer: Rethinking Local Geometric and Semantic Context Representation for Point Cloud Transformers▲3.0k2.33
[PDF]A Lasting Bias of Initialization: How Initialization Shapes Generalization in Vision Transformers▼5.8k2.33
[PDF]The Fates’ Spindle: Rotation Representation Emerges for Relative Position in Transformer▼12k1.67
[PDF]Fully Spectral Graph Scattering Networks With Transformer-Based Component-Adaptive Graph Filter Banks and Spectral Nonlinearity▼4.5k2.25
[PDF]CATD-MoE: Conflict-Aware Timestep-Dynamic K/V Mixture-of-Experts for Instruction-guided Image Editing▼1.2k1.67
[PDF]Mesh-Aware Tokenization for Structured Graph Transformers: Learning Physical Simulation on Higher-Order Meshes▼1611.50
[PDF]Right Direction, Wrong Step: Geometric Analysis of Finite-Step Failure in Looped Transformers▲3.0k2.33
[PDF]TokenDistill: Compressing CoT via Iterative Token Distillation with Continuous Prompt Transformation▼1.2k1.67
[PDF]Robustness from Interaction: Event-Structure-Aware Attention for Event-Based Spiking Transformers▼4.5k2.67
[PDF]Hard to Remove, Cheap to Replace: Compact, Transferable Surrogates for Sensitive LLM Layers▲6.1k2.00
[PDF]A Sparse Frequency-Aware Spiking Transformer with Hierarchical Wavelet Pruning and Adaptive Dual-Path Routing▼1361.33
Withdrawn or desk rejected (230)
[PDF]Caustic Spectroscopy: Identifiability and Acquisition Limits of Topological Event TimingWithdrawn2.00
[PDF]Decoupling Temporal Action Ownership and Actor Geometry for Spatio-Temporal Action LocalizationWithdrawn1.33
[PDF]Activation Density in Transformer Feed-Forward Networks Is Set by the Nonlinearity, Not the WidthWithdrawn2.00