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1,103 results for “keyword:"transform"” in ICLR 2027. 230 withdrawn or desk rejected listed apart.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]Reconstruction, Not Localization: A Mechanistic Account of Sparse-Feature OOD Detection in Vision Transformers▼1361.33
[PDF]Representation Geometry in Diffusion Transformers: What Matters for Generation Quality?▼1.3k1.75
[PDF]Not Order but Support: Curriculum Effects on Grokking Are a Transient-Support Phenomenon▲14k3.00
[PDF]OUTPUT WITHOUT WARRANT: SPECTRAL DIMENSION READOUTS CANNOT CERTIFY THEIR OWN HYPOTHESES▲6.1k2.00
[PDF]FROM ATTENTION SENSITIVITY TO LAYER ROLE: REVISITING MIXED-PRECISION QUANTIZATION OF TRANSFORMERS▼1.2k1.67
[PDF]TEMPO: Temporal Error-Modulated Precision Overlays for Recursive Transformer Quantization▲3.0k2.33
[PDF]Effective Does Not Mean Useful: Conditional Functional Substitutability for Redundancy and Scaling in Transformers▼5.8k2.33
[PDF]Beyond Berry–Esseen: Loss-Aware Distortion Transfer for Randomized Hadamard Quantization▼1.2k1.67
[PDF]What Survives Token Merging? Merge-Invariant Low-Rank Attention for Vision Transformers▼4.3k2.00
[PDF]When Are Linear Transformers Nearly Ridge-Optimal? Task-Varying Noise and Covariance Adaptation for In-Context Regression▼5.8k2.33
[PDF]RESAD: Round-Efficient Secure Autoregressive Decoding Scheme for Transformer Inference▼4.3k2.00
[PDF]CausalExoFormer: End-to-End Lag-Aware Causal Structure Learning for Exogenous Time-Series Forecasting▼1.2k1.67
[PDF]A DEPTH–WIDTH SEPARATION FOR QUADRATIC IN-CONTEXT LEARNING WITHPROTECTED-LABEL BILINEAR TRANSFORMERS▲3952.67
Withdrawn or desk rejected (230)
[PDF]Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding PredictionDesk rejected
[PDF]SMIC: Shared Multiscale Input-Reference Conditioning for Natural Language InferenceWithdrawn1.67
[PDF]Approximating Longer Birth and Death Processes with Large Language Models and the Self Improvement FrameworkWithdrawn1.00
[PDF]AxisQ: Depth-Adaptive Channel–Frequency Quantization for Camouflaged Object DetectionWithdrawn2.00
[PDF]Representation by Design in Generation: Cross-View Class-Token Alignment in Diffusion TransformersWithdrawn2.33
[PDF]Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature SpacesWithdrawn1.33