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
606 results for “keyword:"linear"” in ICLR 2027. 100 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Age Subspaces in 3D Face Representations: Readability, Predictive Dependence, and Transferability▼1361.33
[PDF]Who Grades the Edit? Frozen and Re-fit Readouts for Position Interventions in RoPE Models▼1361.33
[PDF]Harnessing Smoothness: Asymmetric Differential Linear Attention for Vision Transformers▲3952.67
[PDF]Single-Configuration Evaluation Can Mislead Learned MILP Cut Selection: Seed Fragility, Measurement-Era Artifacts, and the Limits of Score Blending▼1361.33
[PDF]Linear Separability Is Not Input Controllability: Intermediate-Layer Jailbreak on VLMs▲6.1k2.00
[PDF]Where Does the Recurrence Help? Retrieval-Distance Attribution in Hybrid Sequence Models▼1.2k1.67
[PDF]SFA: A Statistical Physics-Inspired Diffusion Transformer for Efficient and High-Quality Image Generation▲3.0k2.33
[PDF]Preference-Guided Tree Search for Feasible Solution Generation in Integer Linear Programming▲2843.00
[PDF]Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design▲3.0k2.33
Withdrawn or desk rejected (100)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]Exact Recovery Thresholds for Weighted Data Selection in Vector-Valued Linear RegressionDesk rejected
[PDF]Learning Iteration Schedules, Not Inverses: Zero-Shot Amortized Neural Preconditioning for Large-Scale Linear SystemsDesk rejected
[PDF]Concept Subspaces Compute Beyond the Logit Lens: A Weights-Only Test for Locating Representations Upstream of ReadoutWithdrawn