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606 results for “keyword:"linear"” in ICLR 2027. 100 withdrawn or desk rejected listed apart.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]On Parameters of Nonlinear Scalar Dynamics from Video: Invariants, Calibration, and Identifiability▼5.8k2.33
[PDF]Understanding Gap-Dependent Regret for Optimism-Based Reinforcement Learning with Linear Function Approximation▲3.0k2.50
[PDF]Effective Regularity: When Point Estimates Generalize Like the Bayesian Posterior in Singular Models▲3.0k2.33
[PDF]Bridging KV-Cache Quantization and Linear Attention: From Theory to Pretrained Weight Migration▲3952.67
[PDF]A Proximal Stochastic Gradient Method for Doubly-regularized Spectral Risk Minimization▲9.2k2.67
[PDF]Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus▲3952.67
[PDF]Graph-Discovering for Networked Restless Multi-Armed Bandits with Nonlinear Delayed Propagation▲593.50
[PDF]Safe in Text, Unsafe in Action: Distinguishing Content and Physical Danger in LLM Hidden States▼4.5k2.67
[PDF]Hidden in the Multiplicative Interaction: Uncovering Fragility in Multimodal Contrastive Learning▲3952.67
[PDF]Directional Linear Separability of Neural Representations: Geometry and Transformations▼1361.33
[PDF]Recurrent Refinement Moves Candidate-Quality Readability Earlier and Stabilizes Its Coordinates▼1.2k1.67
[PDF]Conservative Local-Global Transport: Mesh-Local Convolution and Scalable Linear Attention for Neural Lagrangian Simulation▲9.2k2.67
Withdrawn or desk rejected (100)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