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
38 results for “keyword:"weight space"” in ICLR 2027. 8 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Correspondence over Content: What Makes Task Information Readable in Neural Network Weights▼1351.33
[PDF]Bidirectional Transfer, Asymmetric Expression: Math Fine-Tuning Conceals the Code Gains It Carries▲13k2.33
[PDF]A NIGHT AT THE LLM ZOO: DATA CONDITIONED FLOW MATCHING FOR GENERATING PRETRAINED LLM WEIGHTS▼1.2k1.67
[PDF]Parameter Symmetries Are Not Task Symmetries: Which Invariances Can Weight-Space Learning Afford?▼11k2.33
[PDF]Interfaces and Modules: A Scalable Representation for Weight-Space Learning across Architectures▼1.2k1.67
[PDF]Back to the Weights: Training-Free Model Enhancement via Training Trajectory Extrapolation▼1.2k1.67
[PDF]Socialized Continual Learning: Recursive Weight Space Editing for Scalable Multi-Expert Collaboration▼1351.33
[PDF]Structural Preservation of Data in Implicit Neural Representations via the Implicit Function Theorem▲13k2.33
[PDF]Morpheus: Modality-Agnostic Adversarial Attack from Leaked Models in Federated Learning▲5.4k3.00
Withdrawn or desk rejected (8)
[PDF]Shared Parametric Geometry and Data Provenance in Model Organisms for Emergent MisalignmentWithdrawn2.00
[PDF]Detectability Inversely Tracks Disruption: Reference-Free, Static-Weight Detection of Backdoored LoRA AdaptersWithdrawn1.33