Research map / Learning theory and algorithms / Matrix and tensor methods
Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Closest papers by meaning
- Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic (ICLR 2025 · similarity 0.85)
- No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces (ICML 2025 · similarity 0.85)
- Task Singular Vectors: Reducing Task Interference in Model Merging (CVPR 2025 · similarity 0.84)
- DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations (CVPR 2025 · similarity 0.84)
- Variational Task Vector Composition (NeurIPS 2025 · similarity 0.84)
- Platonic Task Arithmetic (NeurIPS 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.