AI RESEARCH
What Linear Probes Miss: Multi-View Probing for Weight-Space Learning
arXiv CS.LG
•
ArXi:2605.23410v1 Announce Type: new The explosive growth of open-source model repositories has created a Model Jungle, where checkpoints are frequently shared without adequate documentation or metadata. While weight-space learning offers a pathway to identify and analyze these models directly from their parameters, processing full-scale weights is computationally prohibitive. Probing-based methods have emerged as a lightweight alternative, extracting permutation-equivariant representations via learnable probe vectors.