Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

What Linear Probes Miss: Multi-View Probing for Weight-Space Learning

About

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. However, existing probing methods are limited by a single-view design: they capture first-order structures but fail to encode the rich, higher-order correlation patterns inherent in row-column interactions. To bridge this gap, we introduce MVProbe, a multi-perspective probing framework that synthesizes first-order signals with interaction-aware (Gram-based) views. Our approach is theoretically grounded; we analyze the scaling laws of different probing orders to derive a principled standardization and fusion strategy that ensures balanced contributions from all branches. On the Model Jungle benchmark, MVProbe consistently outperforms the state-of-the-art ProbeX across diverse architectures, including discriminative backbones (ResNet, SupViT, MAE, DINO) and large-scale generative LoRA adapters (Stable Diffusion LoRA).

Eunwoo Heo, Kyeongkook Seo, Jaejun Yoo• 2026

Related benchmarks

TaskDatasetResultRank
Weight-Space ClassificationModel Jungle
Accuracy92.33
20
Model ClassificationSD200 zero-shot (holdout)
Accuracy95.53
7
kNN retrievalSD LoRA (SD200)
Accuracy99.8
6
kNN retrievalSD LoRA (SD1k)
Accuracy93.99
6
One-Class Classification (OCC)SD LoRA (SD200)
Accuracy100
6
Weight-Space ClassificationMNIST INR
Accuracy97.2
5
One-Class Classification (OCC)SD LoRA (SD1k)
Accuracy99.99
4
Weight-Space ClassificationStable Diffusion LoRA In-Distribution SD200 (train)
Accuracy99.8
2
Weight-Space ClassificationStable Diffusion LoRA In-Distribution SD1k (train)
Accuracy97.88
2
Weight-Space ClassificationStable Diffusion LoRA Zero-shot SD1k (held-out classes)
Accuracy97.96
2
Showing 10 of 10 rows

Other info

Follow for update