Pre-PEFT Probing: Weight Statistics and Perturbation Robustness for Layer Selection in VLM Vision Encoders

arXiv:2609.15229 · cs.CV, cs.AI · Submitted 2026-09-14 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: 6 pages, 4 figures. Accepted at the 2026 International Joint Conference on Neural Networks (IJCNN 2026)

Code: https://github.com/atoz03/prepeft-probing

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Fine-Tuning — 21× in this paper · explained in 5 episodes
• Benchmark — 18× in this paper · explained in 2 episodes
• Robustness — 13× in this paper · explained in 5 episodes
• Adaptation — 8× in this paper · explained in 1 episode
• Transformer — 8× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning — 4× in this paper · explained in 2 episodes
• Vision-language models — 4× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Adaptability — 2× in this paper · explained in 1 episode
• Hallucination — 2× in this paper · explained in 4 episodes
• Parameter-Efficient Fine-Tuning (PEFT) — 2× in this paper · explained in 4 episodes
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Convolutional Neural Networks (CNNs) — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Hallucination Detection — 1× in this paper · explained in 2 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Singular Value Decomposition — 1× in this paper
• Singular Value Decomposition (SVD) — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models
• Large Language Models: A Survey
• A Survey on Multimodal Large Language Models
• LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
• Qwen2 Technical Report
• Qwen2.5-VL Technical Report
• Investigating and unmasking feature-level vulnerabilities of CNNs to adversarial perturbations
• Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
• Chart-to-Text: A Large-Scale Benchmark for Chart Summarization
• CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning
• Are We on the Right Way for Evaluating Large Vision-Language Models?
• ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning
• MMBench: Is Your Multi-modal Model an All-around Player?
• VeRA: Vector-based Random Matrix Adaptation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models