arXiv (OAI Expanded)
open access
Same Answer, Different Representations: Hidden instability in VLMs
The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. In this work, we argue that this assumption is insufficient. We introduce a representation-aware and frequency-aware
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- From Knowing to Abstaining: Bridging the Representation-Action Gap in Vision-Language Models#1116984
- Semantic Misalignment in Vision-Language Models under Perceptual Degradation#1143662
- Revealing Multi-View Hallucination in Large Vision-Language Models#820396
- Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes#987527
- Speed in the Blind Spot: An Interpretability Analysis of Dynamic Perception in VLMs for Autonomous Driving#1132247
Record · ID 1123018
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive