arXiv (All)
open access
Readout Blindness: VLM Scores Miss the Spatial Direction Their Frozen Encoders Retain
CLIP-like vision-language models remain a cornerstone of multimodal systems, yet their scores stay near chance on directed spatial relations, such as whether one object is left of another. We call this failure readout blindness and analyze, theoretically and empirically, why deployed scores miss the
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
- Assisted Spatial Cognition Through Vision-Language Models#1070218
- Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs#1234772
- One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models#1130943
- Exploring Attention Sinks in Text-to-Image Transformers from Diffusion and Autoregressive Models#1297689
- LinguDistill: Recovering Linguistic Ability in Vision-Language Models via Selective Cross-Modal Distillation#1199785
Record · ID 1202743
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