Co-Occurrence Priors Override Visual Spatial Evidence: Understanding False Alarms in Vision-Language Models for Construction Struck-By Hazard Detection
cs.CV, cs.LG
Submitted: 2026-11-03
Updated: 2026-11-03
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Understanding intermediate layers using linear classifier probes
- Qwen2.5-VL Technical Report
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- Hidden in plain sight: VLMs overlook their visual representations
- Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs
- Why Far Looks Up: Probing Spatial Representation in Vision-Language Models
- Towards Interpreting Visual Information Processing in Vision-Language Models
- Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
- Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models
- SAM 2: Segment Anything in Images and Videos
- Pathways of Visual Information Flow in Vision-Language Models
- Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
- Image Tokens Matter: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- Qwen-Image Technical Report
- Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention
- When and why vision-language models behave like bags-of-words, and what to do about it?
- MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs