Perception, Not Reasoning, Limits Visual Theory of Mind
cs.CV, cs.AI, cs.CL, q-bio.NC
Submitted: 2026-11-07
Updated: 2026-11-07
Terminology
Sources
- Qwen2.5-VL Technical Report
- Vision Language Models See What You Want but not What You See
- MMToM-QA: Multimodal Theory of Mind Question Answering
- Core Knowledge Deficits in Multi-Modal Language Models
- Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs
- Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models
- Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks
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