Tag: multimodal AI
Browse our exclusive articles!
Dynamic Preferences in Situated Conversational Recommendations
Explore how dynamic and implicit user preferences improve situated conversational recommendations using the SiPeR framework for personalized AI interaction...
A-MAR: Agent-Based Multimodal Art Retrieval Explained
Discover A-MAR, an agent-based multimodal art retrieval system enhancing fine-grained artwork understanding with explicit reasoning and evidence.
SafetyALFRED: Testing Safety in Multimodal Language Models
Discover SafetyALFRED, a benchmark assessing safety-conscious planning of multimodal large language models in real-world hazard scenarios.
VIB-Probe: Reducing Hallucinations in Vision-Language Models
Discover how VIB-Probe uses Variational Information Bottleneck to detect and mitigate hallucinations in Vision-Language Models for improved accuracy.
Chain-of-Thought Lowers Visual Spatial Reasoning in Multimodal LLMs
Study reveals Chain-of-Thought prompting reduces visual spatial reasoning accuracy in multimodal LLMs, urging new vision-centric AI methods.