Tag: vision-language models

Researchers have developed KARAMEL, a knowledge-aware framework that fuses vision-language encoding with heterogeneous graph neural networks to link artworks to ...

A new 200,000-question benchmark from Carnegie Mellon University reveals that leading vision-language models perform at random chance when interpreting engineering ...

Researchers in Vietnam have built a hybrid vision-language AI that diagnoses grapevine diseases with 98.7 percent accuracy while explaining its ...

A fine-tuned three-billion-parameter vision-language model learned to halt all traffic at simulated intersections when pedestrians were in danger, cutting their ...

Researchers in Taiwan have built a dual-arm robot that autonomously makes hospital beds using vision-language semantic keypoints and closed-loop failure ...

Researchers in India show that training only a 2.4-million-parameter projection module on top of frozen CLIP encoders lifts fashion image-to-text ...

A new conflict-aware framework teaches vision-language models to align their own uncertainty with tool confidence, reject unreliable OCR output, and ...

Researchers have introduced HGA-Net, a hypergraph-based adapter that connects related examples within each mini-batch and achieves near-perfect fine-grained recognition with ...

A new comprehensive review analyzes 13 pretrained multimodal AI models from 2020 to 2025, comparing their architectures, datasets, and applications ...

A new survey maps how training-free pipelines built on frozen AI models are tackling hour-long video understanding through token selection, ...