Tag: Vision-Language Models
Browse our exclusive articles!
EgoTSR: Advancing Ego-Centric Spatiotemporal AI Reasoning
Discover EgoTSR, a curriculum learning framework boosting ego-centric spatiotemporal reasoning for AI with 92.4% accuracy in long-horizon tasks.
Progressive Training to Fix Vision-Language Model Hallucinations
Discover a progressive training strategy that reduces spatio-temporal hallucinations in vision-language models, boosting dynamic reasoning accuracy.
SVSR: Enhancing Multimodal Reasoning with Self-Verification
Discover how SVSR improves multimodal reasoning by integrating self-verification and self-rectification for robust AI visual-text understanding.
Edu-MMBias: Auditing Social Bias in Vision-Language Models
Discover Edu-MMBias, a benchmark for auditing social bias in vision-language models within education, ensuring fairness across cognitive, affective, and be...
Improving Safety of Medical Vision-Language Models with Synthetic Demos
Discover how synthetic demonstrations enhance safety and performance in medical vision-language AI models, preventing harmful queries effectively.