Tag: Vision-Language Models
Browse our exclusive articles!
INDOTABVQA: Cross-Lingual Table VQA Benchmark for Bahasa
Explore INDOTABVQA, a benchmark for cross-lingual table understanding in Bahasa Indonesia documents, enhancing Vision-Language Models' accuracy.
MemJack: Advanced Multi-Agent Jailbreak Attacks on VLMs
Discover MemJack, a memory-augmented multi-agent framework exposing deep vulnerabilities in Vision-Language Models with 90% attack success rate.
Fine-Tuning Qwen2.5-VL for Better Web Interaction
Improve Qwen2.5-VL's web interaction skills with fine-tuning to enhance localization, instruction comprehension, and action accuracy.
Multi-Agent Script Generation for Murder Mystery Games
Enhance imperfect-information reasoning in murder mystery games with collaborative multi-agent script generation and multimodal context integration.
Anthropogenic Regional Adaptation in Vision-Language Models
Discover how Anthropogenic Regional Adaptation and GG-EZ enhance vision-language models for regional relevance without losing global accuracy.