Tag: AI fine-tuning
Browse our exclusive articles!
AGFT: Boost Zero-Shot Adversarial Robustness in VLMs
Enhance zero-shot adversarial robustness of vision-language models with AGFT's alignment-guided fine-tuning preserving cross-modal integrity.
PRISM Dataset: Enhancing Retail Vision-Language Models
Discover PRISM, a multi-view retail video dataset boosting embodied vision-language models with spatial and action understanding.
How Markdown Training Influences Em Dash Use in LLMs
Explore how markdown training shapes em dash usage in large language models, revealing unique stylistic fingerprints and fine-tuning insights.
Balanced Fine-Tuning for Biomedical LLM Alignment
Enhance Large Language Models in biomedical fields using Balanced Fine-Tuning for improved accuracy and knowledge alignment.
Boost Vision-Language Fine-Tuning with Adaptive Depth Aggregation
Improve vision-language model fine-tuning by mitigating reasoning tax using Input-Adaptive Depth Aggregation for better reasoning and perception.