3 papers
cs.CV2025
Modular Prompt Learning Improves Vision-Language Models
Zhenhan Huang, Tejaswini Pedapati, Pin-Yu Chen +1
Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encode…
cs.LG2025
Sparse Gradient Compression for Fine-Tuning Large Language Models
David H. Yang, Mohammad Mohammadi Amiri, Tejaswini Pedapati +2
Fine-tuning large language models (LLMs) for downstream tasks has become increasingly crucial due to their widespread use and the growing availability of open-source models. Howeve…
cs.LG2024
Differentiable Prompt Learning for Vision Language Models
Zhenhan Huang, Tejaswini Pedapati, Pin-Yu Chen +1
Prompt learning is an effective way to exploit the potential of large-scale pre-trained foundational models. Continuous prompts parameterize context tokens in prompts by turning th…