Fundamental limits of prompt tuning transformers: Universality, capacity and efficiency

JYC Hu, WP Wang, A Gilani, C Li, Z Song… - arxiv preprint arxiv …, 2024 - arxiv.org
We investigate the statistical and computational limits of prompt tuning for transformer-based
foundation models. Our key contributions are prompt tuning on\textit {single-head} …

Gita: Graph to visual and textual integration for vision-language graph reasoning

Y Wei, S Fu, W Jiang, Z Zhang, Z Zeng… - The Thirty-eighth …, 2024 - openreview.net
Large Language Models (LLMs) are increasingly used for various tasks with graph
structures. Though LLMs can process graph information in a textual format, they overlook the …

Multi-Perspective Test-Time Prompt Tuning for Global, Local Visuals, and Language

Z Huang, Y Zhang, JJ **e, F Chao, R Ji - openreview.net
Recent advances in vision-language models (VLMs) have demonstrated significant
generalization across a broad range of tasks through prompt learning. However, bridging …