From the 1 of 6 linked papers with an AI index.
6 papers
MQAdapter: Multi-Modal Quantum Adapter for Coarse-to-Fine VLM Fine-tuning
Yumiao Zhao, Bo Jiang, Min Lu +2
The paper introduces MQAdapter, a parameter‑efficient adapter that uses quantum state encoding to refine visual features with top‑K semantic anchors, enabling coarse‑to‑fine fine‑t…
Unified Graph Prompt Learning via Low-Rank Graph Message Prompting
Beibei Wang, Bo Jiang, Ziyan Zhang +1
Graph Data Prompt (GDP), which introduces specific prompts in graph data for efficiently adapting pre-trained GNNs, has become a mainstream approach to graph fine-tuning learning p…
Robust and Generalizable GNN Fine-Tuning via Uncertainty-aware Adapter Learning
Bo Jiang, Weijun Zhao, Beibei Wang +2
Recently, fine-tuning large-scale pre-trained GNNs has yielded remarkable attention in adapting pre-trained GNN models for downstream graph learning tasks. One representative fine-…
RepoMasterEval: Evaluating Code Completion via Real-World Repositories
Qinyun Wu, Chao Peng, Pengfei Gao +9
With the growing reliance on automated code completion tools in software development, the need for comprehensive evaluation benchmarks has become critical. Existing benchmarks focu…
Fine-Grained VLM Fine-tuning via Latent Hierarchical Adapter Learning
Yumiao Zhao, Bo Jiang, Yuhe Ding +3
Adapter-based approaches have garnered attention for fine-tuning pre-trained Vision-Language Models (VLMs) on few-shot classification tasks. These methods strive to develop a light…
HeGraphAdapter: Tuning Multi-Modal Vision-Language Models with Heterogeneous Graph Adapter
Yumiao Zhao, Bo Jiang, Xiao Wang +2
Adapter-based tuning methods have shown significant potential in transferring knowledge from pre-trained Vision-Language Models to the downstream tasks. However, after reviewing ex…