7 papers
Hallucination Begins Where Saliency Drops
Xiaofeng Zhang, Yuanchao Zhu, Chaochen Gu +8
Recent studies have examined attention dynamics in large vision-language models (LVLMs) to detect hallucinations. However, existing approaches remain limited in reliably distinguis…
GraphShaper: Geometry-aware Alignment for Improving Transfer Learning in Text-Attributed Graphs
Heng Zhang, Tianyi Zhang, Yuling Shi +6
Graph foundation models represent a transformative paradigm for learning transferable representations across diverse graph domains. Recent methods leverage large language models to…
AsyMoE: Leveraging Modal Asymmetry for Enhanced Expert Specialization in Large Vision-Language Models
Heng Zhang, Haichuan Hu, Yaomin Shen +9
Large Vision-Language Models (LVLMs) have demonstrated impressive performance on multimodal tasks through scaled architectures and extensive training. However, existing Mixture of…
S^2-KD: Semantic-Spectral Knowledge Distillation Spatiotemporal Forecasting
Wenshuo Wang, Yaomin Shen, Yingjie Tan +1
Spatiotemporal forecasting often relies on computationally intensive models to capture complex dynamics. Knowledge distillation (KD) has emerged as a key technique for creating lig…
H4G: Unlocking Faithful Inference for Zero-Shot Graph Learning in Hyperbolic Space
Heng Zhang, Tianyi Zhang, Zijun Liu +6
Text-attributed graphs are widely used across domains, offering rich opportunities for zero-shot learning via graph-text alignment. However, existing methods struggle with tasks re…
Can Representation Gaps Be the Key to Enhancing Robustness in Graph-Text Alignment?
Heng Zhang, Tianyi Zhang, Yuling Shi +6
Representation learning on text-attributed graphs (TAGs) integrates structural connectivity with rich textual semantics, enabling applications in diverse domains. Current methods l…