HZHeng Zhang

Heng Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Heng Zhang has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    HyperBalance: Hypergraph-based Topology Optimization for Reliable Multi-Agent Communication

    by Heng Zhang, Xinyuan Liu, Yuling Shi, Yihao Zhong, Jiawei Chen, Lubin Gan, Hao Zhang, Jin Huang

  • Open Access

    H4G: Unlocking Faithful Inference for Zero-Shot Graph Learning in Hyperbolic Space

    by Heng Zhang, Jin Huang

    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 requiring fine-grained pattern recognition, particularly on heterophilic graphs. Through empirical and theoretical analysis, we identify an over-abstraction problem: current approaches operate at excessively large hyperbolic radii, compressing multi-scale structural information into uniform high-level abstractions. This abstraction-induced information loss obscures critical local patterns essential for accurate predictions. By analyzing embeddings in hyperbolic space, we demonstrate that optimal graph learning requires faithful preservation of fine-grained structural details, better retained by representations positioned closer to the origin. To address this, we propose H4G, a framework that systematically reduces embedding radii using learnable block-diagonal scaling matrices and Möbius matrix multiplication. This approach restores access to fine-grained patterns while maintaining global receptive ability with minimal computational overhead. Experiments show H4G achieves state-of-the-art zero-shot performance with 12.8% improvement on heterophilic graphs and 8.4% on homophilic graphs, confirming that radius reduction enables faithful multi-scale representation for advancing zero-shot graph learning.

  • Open Access

    Hyperbolic and Evidence-Prioritized Experts for Large Vision-Language Models

    by Zijie Zhou, Dandan Zhu, Hangxiangpan Wang, Heng Zhang, Huishen Jiao, Yi Zhao

  • Open Access

    Shifting the Computational Burden: Efficient Long-Text MLLMs via LLM-Guided Visual Text Rendering

    by Wenjun Huang, ShengZhi Shen, Yuan Liu, Pi Fang, Yong Wu, Yuhe Wang, Heng Zhang, Jiakai Pan, Zhengzhuo Wang, Jianguo Hu

    To address the significant computational overhead and semantic alignment challenges of processing long texts in Multimodal Large Models (MLLMs), this paper introduces a novel framework named \textbf{VisCompConText}. This framework leverages two key innovations—-visual text compression and LLM-guided training—to efficiently extend the context-handling capabilities of multimodal models. The core mechanism involves rendering lengthy text segments into spatially compact visual images (i.e., visual tokens), which drastically reduces GPU memory consumption and computational load during both training and inference. Concurrently, we leverage the superior comprehension abilities of Large Language Models (LLMs) to guide the training of the visual encoder, significantly enhancing its deep semantic awareness of long-form text. Experiments demonstrate that \textbf{VisCompConText} effectively improves model performance on tasks such as long-document understanding and visual question answering, complementing existing context-extension techniques. This work provides a systematic solution for achieving long-context multimodal learning that balances computational efficiency with semantic fidelity.