YSYang Shi

Yang Shi

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yang Shi has a total of 28 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Diffusion Image Editing via Asynchronous Token Decoding

    by Yang Shi, Liangsi Lu, Minzhe Guo, Yifeng Xie, Yanhui Chen, Jingchao Wang, Xuhang Chen

    Text-guided diffusion image editing aims to modify semantic attributes of an image while preserving its identity, layout, and background. However, na\''ively switching the text condition during sampling often causes global drift, as denoising dynamics propagate changes across tokens and can disrupt unedited regions. To address this issue, we propose Asynchronous Token Decoding Edit (ATDEdit), an inference-time framework that views each sampler step as a parallel update of a globally coupled token matrix and enables token-indexed condition switching with differentiated update policies. Instead of applying synchronous target-conditioned updates to all tokens, ATDEdit estimates editable locations using token-wise conditional surprisal and applies target-conditioned corrections to the selected token set. It supplies source key/value memory at keep-token positions and projects selected keep-token latent rows back to their source values; these operations promote background preservation but do not constitute a pixel-level invariance guarantee. This approach combines local editing and background preservation without external or user-provided spatial masks and without model fine-tuning. On PIE-Bench, ATDEdit achieves the strongest reported preservation metrics, including 27.44~dB PSNR and 0.055 LPIPS, while retaining competitive semantic alignment.

  • Open Access

    Enhancing Robustness of Constant Curvature Graph Convolutional Network with Lipschitz Regularization

    by Yang Shi, Jingchao Wang, Liangsi Lu, Haiying Huang, Sutong Xiao, Zhaorong Dai, Ying Wang, Boyan Xu

    Non-Euclidean spaces inherently enable high-fidelity embeddings for hierarchical and cyclical data due to their geometric properties. Existing approaches unify hyperbolic and spherical embeddings within the framework of constant curvature spaces. However, current methods for Lipschitz regularization remain limited to non-positive curvature geometries, such as hyperbolic and Euclidean spaces, and cannot be naturally extended to the general constant curvature setting. In this article, we present a rigorous Lipschitz analysis for constant curvature graph convolutional networks ( \(\kappa\) -GCNs) and enhance their robustness through Lipschitz regularization. We derive upper bounds for the Lipschitz constants across constant curvature spaces, thereby standardizing the Lipschitz limits of the \(\kappa\) -stereographic model. Furthermore, we incorporate these bounds into a regularization framework for \(\kappa\) -GCNs to improve stability and robustness. Experimental results demonstrate that the proposed regularization method often strengthens the robustness of \(\kappa\) -GCNs across various curvature regimes, particularly under Gaussian feature noise.

  • Open Access

    Over-squashing as Transport Congestion: A Sandpile Dynamics Perspective

    by Yang Shi, Lixian Chen, Jingchao Wang, Minzhe Guo, Mingxuan Huang, Yanhui Chen, Yifeng Xie, Xuhang Chen, Liangsi Lu

    Message-passing graph neural networks (MP-GNNs) are widely used for learning on relational data. However, their performance drops on tasks requiring long-range interactions due to over-squash­ing, where exponential information compression overwhelms fixed-width embeddings. While existing analyses often attribute this to geometric bottlenecks under linear diffusion assumptions, thresholded nonlinearities in GNNs motivate a load-release view akin to Abelian sandpiles. Using the discrete sandpile model as a structural proxy, we show that graph bottlenecks force large stabilization cost, effectively creating zones of high transport congestion. We characterize stabilization-invariant equivalence classes induced by the reduced Laplacian and derive cut-based lower bounds linking bottlenecks to unavoidable stabilization effort. The resulting theory is discrete, whereas our implementation is a continuous vector-valued surrogate. The theory identifies the relevant design factors, namely capacity and cut size. Guided by these insights, we propose a differentiable Sandpile Stabilization Layer (SSL) and congestion-aware objectives designed to redistribute excess load and manage stabilization costs. Experiments on long-range benchmarks, together with congestion and collision diagnostics, show that targeting sandpile-identified bottlenecks mitigates representation collapse and improves over standard baselines. Project Page: https://sandpile-gnn.github.io/

  • When task performance deceives: Task-geometry decoupling in learnable-curvature hyperbolic GNNs

    by Lixian Chen, Jingchao Wang, Zhaorong Dai, Hanqian Liu, Danxiang Ai, Yang Shi

  • Open Access

    Riemannian Liquid Spatio-Temporal Graph Network

    by Liangsi Lu, Jingchao Wang, Zhaorong Dai, Hanqian Liu, Yang Shi

    Liquid Time-Constant networks (LTCs), a type of continuous-time graph neural network, excel at modeling irregularly-sampled dynamics but are fundamentally confined to Euclidean space. This limitation introduces significant geometric distortion when representing real-world graphs with inherent non-Euclidean structures (e.g., hierarchies and cycles), degrading representation quality. To overcome this limitation, we introduce the Riemannian Liquid Spatio-Temporal Graph Network (RLSTG), a framework that unifies continuous-time liquid dynamics with the geometric inductive biases of Riemannian manifolds. RLSTG models graph evolution through an Ordinary Differential Equation (ODE) formulated directly on a curved manifold, enabling it to faithfully capture the intrinsic geometry of both structurally static and dynamic spatio-temporal graphs. Moreover, we provide rigorous theoretical guarantees for RLSTG, extending stability theorems of LTCs to the Riemannian domain and quantifying its expressive power via state trajectory analysis. Extensive experiments on real-world benchmarks demonstrate that, by combining advanced temporal dynamics with a Riemannian spatial representation, RLSTG achieves superior performance on graphs with complex structures. Project Page: https://rlstg.github.io


  • Open Access

    PR-CapsNet: Pseudo-Riemannian Capsule Network with Adaptive Curvature Routing for Graph Learning

    by Ye Qin, Jingchao Wang, Yang Shi, Haiying Huang, Junxu Li, Weijian Liu, Tinghui Chen, Jinghui Qin


  • DHS-PE: A more suitable positional encoding for directed hypergraphs

    by Ruixin He, Yang Shi, Mingxuan Huang, Liangsi Lu, Zhaorong Dai, Yingtong Shi, Jingchao Wang, Zhuoming Xie