Institution profile

Durham University

Academic institutioneurope · gb
Official website
Research library305linked papers
Opportunities0open roles
Selected work

Representative Papers

Computing Balanced Solutions for Large International Kidney Exchange Schemes When Cycle Length Is Unbounded

Dec 27, 2023Adaptive Agents and Multi-Agent Systems

This paper addresses the optimization problem in International Kidney Exchange Programs (IKEPs) under the constraint of unbounded exchange cycle length, jointly maximizing social welfare and ensuring fairness in initial country-level allocations. We establish, for the first time, that this problem admits a polynomial-time exact algorithm; however, computing the lexicographically minimal deviation solution is shown to be feasible only under additional assumptions. To achieve fairness, we propose a cooperative-game-theoretic framework incorporating credit adjustment, integrating solution concepts such as the Shapley value and the nucleolus. Our scalable solver combines integer linear programming, graph matching, and cycle-covering algorithms. Extensive experiments on million-node instances demonstrate that unbounded-cycle exchanges significantly improve long-term stability and aggregate social welfare over 2-cycle–only schemes, while maintaining computational efficiency and scalability.

4 citationsRead paper

Convergence analysis of controlled particle systems arising in deep learning: from finite to infinite sample size

Apr 08, 2024arXiv.org

This work investigates the mean-field limit behavior of controlled particle systems in deep learning as the sample size $N o infty$, focusing on the convergence of optimal control for the associated neural stochastic differential equation (Neural SDE) sampling problem. Methodologically, we establish $N$-uniform regularity estimates for the Hamilton–Jacobi–Bellman equation, and integrate the stochastic maximum principle, backward stochastic Riccati equations, variational calculus on Wasserstein space, and mean-field limit theory. Our main contribution is the first derivation of **quantitative algebraic convergence rates**, with explicit dependence on $N$, for both the optimal parameters and the minimal value of the objective functional toward a differentiable functional defined on Wasserstein space. Crucially, we rigorously formulate the limiting control problem as a differentiable optimization problem over Wasserstein space—thereby providing the first convergence guarantee with an explicit rate. This advances the theoretical foundation and algorithmic design of Neural SDEs.

1 citations1 influentialRead paper

Computing Diffusion Geometry

Feb 05, 2026

Traditional calculus and Riemannian geometry struggle to handle non-manifold, noisy real-world data. This work proposes a data-driven framework grounded in diffusion processes that, for the first time, systematically realizes computable formulations of vector calculus and key geometric objects—such as geodesic distances, curvatures, vector field flows, and solutions to partial differential equations—within the paradigm of diffusion geometry. The framework further integrates topological tools from de Rham cohomology and Morse theory. Leveraging efficient numerical linear algebra techniques, it achieves substantial improvements in computational accuracy, noise robustness, and scalability, demonstrating exceptional numerical stability, low computational complexity, and strong robustness across a range of geometric and topological tasks.

1 citationsRead paper

From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction

Feb 02, 2026

This work addresses the challenges of temporally inconsistent predictions—such as flickering—in human-centric dense video tasks under motion, occlusion, and illumination changes, compounded by the scarcity of multi-task paired video supervision. To this end, we propose a scalable, photorealistic synthetic human video generation method that, for the first time, provides both frame-level and sequence-level pixel-wise annotations, including depth, surface normals, and masks. Leveraging this data, we develop a unified Vision Transformer (ViT)-based dense prediction architecture that integrates CSE human geometric priors with a lightweight channel reweighting module. Our approach employs a two-stage training strategy—static pretraining followed by dynamic sequence fine-tuning—to jointly optimize spatial and temporal consistency. The method achieves state-of-the-art performance on THuman2.1 and Hi4D benchmarks and demonstrates strong generalization to in-the-wild real-world videos.

1 citationsRead paper

Dynamic Worlds, Dynamic Humans: Generating Virtual Human-Scene Interaction Motion in Dynamic Scenes

Jan 27, 2026

This work addresses the limitation of existing virtual human–scene interaction methods, which typically assume static environments and thus struggle in real-world dynamic settings. We propose Dyn-HSI, the first cognitive architecture for human–scene interaction generation tailored to dynamic scenes, integrating visual perception, memory mechanisms, and action control to enable continuous environmental awareness, experience reuse, and high-quality motion synthesis. Key innovations include dynamic scene-aware navigation, a hierarchical experience memory module, and a multimodal conditional diffusion model. We also introduce Dyn-Scenes, the first benchmark dataset for dynamic human–scene interactions. Experiments demonstrate that our approach significantly outperforms current methods in both static and dynamic scenarios, generating motions that exhibit high fidelity and strong contextual awareness, thereby validating its generalization capability and motion quality.

1 citationsRead paper
Recent publications

Latest Papers