I recently defended my PhD thesis at Cambridge and wrote a blog post reflecting on the journey. The thesis focuses on Geometric Deep Learning and moves from pure theory to wet-lab applications. I broke the research down into three main questions: Expressivity: How do we characterize the power of 3D representations? (Introducing the Geometric Weisfeiler-Leman Test). Generative Modelling: Can we build unified models for periodic and non-periodic systems? (Proposing the All-atom Diffusion Transformer). Real-world Design: Can generative AI […]

Ver mais

When working in AI, especially when doing an empirical PhD, the engineering required for effective experimentation is incredibly important. I procrastinated on writing this article for a while now, but it is getting more and more apparent these days when a large portion of research shifted to working with large foundation models. But even ~7 years ago, when I started my PhD, I quickly realized that running experiments effectively will be crucial. This is because effective experimentation means […]

Ver mais

arXiv:2512.22909v2 Announce Type: replace-cross Abstract: In this paper we study a nonconvex-strongly-concave constrained minimax problem. Specifically, we propose a first-order augmented Lagrangian method for solving it, whose subproblems are nonconvex-strongly-concave unconstrained minimax problems and suitably solved by a first-order method developed in this paper that leverages the strong concavity structure. Under suitable assumptions, the proposed method achieves an operation complexity of $O(varepsilon^{-3.5}logvarepsilon^{-1})$, measured in terms of its fundamental operations, for finding an $varepsilon$-KKT solution of the constrained minimax […]

Ver mais

Preliminaries convex definition linear algebra vector length vector direction Discriminant Function in Classification The discriminant function or discriminant model is on the other side of the generative model. And we, here, have a look at the behavior of the discriminant function in linear classification.1 In the post ‘Least Squares Classification’, we have seen, in a linear classification task, the decision boundary is a line or hyperplane by which we separate two classes.

Ver mais

arXiv:2601.03386v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV) with slung load system is a classic air transportation system. In practical applications, the suspension point of the slung load does not always align with the center of mass (CoM) of the UAV due to mission requirements or mechanical interference. This offset creates coupling in the system’s nonlinear dynamics which leads to a complicated motion control problem. In existing research, modeling of the system are performed about the UAV’s […]

Ver mais

arXiv:2601.03323v1 Announce Type: new Abstract: Advances in generative models and sequence learning have greatly promoted research in dance motion generation, yet current methods still suffer from coarse semantic control and poor coherence in long sequences. In this work, we present Listen to Rhythm, Choose Movements (LRCM), a multimodal-guided diffusion framework supporting both diverse input modalities and autoregressive dance motion generation. We explore a feature decoupling paradigm for dance datasets and generalize it to the Motorica Dance dataset, separating […]

Ver mais

Ver mais