digitado

Graph Transformers have recently attracted attention for molecular property prediction by combining the inductive biases of graph neural networks (GNNs) with the global receptive field of Transformers. However, many existing hybrid architectures remain GNN-dominated, causing the resulting representations to remain heavily shaped by local message passing. Moreover, most existing methods operate at only a single structural granularity, limiting their ability to capture molecular patterns that span multiple molecular scales. We introduce BiScale-GTR, a unified framework for self-supervised molecular […]

Ver mais

In a landmark result, Linial, Mansour and Nisan (J. ACM 1993) gave a quasipolynomial-time algorithm for learning constant-depth circuits given labeled i.i.d. samples under the uniform distribution. Their work has had a deep and lasting legacy in computational learning theory, in particular introducing the $textit{low-degree algorithm}$. However, an important critique of many results and techniques in the area is the reliance on product structure, which is unlikely to hold in realistic settings. Obtaining similar learning guarantees for more […]

Ver mais

Modeling real-world systems requires accounting for noise – whether it arises from unpredictable fluctuations in financial markets, irregular rhythms in biological systems, or environmental variability in ecosystems. While the behavior of such systems can often be described by stochastic differential equations, a central challenge is understanding how noise influences the inference of system parameters and dynamics from data. Traditional symbolic regression methods can uncover governing equations but typically ignore uncertainty. Conversely, Gaussian processes provide principled uncertainty quantification but […]

Ver mais

We have been exploring a project around post-training infrastructure, a minimalist tool that does one thing really well: Make post-training a little less painful by equipping Researchers, AI/ML engineers & Tinkerers with a gentle control plane. Post-training models tends to introduce a new axis of complexity – the orchestration and compute ressource management – alongside defining your own training loop, your rewards & rubrics, managing the parallel training. Tahuna is CLI-first, it sits between your local environment and […]

Ver mais

Value iteration-type methods have been extensively studied for computing a nearly optimal value function in reinforcement learning (RL). Under a generative sampling model, these methods can achieve sharper sample complexity than policy optimization approaches, particularly in their dependence on the discount factor. In practice, they are often employed for offline training or in simulated environments. In this paper, we consider discounted Markov decision processes with state space S, action space A, discount factor $γin(0,1)$ and costs in $[0,1]$. […]

Ver mais