arXiv:2601.16376v1 Announce Type: new Abstract: On-demand Polymer discovery is essential for various industries, ranging from biomedical to reinforcement materials. Experiments with polymers have a long trial-and-error process, leading to long procedures and extensive resources. For these processes, machine learning has accelerated scientific discovery at the property prediction and latent space search fronts. However, laboratory researchers cannot readily access codes and these models to extract individual structures and properties due to infrastructure limitations. We present a closed-loop polymer structure-property […]

Ver mais

arXiv:2603.05598v1 Announce Type: new Abstract: We investigate the impact of tokeniser pretraining on the accuracy and efficiency of physics emulation. Modern high-resolution simulations produce vast volumes of data spanning diverse physical regimes and scales. Training foundation models to learn the dynamics underlying such data enables the modelling of complex multiphysics phenomena, especially in data-limited settings. The emerging class of physics foundation models typically aims to learn two tasks jointly: (i) extracting compact representations of high-resolution spatiotemporal data, and […]

Ver mais

arXiv:2601.00202v1 Announce Type: new Abstract: Reasoning over temporal knowledge graphs (TKGs) is fundamental to improving the efficiency and reliability of intelligent decision-making systems and has become a key technological foundation for future artificial intelligence applications. Despite recent progress, existing TKG reasoning models typically rely on large parameter sizes and intensive computation, leading to high hardware costs and energy consumption. These constraints hinder their deployment on resource-constrained, low-power, and distributed platforms that require real-time inference. Moreover, most existing model […]

Ver mais

Packworks is building the operating system for Southeast Asia’s informal retail economy by digitizing hundreds of thousands of sari-sari stores in the Philippines. Through a mobile ERP platform, data analytics, and AI-driven insights, the company helps micro-retailers manage inventory and sales while enabling FMCG brands to reach fragmented last-mile markets. With over 15 million transactions annually and $272M GMV processed in 2025, Packworks is transforming neighborhood stores into a scalable retail data network.

Ver mais

Robust control of mechanical systems with multiple uncertainties remains a fundamental challenge, particularly when nonlinear dynamics and operating-condition variations are intricately intertwined. While deep reinforcement learning (DRL) combined with domain randomization has shown promise in mitigating the sim-to-real gap, simultaneously handling all sources of uncertainty often leads to sub-optimal policies and poor learning efficiency. This study formulates a new curriculum-based continual learning framework for robust control problems involving nonlinear dynamical systems in which multiple sources of uncertainty are […]

Ver mais

Excess inventory is one of the most persistent and costly inefficiencies in modern supply chains. For many organizations, it quietly erodes working capital, inflates warehousing costs, and creates a false sense of security around product availability. The traditional approach to managing inventory, which relied on intuition, spreadsheets, and static reorder points, simply cannot keep pace with the complexity of today’s demand signals. What has changed the game significantly is the application of data-driven optimization frameworks that bring together […]

Ver mais

arXiv:2601.04149v1 Announce Type: new Abstract: Class imbalance significantly degrades classification performance, yet its effects are rarely analyzed from a unified theoretical perspective. We propose a principled framework based on three fundamental scales: the imbalance coefficient $eta$, the sample–dimension ratio $kappa$, and the intrinsic separability $Delta$. Starting from the Gaussian Bayes classifier, we derive closed-form Bayes errors and show how imbalance shifts the discriminant boundary, yielding a deterioration slope that predicts four regimes: Normal, Mild, Extreme, and Catastrophic. Using […]

Ver mais

arXiv:2602.11243v1 Announce Type: new Abstract: Modern LLM-based agents and chat assistants rely on long-term memory frameworks to store reusable knowledge, recall user preferences, and augment reasoning. As researchers create more complex memory architectures, it becomes increasingly difficult to analyze their capabilities and guide future memory designs. Most long-term memory benchmarks focus on simple fact retention, multi-hop recall, and time-based changes. While undoubtedly important, these capabilities can often be achieved with simple retrieval-augmented LLMs and do not test complex […]

Ver mais