Recently, there have been numerous attempts to enhance the sample efficiency of off-policy reinforcement learning (RL) agents when interacting with the environment, including architecture improvements and new algorithms. Despite these advances, they overlook the potential of directly constraining the initial representations of the input data, which can intuitively alleviate the distribution shift issue and stabilize training. In this paper, we introduce the Tanh function into the initial layer to fulfill such a constraint. We theoretically unpack the convergence […]

Ver mais

arXiv:2601.00260v1 Announce Type: new Abstract: While foundation models in radiology are expected to be applied to various clinical tasks, computational cost constraints remain a major challenge when training on 3D-CT volumetric data. In this study, we propose TotalFM, a radiological foundation model that efficiently learns the correspondence between 3D-CT images and linguistic expressions based on the concept of organ separation, utilizing a large-scale dataset of 140,000 series. By automating the creation of organ volume and finding-sentence pairs through […]

Ver mais

In the first part of this series, here, I feature a click fraud case that we are working on, litigated by one of the largest law firms in the US.  The input data comes from an Excel repository, automatically processed by an AI agent part of our BondingAI enterprise solutions. It comes with insights generation via automated SQL queries and pattern detection. In other contexts, the data may come from a PDF repository, the Internet, databases, or a […]

Ver mais

arXiv:2601.03335v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being used to evolve solutions to problems in many domains, in a process inspired by biological evolution. However, unlike biological evolution, most LLM-evolution frameworks are formulated as static optimization problems, overlooking the open-ended adversarial dynamics that characterize real-world evolutionary processes. Here, we study Digital Red Queen (DRQ), a simple self-play algorithm that embraces these so-called “Red Queen” dynamics via continual adaptation to a changing objective. DRQ uses […]

Ver mais

arXiv:2510.21300v2 Announce Type: replace-cross Abstract: Real-world data is frequently noisy and ambiguous. In crowdsourcing, for example, human annotators may assign conflicting class labels to the same instances. Partial-label learning (PLL) addresses this challenge by training classifiers when each instance is associated with a set of candidate labels, only one of which is correct. While early PLL methods approximate the true label posterior, they are often computationally intensive. Recent deep learning approaches improve scalability but rely on surrogate losses […]

Ver mais

Long-term COVID are frequently causing neuro- logical problems that persist for long time, like cognitive damage and changes in the structure of the brain that are very difficult to find with conventional clinical testing. When coupled with AI, neuroimaging might serve as a useful tool for finding small prob- lems.To build a deep learning-based neuroimaging framework that automatically recognizes and describe neurological diseases in long-term COVID patients. Deep learning models, such as CNNs, transformers, and graph neural networks, […]

Ver mais

arXiv:2601.22352v1 Announce Type: new Abstract: Language model agents often appear capable of self-recovery after failing tool call executions, yet this behavior lacks a formal explanation. We present a predictive theory that resolves this gap by showing that recoverability follows a measurable law. To elaborate, we formalize recoverability through Expected Recovery Regret (ERR), which quantifies the deviation of a recovery policy from the optimal one under stochastic execution noise, and derive a first-order relationship between ERR and an empirical […]

Ver mais

arXiv:2601.16412v1 Announce Type: new Abstract: The study of textit{regret minimization in fixed-price bilateral trade} has received considerable attention in recent research. Previous works [CCC+24a, CCC+24b, AFF24, BCCF24, CJLZ25, LCM25a, GDFS25] have acquired a thorough understanding of the problem, except for determining the tight regret bound for GBB semi-feedback fixed-price mechanisms under adversarial values. In this paper, we resolve this open question by devising an $widetilde{O}(T^{2 / 3})$-regret mechanism, matching the $Omega(T^{2 / 3})$ lower bound from [CJLZ25] up […]

Ver mais

arXiv:2602.08892v1 Announce Type: new Abstract: A major challenge in data-driven decision-making is accurate policy evaluation-i.e., guaranteeing that a learned decision-making policy achieves the promised benefits. A popular strategy is model-based policy evaluation, which estimates a model from data to infer counterfactual outcomes. This strategy is known to produce unwarrantedly optimistic estimates of the true benefit due to the winner’s curse. We searched the recent literature on data-driven decision-making, identifying a sample of 55 papers published in the Management […]

Ver mais