Hi , I’m much interested into applied RL and looking for a job or a summer internship this summer , I’m a 3rd year undergrad at a tier 1 research institute . However my doubt is my main interest in rl is its ability to create greater impact , speaking about impact what I truly wanted was to use sample efficient rl and create an impact in sustainability and energy grid optimization but I think a greater application […]
arXiv:2505.04613v3 Announce Type: replace Abstract: We prove that kernel covariance embeddings lead to information-theoretically perfect separation of distinct continuous probability distributions. In statistical terms, we establish that testing for the emph{equality} of two non-atomic (Borel) probability measures on a locally compact Polish space is emph{equivalent} to testing for the emph{singularity} between two centered Gaussian measures on a reproducing kernel Hilbert space. The corresponding Gaussians are defined via the notion of kernel covariance embedding of a probability measure, and […]
arXiv:2601.12282v1 Announce Type: new Abstract: The functions of different regions of the human brain are closely linked to their distinct cytoarchitecture, which is defined by the spatial arrangement and morphology of the cells. Identifying brain regions by their cytoarchitecture enables various scientific analyses of the brain. However, delineating these areas manually in brain histological sections is time-consuming and requires specialized knowledge. An automated approach is necessary to minimize the effort needed from human experts. To address this, we […]
I wanted to see if I could build a full-duplex speech model that avoids the coherence degradation that plagues models of this type while also requiring low compute for training and inference. I don’t have access to much compute so I spent a lot of the time designing the architecture so it’s efficient and there is no need to brute force with model size and training compute. Also I made sure that all the components can be pretrained […]
Primary care physicians face increasing challenges in managing multimorbidity, continuous home-monitoring data, and fragmented access to specialty input. We propose an agentic artificial intelligence (AI) architecture for Medici di Medicina Generale (MMG) that combines a central planning large language model (LLM) with a bank of small, domain-specialized language models (SLMs) and determinis- tic tools. The system is designed for patient–home integration, safety triage, and transparent interoperability with regional infrastructures such as FSE 2.0 and ePre- scription. Here, we […]
arXiv:2601.18966v1 Announce Type: new Abstract: Users trust algorithms more when they can predict the algorithms’ behavior. Simple algorithms trivially yield predictively accurate mental models, but modern AI algorithms have often been assumed too complex for people to build predictive mental models, especially in the social media domain. In this paper, we describe conditions under which even complex algorithms can yield predictive mental models, opening up opportunities for a broader set of human-centered algorithms. We theorize that users will […]
Emergency Department overcrowding is a critical issue that compromises patient safety and operational efficiency, necessitating accurate demand forecasting for effective resource allocation. This study evaluates and compares three distinct predictive models: Seasonal AutoRegressive Integrated Moving Average with eXogenous regressors (SARIMAX), EXtreme Gradient Boosting (XGBoost) and Long Short-Term Memory (LSTM) networks for forecasting daily ED arrivals over a seven-day horizon. Utilizing data from an Australian tertiary referral hospital spanning January 2017 to December 2021, this research distinguishes itself by […]
Traditional kernel fuzzers rely on coarse-grained coverage metrics that cannot reflect complex microarchitectural behaviors. We present a hardware-assisted fuzzing framework that leverages branch buffer telemetry from modern CPUs (LBR, BTB sampling) to refine fuzzing feedback. A model-based inference algorithm aggregates branch-data patterns to estimate microarchitectural novelty and guides seed prioritization. Experiments on Intel Ice Lake and AMD Zen 3 systems demonstrate 27% improvement in unique path coverage, with 11 newly identified concurrency bugs across filesystem and scheduler subsystems. […]
Numerous offline and model-based reinforcement learning systems incorporate world models to emulate the inherent environments. A world model is particularly important in scenarios where direct interactions with the real environment is costly, dangerous, or impractical. The efficacy and interpretability of such world models are notably contingent upon the quality of the underlying training data. In this context, we introduce Action Shapley as an agnostic metric for the judicious and unbiased selection of training data. To facilitate the computation […]
The life of a prescription at Amazon Pharmacy From pricing estimation and regulatory compliance to inventory management and chatbot assistants, machine learning models help Amazon Pharmacy customers stay healthy and save time and money. Conversational AI Alexandre Alves Anita Vila September 30, 01:32 PM October 02, 11:42 AM Pharmacies play a vital role in ensuring patients health, but the process of dispensing medications is far more complex than it may appear. At Amazon Pharmacy, we are using artificial […]