arXiv:2603.24925v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) systems that rely on semantic search often fail to retrieve the complete set of evidence for complex queries, particularly when information is distributed across multiple sources. Existing approaches either rely on iterative…
arXiv:2606.07581v1 Announce Type: new Abstract: A modern post-training pipeline often writes one symbol for its policy, pi_theta, while evaluating it through two different programs: a training kernel optimized for autograd and an inference kernel optimized for low-precision, fused, dynamically batched…
arXiv:2606.05797v2 Announce Type: replace Abstract: Longitudinal treatment decisions from multivariate time-series data require predicting potential outcomes under future treatment sequences in the presence of time-varying confounding, heterogeneous patient dynamics, and limited domain-specific data. Existing longitudinal causal estimators typically address this…
arXiv:2606.07582v1 Announce Type: new Abstract: Customer churn prediction is essential across data-driven industries such as insurance, digital banking, eCommerce, and subscription platforms, where retaining existing customers is typically more cost-effective than acquiring new ones. Predicting churn on structured datasets remains…
arXiv:2602.12129v2 Announce Type: replace-cross Abstract: Personalized book recommendation in Bangla literature has been constrained by the lack of structured, large-scale, and publicly available datasets. This work introduces RokomariBG, a large-scale heterogeneous book graph dataset designed to support research on personalized…
arXiv:2606.07583v1 Announce Type: new Abstract: Self-healing smart grids can quickly adjust their network configuration during outages to minimize power disruptions. During an outage, several actions can be taken, such as network reconfiguration through switching operations and emergency load shedding. However,…
arXiv:2606.04421v2 Announce Type: replace-cross Abstract: Many current agentic systems and LLM pipelines correct mistakes by optimizing outcome reward. This addresses only the what of failure: when an outcome diverges from prediction, the why and when of the mismatch are not…
arXiv:2606.07586v1 Announce Type: new Abstract: Spatial neural processing units (NPUs) provide an energy-efficient platform for edge LLM inference, but efficiently deploying an LLM end-to-end on such hardware remains labor-intensive. Although AI coding agents have begun to lower this cost, existing…
arXiv:2606.09109v1 Announce Type: cross Abstract: Video retrieval at scale is central to data curation and safety validation in autonomous driving, where users want to find not only scenes but also dynamic events such as cut-ins and hard braking. Existing vision-language…
arXiv:2606.07587v1 Announce Type: new Abstract: LLM routing has become a popular approach to improve the cost-quality trade-off of LLM services by dynamically selecting a model for each query. Recent work has explored a broad range of routing methods, including clustering-based…
