arXiv:2603.19835v2 Announce Type: replace Abstract: We present Future-KL Influenced Policy Optimization (FIPO), a reinforcement learning algorithm designed to overcome reasoning bottlenecks in large language models. While GRPO style training scales effectively, it typically relies on outcome-based rewards (ORM) that distribute…
arXiv:2603.22317v1 Announce Type: new Abstract: Graph-structured data typically exhibits complex topological heterogeneity, making it difficult to model accurately within a single Riemannian manifold. While emerging mixed-curvature methods attempt to capture such diversity, they often rely on implicit, task-driven routing that…
arXiv:2410.12164v2 Announce Type: replace-cross Abstract: Language models such as GPT and Llama have shown remarkable ability on diverse natural language tasks, yet their performance on complex table tasks (e.g., NL-to-Code and data cleaning) remains suboptimal. Improving performance typically requires task-specific…
arXiv:2603.22318v1 Announce Type: new Abstract: Direct numerical simulations of turbulent reacting flows involving millions of grid points and detailed chemical mechanisms with hundreds of species and thousands of reactions are computationally prohibitive. To address this challenge, we present two data-driven…
arXiv:2509.02060v4 Announce Type: replace-cross Abstract: Peptide self-assembly prediction offers a powerful bottom-up strategy for designing biocompatible, low-toxicity materials for large-scale synthesis in a broad range of biomedical and energy applications. However, screening the vast sequence space for categorization of aggregate…
arXiv:2603.22319v1 Announce Type: new Abstract: Data assimilation (DA) for systems governed by partial differential equations (PDE) aims to reconstruct full spatiotemporal fields from sparse high-fidelity (HF) observations while respecting physical constraints. While full-grid low-fidelity (LF) simulations provide informative priors in…
arXiv:2603.08956v5 Announce Type: replace-cross Abstract: This survey (re)introduces reinforcement learning methods to economists. The curse of dimensionality limits how far exact dynamic programming can be effectively applied, forcing us to rely on suitably “small” problems or our ability to convert…
arXiv:2603.22320v1 Announce Type: new Abstract: While climate models provide insights for climate decision-making, their use is constrained by significant computational and technical demands. Although machine learning (ML) emulators offer a way to bypass the high computational costs, their effective use…
arXiv:2603.22987v1 Announce Type: cross Abstract: Membership inference attacks (MIAs) aim to determine whether a data sample was included in a machine learning (ML) model’s training set and have become the de facto standard for measuring privacy leakages in ML. We…
arXiv:2603.22322v1 Announce Type: new Abstract: Machine learning systems deployed in medical devices require governance frameworks that ensure safety while enabling continuous improvement. Regulatory bodies including the FDA and European Union have introduced mechanisms such as the Predetermined Change Control Plan…
