Journal of Artificial Intelligence Research

A Decomposition Strategy for Probability Flow Ordinary Differential Equations in Diffusion Generative Models with Dimensionally Sharp Convergence Guarantees

Gul Agha Jan Assar, Mohammad Khalid Storai — Mon, 06 Jul 2026 00:00:00 +0000

Background: Diffusion generative models have achieved remarkable success in image synthesis, audio generation, and molecular design, yet their deployment is constrained by the high computational cost of hundreds to thousands of sequential sampling steps. Existing accelerated samplers exhibit unfavorable dimensional dependence in their convergence guarantees, limiting their theoretical justification in high-dimensional practical settings. Objective: This study aims to develop a decomposition-based deterministic sampling framework for probability flow ordinary differential equations (PF-ODEs) that achieves dimensionally sharp convergence guarantees while maintaining computational efficiency. Methods: The PF-ODE is systematically partitioned into a linear variance-preserving subsystem and a nonlinear score-dependent subsystem. Sequential composition of their flow maps via a symmetric second-order Strang decomposition yields a training-free integrator. Theoretical analysis employs Baker-Campbell-Hausdorff expansions, renormalization arguments for transport equations, and stability estimates under simultaneous perturbations. Results: A non-asymptotic total variation bound TV(q̃ₕ, q) ≤ C(dε_Jac + √d ε_score + d(1 + 2√(log T))/T²) is established, reducing dimensional dependence from O(d⁶/T²) or O(d⁴/T²) of prior works to O(d/T²). Empirical validation confirms quadratic convergence (slope −1.98) on a synthetic Gaussian benchmark. Comparative experiments on CIFAR-10, CelebA, LSUN, and ImageNet subsets show superior FID against DPM-Solver, UniPC, and SA-Solver without additional runtime or memory overhead. Implications: Decomposition-based integration provides a theoretically principled and practically viable approach to accelerating diffusion sampling, bridging the gap between rigorous convergence guarantees and large-scale generative modeling applications.

Talent Management Transformation: Integrating Artificial Intelligence for Organizational Competitive Advantage

Uswah Nurlatifah — Mon, 02 Mar 2026 00:00:00 +0000

The transformation of talent management in the digital era is increasingly influenced by the development of artificial intelligence (AI), which plays a strategic role in enhancing an organization's competitive advantage. AI not only improves operational efficiency but also transforms the way organizations recruit, develop, evaluate, and retain talent. This study aims to analyze the role of AI in talent management, identify challenges faced by the human resources (HR) function, and evaluate the effectiveness of AI in improving employee performance and potential. The research method used is a qualitative approach based on literature review, reviewing scientific articles published between 2020 and 2025 relevant to the topic of AI and human resource management. The study results indicate that AI contributes significantly to the talent selection process, career development, performance evaluation, and employee turnover prediction through data-driven decision-making. However, AI implementation also faces challenges, such as algorithmic bias, lack of system transparency, organizational resistance, and the risk of dehumanizing HR processes. Therefore, the successful implementation of AI in talent management depends heavily on ethical governance, data quality, organizational cultural readiness, and harmonious collaboration between technology and human roles. This research provides academic and practical contributions to understanding how AI can be optimally and sustainably utilized in talent management in the digital era.

Physics-Constrained Symbolic Regression via Reinforcement Learning: A Rigorous Framework for Discovering Closed-Form Solutions to Differential Equations

Esmatullah Abed, Mallang Ahmadi — Tue, 23 Jun 2026 00:00:00 +0000

Discovering exact, interpretable, closed-form solutions to differential equations (DEs) remains one of the most intellectually demanding challenges at the intersection of applied mathematics and computational intelligence. Classical analytical techniques, while rigorous, are largely restricted to well-structured linear systems and fail to generalise to the nonlinear, high-dimensional configurations that dominate contemporary science and engineering. The present study introduces and theoretically and empirically validates a physics-constrained symbolic regression framework, designated PCSRL (Physics-Constrained Symbolic Regression via Reinforcement Learning), that unifies policy-gradient reinforcement learning with an exact physical constraint evaluator to recover closed-form symbolic solutions for a broad class of ordinary and partial differential equations. Rigorous evaluation across six canonical benchmark problems including linear and nonlinear Poisson, heat, and wave equations in both two- and three-dimensional spatial domains demonstrates that PCSRL achieves complete symbolic recovery (recovery rate = 100%) and physical-constraint residuals multiple orders of magnitude below those of competing methods, including genetic programming-based symbolic regression, Kolmogorov–Arnold Networks, and PINN-assisted symbolic regression pipelines. These results establish a principled, reproducible methodology for the machine discovery of physically exact symbolic solutions, with direct implications for mathematical physics, computational fluid dynamics, and scientific machine learning. Practically, the framework enables engineers and scientists to obtain transparent, analytically tractable models for complex physical systems, facilitating rapid design optimisation, stability analysis, and knowledge discovery in domains where black-box numerical approximations are insufficient.