arXiv:2408.01517v3 Announce Type: replace-cross Abstract: We prove that the standard gradient flow in parameter space that underlies many training algorithms in deep learning can be continuously deformed into an adapted gradient flow which yields (constrained) Euclidean gradient flow in output space. Moreover, for the $L^{2}$ loss, if the Jacobian of the outputs with respect to the parameters is full rank (for fixed training data), then the time variable can be reparametrized so that the resulting flow is simply […]

Ver mais

Task-free online continual learning has recently emerged as a realistic paradigm for addressing continual learning in dynamic, real-world environments, where data arrive in a non-stationary stream without clear task boundaries and can only be observed once. To consider such challenging scenarios, many recent approaches have employed prompt selection, an adaptive strategy that selects prompts from a pool based on input signals. However, we observe that such selection strategies often fail to select appropriate prompts, yielding suboptimal results despite […]

Ver mais

In this paper, all the integrals and their solutions are given for the analytical calculation of all six area and moments values of the arbitrary ellipse region given in trigonometric parametric form, based on the general moment form of Green’s theorem curve integral obtained from the discrete and differential vector product methods. The actual area and moments values of the arbitrary ellipse regions are then calculated by application of Boolean algebra on the ellipse parts and their remaining […]

Ver mais

arXiv:2512.23075v4 Announce Type: replace-cross Abstract: Policy gradient methods for Large Language Models optimize a policy $pi_theta$ via a surrogate objective computed from samples of a rollout policy $pi_{text{roll}}$. However, modern LLM-RL pipelines suffer from unavoidable implementation divergences — backend discrepancies, Mixture-of-Experts routing discontinuities, and distributed training staleness — causing off-policy mismatch ($pi_{text{roll}} neq pi_theta$) and approximation errors between the surrogate and the true objective. We demonstrate that classical trust region bounds on this error scale as $O(T^2)$ with […]

Ver mais

arXiv:2601.02404v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains, including software development, education, and technical assistance. Among these, software development is one of the key areas where LLMs are increasingly adopted. However, when hardware constraints are considered-for instance, in physical computing, where software must interact with and control physical hardware -their effectiveness has not been fully explored. To address this gap, we introduce textsc{PCEval} (Physical Computing Evaluation), the first benchmark in […]

Ver mais

arXiv:2604.09717v1 Announce Type: new Abstract: Character recognition is the fundamental part of an optical character recognition (OCR) system. Word recognition, sentence transcription, document digitization, and language processing are some of the higher-order activities that can be done accurately through character recognition. Nonetheless, recognizing handwritten Bangla characters is not an easy task because they are written in different styles with inconsistent stroke patterns and a high degree of visual character resemblance. The datasets available are usually limited in intra-class […]

Ver mais

Introduction Disclaimer: This article is a cross post from Pytorch Medium Blog Post. One of the most exciting advancements, that has pushed the frontier of the Artificial Intelligence (AI) in recent years, is Deep Reinforcement Learning (DRL). DRL belongs to the family of machine learning algorithms. It assumes that intelligent machines can learn from their actions similar to the way humans learn from experience. Over the recent years we could witness some impressive real-world applications of DRL. The […]

Ver mais