Dastawez Jahan-Numa

arXiv:2601.19791v4 Announce Type: replace Abstract: We study grokking, the onset of generalization long after overfitting, in a classical ridge regression setting. We prove end-to-end grokking results for learning over-p…

arXiv:2602.01086v3 Announce Type: replace Abstract: Generative AI can encode substantial medical knowledge, but patient-specific answers remain constrained by the context supplied at inference time. Electronic health rec…

arXiv:2602.04043v2 Announce Type: replace Abstract: The growing demand for rapid and scalable 3D asset creation has driven interest in feed-forward 3D reconstruction methods, with 3D Gaussian Splatting (3DGS) emerging as…

arXiv:2602.05786v3 Announce Type: replace Abstract: Tree-boosting is a widely used machine learning technique for tabular data. However, its out-of-sample accuracy is critically dependent on multiple hyperparameters. In …

arXiv:2602.08639v4 Announce Type: replace Abstract: The Cahn-Hilliard-Navier-Stokes (CHNS) system utilizes a diffusive phase-field for interface tracking of multi-phase fluid flows. Recently structure preserving methods …

arXiv:2602.09730v3 Announce Type: replace Abstract: Recent advances in imaging technologies, deep learning and numerical performance have enabled non-invasive detailed analysis of artworks, supporting their documentation…

arXiv:2602.12429v2 Announce Type: replace Abstract: Foundation models have achieved remarkable success, yet their growing parameter counts pose significant computational and memory challenges. Low-rank factorization offe…

arXiv:2602.13061v2 Announce Type: replace Abstract: The ability of Flow Matching (FM) to model complex conditional distributions has established it as the state-of-the-art for prediction tasks (e.g., robotics, weather fo…

arXiv:2602.14419v2 Announce Type: replace Abstract: This paper reformulates Transformer/Attention mechanisms in Large Language Models (LLMs) through measure theory and frequency analysis, theoretically demonstrating that…

arXiv:2602.15280v2 Announce Type: replace Abstract: Combining conversational AI with refreshable tactile displays (RTDs) offers significant potential for creating accessible data visualization for people who are blind or…

arXiv:2602.15341v3 Announce Type: replace Abstract: We study monotonicity testing of real-valued functions on directed acyclic graphs (DAGs) with $n$ vertices. Let $m$ and $\ell$ be the numbers of edges in the transitive…

arXiv:2602.16312v4 Announce Type: replace Abstract: This work presents a novel agglomeration-based multilevel preconditioner designed to accelerate the convergence of iterative solvers for linear systems arising from the…

arXiv:2602.18645v3 Announce Type: replace Abstract: Time series reasoning tasks often start with a natural language question and require targeted analysis of a time series. Evidence may span the full series or appear in …

arXiv:2602.19946v5 Announce Type: replace Abstract: Recent text-to-image (T2I) diffusion models produce visually stunning images and demonstrate excellent prompt following. But do they perform well as synthetic vision da…

arXiv:2602.22568v2 Announce Type: replace Abstract: Deep multi-view clustering has achieved remarkable progress but remains vulnerable to complex noise in real-world applications. Existing noisy robust methods predominan…

arXiv:2602.22809v3 Announce Type: replace Abstract: With the recent fast development of generative models, instruction-based image editing has shown great potential in generating high-quality images. However, the quality…

arXiv:2602.23053v2 Announce Type: replace Abstract: Field robotics research in maritime and space domains is constrained by a persistent gap between low-cost, low-fidelity simulation and costly offshore experimentation. …

arXiv:2603.01140v2 Announce Type: replace Abstract: Conventional image denoising models often inadvertently learn spurious correlations between environmental factors and noise patterns. Moreover, due to high-frequency am…

arXiv:2603.03083v2 Announce Type: replace Abstract: Craig's Interpolation theorem has a wide range of applications, from mathematical logic to computer science. Proof-theoretic techniques for establishing interpolation u…

arXiv:2603.05353v3 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) for long-context question answering is bottlenecked by inference-time prefilling over large retrieved contexts. A common strategy i…