arXiv preprints from January 1, 2026 through July 28, 2026 — 14:26:03 EST
High-level synthesis (HLS) is a powerful tool for developing efficient hardware accelerators that rely on specialized memory systems to achieve sufficient on-chip data reuse and off-chip bandwidth utilization. However, even with HLS, designing such systems still requires careful manual tuning, as automatic optimizations provided by...
Data scarcity and unreliable self-reporting -- such as concealment or exaggeration -- pose fundamental challenges to psychiatric intake and assessment. We propose a multi-agent synthesis framework that explicitly models patient deception to generate high-fidelity, publicly releasable synthetic psychiatric intake records. Starting from...
User simulators serve as the critical interactive environment for agent post-training, and an ideal user simulator generalizes across domains and proactively engages in negotiation by challenging or bargaining. However, current methods exhibit two issues. They rely on static and context-unaware profiles, necessitating extensive manual...
We study branching random walk on $\mathbb{Z}$ in a bounded i.i.d. random environment. For this process, we prove that, for almost every realization of the environment, the distributions of the maximally displaced particle (re-centered around their medians) are tight. This extends the result of arXiv:2408.01555 , where tightness was...
Reconstructing natural visual scenes from neural activity is a key challenge in neuroscience and computer vision. We present SpikeVAEDiff, a novel two-stage framework that combines a Very Deep Variational Autoencoder (VDVAE) and the Versatile Diffusion model to generate high-resolution and semantically meaningful image reconstructions...
Despite significant progress in autoregressive image generation, inference remains slow due to the sequential nature of AR models and the ambiguity of image tokens, even when using speculative decoding. Recent works attempt to address this with relaxed speculative decoding but lack theoretical grounding. In this paper, we establish...
This paper addresses the problem of affordance grounding from RGBD images of an object, which aims to localize surface regions corresponding to a text query that describes an action on the object. While existing methods predict affordance regions only on visible surfaces, we propose Affostruction, a generative framework that...
We propose a variational formulation of an inverse problem in continuous-time stochastic control, aimed at identifying control costs consistent with a given distribution over trajectories. The formulation is based on minimizing the suboptimality gap of observed behavior. We establish a connection between the inverse problem and a...
White-Light Imaging (WLI) is the standard for endoscopic cancer screening, but Narrow-Band Imaging (NBI) offers superior diagnostic details. A key challenge is transferring knowledge from NBI to enhance WLI-only models, yet existing methods are critically hampered by their reliance on paired NBI-WLI images of the same lesion, a costly...
Recent progress in large language models and multimodal interaction has made it possible to develop AI companions that can have fluent and emotionally expressive conversations. However, many of these systems have problems keeping users satisfied and engaged over long periods. This paper argues that these problems do not come mainly...
Purpose: Myocardium segmentation in echocardiography videos is a challenging task due to low contrast, noise, and anatomical variability. Traditional deep learning models either process frames independently, ignoring temporal information, or rely on memory-based feature propagation, which accumulates error over time. Methods: We...
In this paper we develop a data-driven approach for marking nonblocking supervisory control of discrete-event systems (DES). We consider a setup in which models of DES to be controlled are unknown, but a set of data concerning the behaviors of DES is available. We ask the question: Under what conditions of the available data set can a...
In this paper the Mikhailov model is discretized by means of the Cauchy matrix approach. A pair of discrete Miura transformations are constructed. The discrete Mikhailov model is a coupled system, in which one equation comes from the compatibility of the two Miura transformations, the other is transformed from the discrete negative...
This paper proposes a novel paradigm centered on Artificial Intelligence (AI)-empowered propagation channel prediction to address the limitations of traditional channel modeling. We present a comprehensive framework that deeply integrates heterogeneous environmental data and physical propagation knowledge into AI models for...
This paper provides a quantitative analysis of the rightmost eigenvalue for a chiral non-Hermitian random Dirac matrix in the maximally non-Hermitian regime ($τ=0$). Let $(σ_i)_{1\le i\le n}$ be the eigenvalues with positive real part. We define the normalization constants \[ s_n = \frac{4n(n+v)}{2n+v}, \qquad γ_n = \frac{1}{2}\log...
Nonlocality is a peculiar nature of quanta and it stands as an important quantum resource in application. Yet mere linear property of it, viz. the first order in moment, has been explored through various inequalities. Noticing the vast higher-order regime unexplored, in this study we investigate the higher-order quantum correlations...
Let $M$ be a $d$-dimensional complete Riemannian manifold and let $π: SM \to M$ denote the canonical projection from the unit tangent bundle. We prove that if $E \subset SM$ is a set that invariant under the geodesic flow with Hausdorff dimension $\dim_{\mathcal{H}} E \ge 2(k-1)+1 +β$ for some integer $1 \le k \le d-1$ and some $β\in...
Polynomials and elements over finite fields exhibit closely related algebraic structures, and many properties defined for elements extend naturally to polynomials. The concepts of order and $\mathbb{F}_q$-Order for elements have been extensively studied. In this paper, we investigate several properties of $r$-primitive and $k$-normal...
We introduce A.X K1, a 519B-parameter Mixture-of-Experts (MoE) language model trained from scratch. Our design leverages scaling laws to optimize training configurations and vocabulary size under fixed computational budgets. A.X K1 is pre-trained on a corpus of approximately 10T tokens, curated by a multi-stage data processing...
Ultracompact dwarf galaxies (UCDs) are thought to be remnants of stripped galactic nuclei, among which a handful are known to host a central supermassive black hole (SMBH). As in stripped nuclear star clusters, the SMBHs in UCDs may be fed by stellar winds from old stellar populations, in the absence of substantial gas reservoirs and...
We study surplus division in network constrained bilateral matching markets with transferable utility. We introduce a new solution concept, the credible bargaining solution, which refines stability by requiring that, for each matched pair of buyer and seller, surplus be divided according to the Nash bargaining solution with respect to...
In this paper we extend the notion of $\varphi$-mixing to set-valued random sequences that take values in the family of closed subsets of a Banach space. Several strong laws of large numbers for such $\varphi$-mixing sequences are stated and proved. Illustrative examples show that the hypotheses of the theorems are both natural and sharp.
In two-sampling testing, one observes two independent sequences of independent and identically distributed random variables distributed according to the distributions $P_1$ and $P_2$ and wishes to decide whether $P_1=P_2$ (null hypothesis) or $P_1\neq P_2$ (alternative hypothesis). The Gutman test for this problem compares the...
Large Language Models (LLMs) have been increasingly employed for query expansion. However, their generative nature often undermines performance on complex multi-hop retrieval tasks by introducing irrelevant or noisy information. To address this challenge, we propose DeCoR (Decompose and Compress for Retrieval), a framework grounded in...
Triad magnetometer components change with sensor attitude even when the IGRF total intensity target stays invariant. NavFormer forecasts this invariant target with rotation invariant scalar features and a Canonical SPD module that stabilizes the spectrum of window level second moments of the triads without sign discontinuities. The...