arXiv preprints from January 1, 2026 through September 25, 2026 — 12:22:36 EST
Long-term memory is a critical capability for multimodal large language model (MLLM) agents, particularly in conversational settings where information accumulates and evolves over time. However, existing benchmarks either evaluate multi-session memory in text-only conversations or assess multimodal understanding within localized...
Open-source scientific software is abundant, yet most tools remain difficult to compile, configure, and reuse, sustaining a small-workshop mode of scientific computing. This deployment bottleneck limits reproducibility, large-scale evaluation, and the practical integration of scientific tools into modern AI-for-Science (AI4S) and...
Code translation across multiple programming languages is essential yet challenging due to two vital obstacles: scarcity of parallel data paired with executable test oracles, and optimization imbalance when handling diverse language pairs. We propose BootTrans, a bootstrapping method that resolves both obstacles. Its key idea is to...
In complex Unmanned Aerial Vehicle (UAV) networks, UAVs can establish dynamic and heterogeneous links with one another for various purposes, such as communication coverage, collective sensing, and task collaboration. These interactions give rise to dynamic multiplex UAV networks, where each layer represents a distinct type of...
Large Language Models (LLMs) are increasingly deployed in sensitive domains such as healthcare, finance, and law, yet their integration raises pressing concerns around trust, accountability, and reliability. This paper explores adaptive trust metrics for multi LLM ecosystems, proposing a framework for quantifying and improving model...
A major challenge for the operation of large language models (LLMs) is how to predict whether a specific LLM will produce sufficiently high-quality output for a given query. Existing approaches rely on external classifiers, most commonly BERT based models, which suffer from limited context windows, constrained representational...
Point cloud segmentation is critical for 3D scene understanding. However, sparse and irregular point distributions provide limited appearance evidence, making geometry-only features insufficient to distinguish objects with similar shapes but distinct appearances e.g., color, texture, and material. We propose Gaussian-to-Point (G2P),...
We study continual skill acquisition in open-ended embodied environments where an agent must construct, refine, and reuse an expanding library of executable skills. We introduce the Programmatic Skill Network (PSN), a framework in which skills are executable symbolic programs forming a compositional network that evolves through...
This paper critically examines the 2022 Medibank health insurance data breach, which exposed sensitive medical records of 9.7 million individuals due to unencrypted storage, centralized access, and the absence of privacy-preserving analytics. To address these vulnerabilities, we propose an entropy-aware differential privacy (DP)...
We present a novel system for real-time tracking of facial expressions using egocentric views captured from a set of infrared cameras embedded in a virtual reality (VR) headset. Our technology facilitates any user to accurately drive the facial expressions of virtual characters in a non-intrusive manner and without the need of a...
Procurement and inventory planning is governed not only by demand forecasts and bills of materials (BOMs), but also by operational terms in contracts and supplier documents (e.g., MOQs, lead times, price tiers, allocation caps, substitution approvals). LLM-based extraction can speed up structuring these terms, but extraction-only or...
Recent large reasoning models (LRMs) have made substantial progress in complex reasoning tasks, yet they often generate lengthy reasoning paths for every query, incurring unnecessary computation and latency. Existing speed-up approaches typically rely on retraining the model or designing sophisticated prompting, which are either...
Supervised Fine-Tuning (SFT) is a standard approach for injecting domain knowledge into Large Language Models (LLMs). However, relying on validation perplexity to monitor training is often insufficient, as it confounds stylistic mimicry with genuine factual internalization. To address this, we introduce the Knowledge Retention (KR)...
The emergence of large-scale quantum computing threatens widely deployed public-key cryptographic systems, creating an urgent need for enterprise-level methods to assess post-quantum (PQ) readiness. While PQ standards are under development, organizations lack scalable and quantitative frameworks for measuring cryptographic exposure...
Large Vision-Language Models (LVLMs) demonstrate significant progress in multimodal understanding and reasoning, yet object hallucination remains a critical challenge. While existing research focuses on mitigating language priors or high-level statistical biases, they often overlook the internal complexities of the visual encoding...
Tasks in the aerospace industry heavily rely on searching and reusing large volumes of technical documents, yet there is no public information retrieval (IR) benchmark that reflects the terminology- and query-intent characteristics of this domain. To address this gap, this paper proposes the STELLA (Self-Reflective TErminoLogy-Aware...
Automatic prompt optimization reduces manual prompt engineering, but relies on task performance measured on a small, often randomly sampled evaluation subset as its main source of feedback signal. Despite this, how to select that evaluation subset is usually treated as an implementation detail. We study evaluation subset selection for...
This paper introduces a class of Hermitian LCD $2$-quasi-abelian codes over finite fields and presents a comprehensive enumeration of these codes in which relative minimum weights are small. We show that such codes are asymptotically good over finite fields. Furthermore, we extend our analysis to finite chain rings by characterizing...
Referring remote sensing image segmentation aims to localize specific targets described by natural language within complex overhead imagery. However, due to extreme scale variations, dense similar distractors, and intricate boundary structures, the reliability of cross-modal alignment exhibits significant \textbf{spatial...
A subspace code is a nonempty collection of subspaces of the vector space $\mathbb{F}_q^{n}$. A pair of linear codes is called a linear complementary pair (in short LCP) of codes if their intersection is trivial and the sum of their dimensions equals the dimension of the ambient space. In this paper, we introduce the concept of LCPs...
Deploying models, especially large language models (LLMs), is becoming increasingly attractive to a broader user base, including those without specialized expertise. However, due to the resource constraints of certain hardware, maintaining high accuracy with larger model while meeting the hardware requirements remains a significant...
Cultural awareness in language models is the capacity to understand and adapt to diverse cultural contexts. However, most existing approaches treat culture as static background knowledge, overlooking its dynamic and evolving nature. This limitation reduces their reliability in downstream tasks that demand genuine cultural sensitivity....
Large foundation models (LFMs) transform healthcare AI in prevention, diagnostics, and treatment. However, whether LFMs can provide truly personalized treatment recommendations remains an open question. Recent research has revealed multiple challenges for personalization, including the fundamental generalizability paradox: models...
Hate speech detection models rely on surface-level lexical features, increasing vulnerability to spurious correlations and limiting robustness, cultural contextualization, and interpretability. We propose Supervised Moral Rationale Attention (SMRA), the first self-explaining hate speech detection framework to incorporate moral...
Recent years have witnessed success of sequential modeling, generative recommender, and large language model for recommendation. Though the scaling law has been validated for sequential models, it showed inefficiency in computational capacity when considering real-world applications like recommendation, due to the...