arXiv preprints from January 1, 2026 through July 21, 2026 — 20:54:05 EST
Large Language Model (LLM) agents are increasingly used in many applications, raising concerns about their safety. While previous work has shown that LLMs can deceive in controlled tasks, less is known about their ability to deceive using natural language in social contexts. In this paper, we study deception in the Social Deduction...
We introduce a physics-informed Generative Adversarial Network framework that recasts quantum resource-state generation as an inverse-design task. By embedding task-specific utility functions into training, the model learns to generate valid two-qubit states optimized for teleportation and entanglement broadcasting. Comparing...
Hallucinations in large vision--language models (LVLMs) often arise when language priors dominate over visual evidence, leading to object misidentification and visually inconsistent descriptions. We address this problem by framing hallucination mitigation as contrastive guidance that steers generation toward visually grounded and...
High-fidelity parking-lot digital twins provide essential priors for path planning, collision checking, and perception validation in Automated Valet Parking (AVP). Yet robot-oriented reconstruction faces a trilemma: sparse forward-facing views cause weak parallax and ill-posed geometry; dynamic occlusions and extreme lighting hinder...
Puzzles have long served as compact and revealing probes of human cognition, isolating abstraction, rule discovery, and systematic reasoning with minimal reliance on prior knowledge. Leveraging these properties, visual puzzles have recently emerged as a powerful diagnostic tool for evaluating the reasoning abilities of Large...
In speech machine learning, neural network models are typically designed by choosing an architecture with fixed layer sizes and structure. These models are then trained to maximize performance on metrics aligned with the task's objective. While the overall architecture is usually guided by prior knowledge of the task, the sizes of...
Coherent detection ghost imaging lidar (CD-GI lidar) integrates ghost imaging with coherent detection, thereby achieving enhanced anti-interference and phase-resolved imaging capability. Here, we propose a bucket-detector-based multi-mode coherent detection scheme for CD-GI lidar, where the reflected multi-mode light fields are...
Agentic AI (AAI), which extends Large Language Models with enhanced reasoning capabilities, has emerged as a promising paradigm for autonomous edge service scheduling. However, user mobility creates highly dynamic service demands in edge networks, and existing service scheduling agents often lack generalization capabilities for new...
We report the third observation of the Seyfert-1.9 active galactic nucleus (AGN) MCG-05-23-16 with the Imaging X-ray Polarimetry Explorer (\textit{IXPE}), together with optical spectro-polarimetry obtained at the Very Large Telescope (VLT), and combined with archival near-ultraviolet, optical and near-infrared polarimetric data. No...
With the advancement of self-supervised learning (SSL), fine-tuning pretrained SSL models for mean opinion score (MOS) prediction has achieved state-of-the-art performance. However, during fine-tuning, these SSL-based MOS prediction models often suffer from catastrophic forgetting of the pretrained knowledge and tend to overfit the...
We present a systematic quantum encoding framework for leptophilic extensions of the Standard Model, tailored to quantum simulation applications on near term and future quantum devices. Focusing on anomaly free $U(1)'_{\ell}$ gauge theories, we show that the leptonic charge structure admits a natural and scalable representation on...
Fairness and privacy are two vital pillars of trustworthy machine learning. Despite extensive research on these individual topics, their relationship has received significantly less attention. In this paper, we utilize an information-theoretic measure Chernoff Information to characterize the fundamental trade-off between fairness,...
Instruction tuning is a standard paradigm for adapting large language models (LLMs), but modern instruction datasets are large, noisy, and redundant, making full-data fine-tuning costly and often unnecessary. Existing data selection methods either build expensive gradient datastores or assign static scores from a weak proxy, largely...
As silicon transistors scale toward future technology nodes, three-dimensional architectures -- including gate-all-around (GAA) nanoribbon and complementary field-effect transistors (CFETs) -- require channel widths in the tens of nanometers to meet density targets. Monolayer transition metal dichalcogenides (TMDs), with their...
Executable SQL generation is typically studied in text-to-SQL settings, where tables are provided as fully linearized textual schemas and contents. While effective, this formulation assumes access to structured text and incurs substantial token overhead, which is misaligned with many real-world scenarios where tables appear as visual...
With the development of artificial intelligence (AI), Agentic AI (AAI) based on large language models (LLMs) is gradually being applied to network management. However, in edge network environments, high user mobility and implicit service intents pose significant challenges to the passive and reactive management of traditional AAI. To...
Identifying protein targets for small molecules, or reverse screening, is essential for understanding drug action, guiding compound repurposing, predicting off-target effects, and elucidating the molecular mechanisms of bioactive compounds. Despite its critical role, reverse screening remains challenging because accurately capturing...
This study aims to investigate the relationship between the spatial-temporal evolution of shock properties and the longitudinal dependence of SEP intensities and spectra. The shock parameters, including the normal speed, oblique angles, compression ratio, and Alfven Mach number, were derived by combining a steady-state solar-wind...
The orbital angular momentum (OAM) of light provides an unbounded set of orthogonal modes for ultrahigh-capacity optical information processing. However, current OAM detection schemes typically rely on light interference or diffraction, which require bulky optical components and pose a major obstacle to on-chip integration. Here, we...
Clinical Decision Support Systems (CDSSs) provide reasoning and inquiry guidance for physicians, yet they face notable challenges, including high maintenance costs and low generalization capability. Recently, Large Language Models (LLMs) have been widely adopted in healthcare due to their extensive knowledge reserves, retrieval, and...
Law enforcement authorities are increasingly interested in 3D modelling for virtual crime scene reconstruction, enabling offline analysis without the cost and contamination risk of on-site investigation. Past work has demonstrated spatial relationships through static modelling but validating the sequence of events in dynamic scenarios...
The inherent non-convexity of poriferous surfaces typically entraps agents in local minima and complicates workload distribution. To resolve this, we propose a distributed diffeomorphic coverage control framework for the multi-agent system (MAS) in such surfaces. First, we establish a distributed poly-annulus conformal mapping that...
Existing dynamic Theory of Mind (ToM) benchmarks mostly place language models in a passive role: the model reads a sequence of connected scenarios and reports what people believe, feel, intend, and do as these states change. In real social interaction, ToM is also used for action: a speaker plans what to say in order to shift another...
We study optimal dynamic persuasion in a bandit experimentation model where a principal, unlike in standard settings, has a single-peaked preference over the agent's stopping time. This non-monotonic preference arises because maximizing the agent's effort is not always in the principal's best interest, as it may lead to a dead end....
Agentic artificial intelligence (AI) is an AI paradigm that can perceive the environment, reason over observations, and execute actions to achieve specific goals. Task-oriented communication supports agentic AI by transmitting only the task-related information instead of full raw data in order to reduce the bandwidth requirement. In...