arXiv preprints from January 1, 2026 through September 8, 2026 — 04:15:31 EST
Psychiatric narratives encode patient identity not only through explicit identifiers but also through idiosyncratic life events embedded in their clinical structure. Existing de-identification approaches, including PHI masking and LLM-based synthetic rewriting, operate at the text level and offer limited control over which semantic...
The efficacy of multimodal learning in remote sensing (RS) is severely undermined by missing modalities. The challenge is exacerbated by the RS highly heterogeneous data and huge scale variation. Consequently, paradigms proven effective in other domains often fail when confronted with these unique data characteristics. Conventional...
This study examines how the fate of a perpetrator in a public mass shooting influences the fate of subsequent perpetrators. Using data from 1966 to 2024, we classify incidents according to whether the perpetrator died at the scene or survived the attack. Using a bivariate Hawkes process, we quantify the cross-excitation effect, which...
Two-player games on finite graphs provide a rigorous foundation for modeling the strategic interaction between reactive systems and their environment. While concurrent game semantics naturally capture the synchronous interactions characteristic of many cyber-physical systems (CPS), their adoption in CPS design remains limited....
Vision-Language-Action (VLA) models are increasingly deployed in safety-critical robotic applications, yet their security vulnerabilities remain underexplored. We identify a fundamental security flaw in modern VLA systems: the combination of action chunking and delta pose representations creates an intra-chunk visual open-loop. This...
Event vision sensors (neuromorphic cameras) output sparse, asynchronous ON/OFF events triggered by log-intensity threshold crossings, enabling microsecond-scale sensing with high dynamic range and low data bandwidth. As a nonlinear system, this event representation does not readily integrate with the linear forward models that...
While RPCs form the bedrock of systems stacks, we posit that IoT device collections in smart spaces like homes, warehouses, and office buildings--which are all "user-facing"--require a more expressive abstraction. Orthogonal to prior work, which improved the reliability of IoT communication, our work focuses on improving the...
We study the online traveling repairperson problem on a line within the recently proposed learning-augmented framework, which provides predictions on the requests to be served via machine learning. In the original model (with no predictions), there is a stream of requests released over time along the line. The goal is to minimize the...
Large-scale data has fuelled the success of frontier artificial intelligence (AI) models over the past decade. This expansion has relied on sustained efforts by large technology corporations to aggregate and curate internet-scale datasets. In this work, we examine the environmental, social, and economic costs of large-scale data in AI...
Recent advances, such as RegretNet, ALGnet, RegretFormer and CITransNet, use deep learning to approximate optimal multi item auctions by relaxing incentive compatibility (IC) and measuring its violation via ex post regret. However, the true accuracy of these regret estimates remains unclear. Computing exact regret is computationally...
News consumption on social media has become ubiquitous, yet how different forms of engagement shape psychosocial outcomes remains unclear. To address this gap, we leveraged a large-scale dataset of ~26M posts and ~45M comments on the BlueSky platform, and conducted a quasi-experimental study, matching 81,345 Treated users exposed to...
Radio Access Network (RAN) sharing, which often also includes spectrum sharing, is a strategic cooperative agreement among two or more mobile operators, where one operator may use another's RAN infrastructure to provide mobile services to its users. By mutually sharing physical sites, radio elements, licensed spectrum and other parts...
Linguistic expressions of emotions such as depression, anxiety, and trauma-related states are pervasive in clinical notes, counseling dialogues, and online mental health communities, and accurate recognition of these emotions is essential for clinical triage, risk assessment, and timely intervention. Although large language models...
Peer agents can supplement real-time collaborative learning in asynchronous online courses. Constructive Controversy (CC) theory suggests that humans deepen their understanding of a topic by confronting and resolving controversies. This study explores whether CC's benefits apply to LLM-based peer agents, focusing on the impact of...
We study perfect error-correcting codes in $\mathbb{Z}^n$ for the symmetric limited-magnitude error channel, where at most $e$ coordinates of an integer vector may be altered by a value whose magnitude is at most $s$. Geometrically, such codes correspond to tilings of $\mathbb{Z}^n$ by the symmetric limited-magnitude error ball...
The reliability of data-driven applications in electric vehicle (EV) infrastructure, such as charging demand forecasting, hinges on the availability of complete, high-quality charging data. However, real-world EV datasets are often plagued by missing records, and existing imputation methods are ill-equipped for the complex, multimodal...
The Muon optimizer, a matrix-structured algorithm that leverages spectral orthogonalization of gradients, is a milestone in the pretraining of large language models. However, the underlying mechanisms of Muon -- particularly the role of gradient orthogonalization -- remain poorly understood, with very few works providing end-to-end...
We investigate visual reasoning limitations of both multimodal large language models (MLLMs) and image generation models (IGMs) by creating a novel benchmark to systematically compare failure modes across image-to-text and text-to-image tasks, enabling cross-modal evaluation of visual understanding. Despite rapid growth in machine...
The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alignment and guardrails mitigate common misuse, they remain vulnerable to automated jailbreaking methods such as GCG, PEZ, and GBDA, which...
Efficiently serving Large Language Models (LLMs) with persistent Prefix Key-Value (KV) Cache is critical for applications like conversational search and multi-turn dialogue. Serving a request requires loading the pre-computed prefix KV cache and generating the first token, defined as the Re-Prefill Phase. Offloading this shared prefix...
Large language models (LLMs) are increasingly deployed over knowledge bases for efficient knowledge retrieval and question answering. However, LLMs can inadvertently answer beyond a user's permission scope, leaking sensitive content, thus making it difficult to deploy knowledge-base QA under fine-grained access control requirements....
This paper presents PRIMAL, a processing-in-memory (PIM) based large language model (LLM) inference accelerator with low-rank adaptation (LoRA). PRIMAL integrates heterogeneous PIM processing elements (PEs), interconnected by 2D-mesh inter-PE computational network (IPCN). A novel SRAM reprogramming and power gating (SRPG) scheme...
Iterative code generation with Large Language Models (LLMs) can be viewed as an optimization process guided by textual feedback. However, existing LLM self-correction methods predominantly operate in a stateless, trial-and-error manner akin to first-order search, failing to leverage past problem-solving experiences. To bridge this...
Large vision-language models (LVLMs) are typically trained using autoregressive language modeling objectives, which align visual representations with linguistic space. While effective for multimodal reasoning, this alignment can weaken vision-centric capabilities, causing LVLMs to underperform their base vision encoders on tasks such...
Maritime communication is becoming a vital component of 6G networks, driven by the rapid expansion of the maritime economy. However, existing technologies face critical challenges in signal coverage, availability, and robustness, especially under harsh sea conditions. This paper proposes a novel framework for the maritime...