arXiv preprints from January 1, 2026 through September 23, 2026 — 09:32:45 EST
Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content, restricting their safe deployment. While traditional methods (e.g., alignment) adjust output preferences, they fail to eliminate underlying toxic regions in parameters, leaving models vulnerable to adversarial attacks....
The advent of transformer-based language models has reshaped how AI systems process and generate text. In software engineering (SE), these models now support diverse activities, accelerating automation and decision-making. Yet, evidence shows that these models can reproduce or amplify social biases, raising fairness concerns. Recent...
Altermagnet-superconductor heterostructures have been shown, in principle, to provide a route towards realising topological superconductivity, and therefore host topologically protected boundary states. In this work we demonstrate that the topological states observed are dependent on the structure of the underlying lattice. By...
Prostate cancer is one of the most common types of cancer in men. Its diagnosis by biopsy requires a high level of expertise and precision from the surgeon, so the results are highly operator-dependent. The aim of this work is to develop a robotic system for assisted ultrasound (US) examination of the prostate, a prebiopsy step that...
The response of the Fermi energy to external perturbations governs key physical observables at metallic interfaces. Although this response admits a local formulation in terms of the Fukui function, its evaluation has traditionally been limited by inherent approximations, fundamentally rooted in the difficulty of adding a finite charge...
Magnetrons are widely used as a high-efficiency, large-power, and low-cost microwave source. This article proposes a method to improve the magnetron output characteristics based on regulating its anode current by a novel active distortion eliminator. It takes advantage of the constant current state of MOSFETs to suppress the anode...
A comprehensive study of the $J/ψ$ energy correlator as a probe of non-perturbative hadronization in color-octet $c\bar{c}$ production is performed. The energy correlator measures the energy flow as a function of the angular distance ($χ$) from the identified $J/ψ$ meson. Using the PYTHIA 8 Monte Carlo event generator, the correlator...
Instant-messaging human social chat typically progresses through a sequence of short messages. Existing step-by-step AI chatting systems typically split a one-shot generation into multiple messages and send them sequentially, but they lack an active waiting mechanism and exhibit unnatural message pacing. In order to address these...
High-fidelity agent initialization is crucial for credible Agent-Based Modeling across diverse domains. A robust framework should be Topic-Adaptive, capturing macro-level joint distributions while ensuring micro-level individual rationality. Existing approaches fall into two categories: static data-based retrieval methods that fail to...
We propose digital signal processing techniques for nonlinearity mitigation in high power optical amplifiers used in satellite communications. The acceptable link loss increases by 6dB with negligible complexity.
We investigate the capabilities and scalability of Large Language Models (LLMs) in optimization modeling, a domain requiring structured reasoning and precise formulation. To this end, we introduce OPT-ENGINE, an extensible benchmark framework with quantifiable and controllable complexity. OPT-ENGINE spans ten canonical Operations...
Estimating the persuasiveness of messages is critical in various applications, from recommender systems to safety assessment of LLMs. While it is imperative to consider the target persuadee's characteristics, such as their values, experiences, and reasoning styles, there is currently no established systematic framework to optimize...
Existing traffic simulation frameworks for autonomous vehicles typically rely on imitation learning or game-theoretic approaches that solve for Nash or coarse correlated equilibria, implicitly assuming perfectly rational agents. However, human drivers exhibit bounded rationality, making approximately optimal decisions under cognitive...
A new geometric shaping technique, referred to as coset shaping, is proposed and analyzed for coded QAM and PAM signaling. This method can be applied to both information and parity bits without introducing additional complexity. It is shown that, as the error-correcting code length and the modulation order grow, the gap to capacity of...
Engaging learners in dialogue around controversial issues is essential for examining diverse values and perspectives in pluralistic societies. While prior research has identified productive discussion moves mainly in STEM-oriented contexts, less is known about what constitutes productive discussion in ethical and value-laden...
Wi-Fi fingerprinting remains one of the most practical solutions for indoor positioning, however, its performance is often limited by the size and heterogeneity of fingerprint datasets, strong Received Signal Strength Indicator variability, and the ambiguity introduced in large and multi-floor environments. These factors significantly...
High-dimensional dense embeddings have become central to modern Information Retrieval, but many dimensions are noisy or redundant. Recently proposed DIME (Dimension IMportance Estimation), provides query-dependent scores to identify informative components of embeddings. DIME relies on a costly grid search to select a priori a...
Recent advancements in single-cell multi-omics, particularly RNA-seq, have provided profound insights into cellular heterogeneity and gene regulation. While pre-trained language model (PLM) paradigm based single-cell foundation models have shown promise, they remain constrained by insufficient integration of in-depth individual...
We reveal that transformers trained in an autoregressive manner naturally encode time-delayed causal structures in their learned representations. When predicting future values in multivariate time series, the gradient sensitivities of transformer outputs with respect to past inputs directly recover the underlying causal graph, without...
The observational tension regarding the value of the Hubble constant ($H_0$) has motivated the exploration of alternative cosmological scenarios, including Interacting Dark Energy models. However, the majority of IDE models studied in the literature rely on phenomenological interaction terms proportional to the Hubble parameter (e.g.,...
Nickel-titanium that has an austenite to martensite phase transition has been studied extensively in the past as a shape memory alloy, but a lot remains to be learned from such phase transitions. However, single crystals are needed for a detailed characterization of the emerging phase transition. In order to produce NiTi single...
We analyze the problem of identifying large cliques in graphs that are affected by adversarial uncertainty. More specifically, we consider a new formulation, namely the adversarial maximum clique problem, which extends the classical maximum-clique problem to graphs with edges strategically perturbed by an adversary. The proposed...
Chirality, the absence of mirror symmetry, is a fundamental molecular property with far-reaching consequences from chemistry to biology. Yet enantiosensitive optical responses are very weak. Here, we introduce a theoretical framework in which a chiral optical cavity under strong coupling directly lifts the degeneracy of opposite...
Harnack inequalities are useful qualitative tools for understanding the properties of partial differential equations. Originally discovered as a property of harmonic functions, Harnack inequalities have since been studied for solutions of wider classes of elliptic and parabolic problems. In this monograph, we take particular interest...
As multilingual large language models become more widely used, ensuring their safety and fairness across diverse linguistic contexts presents unique challenges. While existing research on machine unlearning has primarily focused on monolingual settings, typically English, multilingual environments introduce additional complexities due...