April 2026 arXiv papers — page 122

Yiyu Qian, Liyuan Zhao, Tim Miller

Monte-Carlo Tree Search (MCTS) is a fundamental sampling-based search algorithm widely used for online planning in sequential decision-making domains. Despite its success in driving recent advances in artificial intelligence, understanding the behavior of MCTS agents remains a challenge for both developers and users. This difficulty stems from the complex se

Cahit Dede, Kalpesh M. Popat

For a given graph \( G \), let \( G^{(j)} \) denote the graph obtained by the deletion of vertex \( v_j \) from \( G \). The difference \( \mathscr{E}(G) - \mathscr{E}(G^{(j)}) \) quantifies the change in the energy of \( G \) upon the removal of \( v_j \), termed as the local energy of \( G \) at vertex $v_j$, as defined by Espinal and Rada in 2024. The loc

Fan Yang, Binyan Xu, Di Tang, Kehuan Zhang

Provenance-based intrusion detection has emerged as a promising approach for analyzing complex attack behaviors through system-level provenance graphs. However, existing defense methods face an inherent granularity limitation. Node-centric detectors, which evaluate anomalies using entities' attributes and local structural patterns, may misclassify benign beh

Qianqian Xie, Qingheng Xiong, He Zhu, Tiantian Xia

Deep Research Agents (DRAs) aim to solve complex, long-horizon research tasks involving planning, retrieval, multimodal understanding, and report generation, yet their evaluation remains challenging due to dynamic web environments and ambiguous task definitions. We propose DR$^{3}$-Eval, a realistic and reproducible benchmark for evaluating deep research age

Saif Mahmoud

Speculative decoding accelerates large language model (LLM) inference. It uses a small draft model to propose a tree of future tokens. A larger target model then verifies these tokens in a single batched forward pass. Despite the growing body of work on speculative methods, the degree to which the cognitive characteristics of a task affect acceptance probabi

Fabio Frommer, Tobias Kuna, Dimitrios Tsagkarogiannis

Given a classical gas described by the truncated correlation functions of all orders, we prove convergence of an expansion of the pair interaction part of the (unknown) potential in terms of the truncated correlation functions of all orders, at infinite volume.

Shimul Kanti Nath, Sanjoy Kumar Nandi, Xiao Sun, Sujan Kumar Das

Electroforming of metal-oxide-metal memristors is generally attributed to the creation of oxygen-vacancy filaments within the oxide, with noble metal electrodes such as Pt and Au remaining chemically inert. Here, we demonstrate that electroforming and subsequent operation of Pt/NbOx/Nb2O5/Pt devices can induce an unexpected and highly correlated redistributi

Johannes Kübel, Henrik Krauss, Jinjie Li, Moju Zhao

Data-driven Model Predictive Control (MPC) has lately been the core research subject in the field of control theory. The combination of an optimal control framework with deep learning paradigms opens up the possibility to accurately track control tasks without the need for complex analytical models. However, the system dynamics are often nuanced and the neur

Minati De, Satyam Singh

In the classical online model, the maximum independent set problem admits an $\Omega(n)$ lower bound on the competitive ratio even for interval graphs, motivating the study of the problem under additional assumptions. We first study the problem on graphs with a bounded independent kissing number $\zeta$, defined as the size of the largest induced star in the

Bhaskar Arya, Kartick C. Sarkar, Shiv K. Sethi

Ionization balance in the intergalactic medium (IGM) is central to the interpretation of quasar absorption spectra, linking observed ionic columns to the underlying gas density, temperature, metallicity, and ionizing radiation field. Because ionization, recombination, and cooling timescales can be comparable to the timescales over which the ultraviolet backg

Peter Connor, Shoichi Fujimori

Utilizing the Weierstrass representation for embedded doubly periodic minimal surfaces with parallel ends, we construct entire singly periodic graphs of spacelike maximal surfaces with isolated cone-like singularities in the Lorentz-Minkowski 3-space.

Cesare Chiosi, Mauro D'Onofrio, Emanuela Chiosi

In the context of the hierarchical formation of galaxies, we investigated the role played by mergers in shaping the scale relations of galaxies, that is the projections of their Fundamental Plane onto the \IeRe, \IeSig, \MRa\ and \Lsig\ planes. To this aim, we developed a simple model of multiple dry mergers among galaxies by suitably combing the formalism a

Yiting Cai, Hongying Lin, Bo Zhou

A signed graph $(G,\sigma)$ is a graph $G$ together with an assignment $\sigma$ of either a positive sign or a negative sign to each edge. A signed graph is unbalanced if it contains a cycle with odd number of negative edges. The spectral radius of a signed graph is the spectral radius of its adjacency matrix, in which for vertices $u,v$, the $(u,v)$-entry i

Binxian Su, Haoye Lou, Shucheng Zhu, Weikang Wang

Large language models (LLMs) are being increasingly used in urban planning, but since gendered space theory highlights how gender hierarchies are embedded in spatial organization, there is concern that LLMs may reproduce or amplify such biases. We introduce SPAGBias - the first systematic framework to evaluate spatial gender bias in LLMs. It combines a taxon

Pan Hao, Rishi Selvakumaran, Jacob Sun, Qianwen Wang

Complex visual interfaces are powerful yet have a steep learning curve, as users must navigate feature-rich visual interfaces while reasoning about domain-specific operations. Existing approaches either deliver assistance through a separate chat-based interaction, or require substantial application-specific engineering to build support natively into each int

Zhiye Yang, Keqin Feng

Golay complementary pair (GCP), first introduced by Golay in 1951, has been extensively studied and widely applied in communication systems. A $q$-ary GCP $\{\mathbf{A},\mathbf{B}\}$ consists of two $q$-ary complex sequences $\mathbf{A}=(A_0,\cdots,A_{M-1})$ and $\mathbf{B}=({B}_0,\cdots,{B}_{M-1})$ of equal length $M$, where $\textit{A}_i,\textit{B}_i\in\{\

Taohe Chen, Yin Xu, Tianyao Ma, Aimin Tang

Affine frequency division multiplexing (AFDM), an emerging multi-carrier modulation scheme, has garnered significant attention due to its resilience to Doppler shifts and capability to achieve full diversity in doubly dispersive channels. However, existing data detection algorithms for AFDM systems face a significant trade-off between computational complexit

Oluwaseun Alo, Ishan Thakkar

We analyze five photonic microring tensor core designs with a common optical power model. The results show that circuit ordering, unary encoding, and homodyne accumulation shape scalability, with the last two offering the strongest path to higher parallelism.

Noor Islam S. Mohammad

Federated learning (FL) enables collaborative intrusion detection without raw data exchange, but conventional FL incurs high communication overhead from full-precision gradient transmission and remains vulnerable to gradient inference attacks. This paper presents EdgeDetect, a communication-efficient and privacy-aware federated IDS for bandwidth-constrained

Jiayin Liu

We study dimensions of sets projected to an $(n-2)$-dimensional family of hyperplanes in $\mathbb{R}^n$ under curvature conditions. Let $n\ge 3$ and $\Sigma \subset S^{n-1}$ be an $(n-2)$-dimensional $C^2$ manifold such that $\Sigma$ has non-vanishing geodesic curvature ($n=3$)/sectional curvature $>1$ ($n \ge 4)$. Let $Z \subset \mathbb{R}^{n}$ be analytic

Jianhao Su, Zhanwei Wu, ShengTing Huang, Weidong Feng

Edge AI model deployment is a multi-stage engineering process involving model conversion, operator compatibility handling, quantization calibration, runtime integration, and accuracy validation. In practice, this workflow is long, failure-prone, and heavily dependent on deployment expertise, particularly when targeting hardware-specific inference runtimes. T

Mingzhu Weng, Gang Wang, Zhihai Wang

Photonic state engineering in waveguide QED is typically based on local light-matter interactions. This limits its control over the spatial structure of bound photonic states. Here, we demonstrate a distinct mechanism arising from the interplay between nonlocal giant-atom coupling and topological band structure. Specifically, we consider giant atoms coupled

Yu. O. Koroleva

A new weighted Hardy-type inequality for functions from the Sobolev space $W_{p}^{1}$ is proved. It is assumed that functions vanish on small alternating pieces of the boundary. The proved inequality generalizes the classical known weighted Hardy-type inequalities.

Alessandra Recalde, Luyu Liu, Xiaojian Zhang, Sangung Park

Hurricanes are causing unprecedented damage to the natural environment, infrastructure, and communities. Understanding evacuation behavior is essential for improving emergency preparedness. Past studies have relied on surveys and interviews, which are prone to recall bias. Additionally, they urge incorporating social vulnerability in evacuation research, emp

Seyedreza Mohseni, Sarvesh Baskar, Edward Raff, Manas Gaur

Code deobfuscation is the task of recovering a readable version of a program while preserving its original behavior. In practice, this often requires days or even months of manual work with complex and expensive analysis tools. In this paper, we explore an alternative approach based on Chain-of-Thought (CoT) prompting, where a large language model is guided

Zonghai Yao, Zhipeng Tang, Chengtao Lin, Xiong Luo

Most medical multimodal benchmarks focus on static tasks such as image question answering, report generation, and plain-language rewriting. Patient education is more demanding: systems must identify relevant evidence across images, show patients where to look, explain findings in accessible language, and handle confusion or distress. Yet most patient educati

David Y. Y. Tan, Kellie Chin, Jingxian Zhang

We present AgentGA, a framework that evolves autonomous code-generation runs by optimizing the agent seed: the task prompt plus optional parent archives that initialize a fresh workspace. The outer loop searches over these reusable starting conditions rather than editing code directly. Each generation launches a fresh autonomous run in an isolated workspace,

Dennis Delali Kwesi Wayo, Chinonso Onah, Leonardo Goliatt, Sven Groppe

We present an architecture-level hardware-to-logical-to-decoder execution stack for hybrid continuous-variable and discrete-variable quantum error correction in LiDMaS+. Provider-native records are normalized into a single decoder IO contract and replayed under fixed controls across MWPM, UF, BP, and neural-MWPM. In a Xanadu case study using fixture inputs a

Mu-Chi Chen, Po-Hsuan Huang, Yu-Hung Kao, Yen-Fu Liu

Recent advances in large language models have improved code generation, but their use in hardware description languages is still limited. Moreover, training data and testbenches for these models are often scarce. This paper presents a workflow that uses multi-agent models to generate testbenches for high-quality fine-tuning data. By automating testbench crea

Junyi Wang, Chi Zhang, Jing Qian, Haifeng Luo

In bandwidth-constrained communication such as satellite and underwater channels, speech must often be transmitted at ultra-low bitrates where intelligibility is the primary objective. At such extreme compression levels, codecs trained with acoustic reconstruction losses tend to allocate bits to perceptual detail, leading to substantial degradation in word e

Ziyong Wu, Xu Xiao, Fuyu Dong, Juhan Kim

The cosmic vorticity field, an essential tracer of nonlinear structure formation, has remained observationally inaccessible because transverse galaxy motions are difficult to measure and analytic models struggle to capture shell-crossing. Here we report an empirical reconstruction of this field by applying an artificial intelligence framework trained on simu

Marco Camurri, Enrico Tomelleri, Matías Mattamala, Sebastián Barbas Laina

Covering one third of Earth's land surface, forests are vital to global biodiversity, climate regulation, and human well-being. In Europe, forests and woodlands reach approximately 40% of land area, and the forestry sector is central to achieving the EU's climate neutrality and biodiversity goals; these emphasize sustainable forest management, increased use

Sizhe Wang, Ziqi Xu, Claire Najjuuko, Charles Alba

Clinical language models (LMs) are increasingly applied to support clinical risk prediction from free-text notes, yet their uncertainty estimates often remain poorly calibrated and clinically unreliable. In this work, we propose Clinical Uncertainty Risk Alignment (CURA), a framework that aligns clinical LM-based risk estimates and uncertainty with both indi

Changzhu Liu, Ruisi He, Haoxiang Zhang, Jiahui Han

Reconfigurable intelligent surface (RIS) has recently been gained attention as an effective technique improving the coverage and performance of communication systems by creating additional communication links. Deployment of RIS is crucial for overcoming signal coverage limitations, especially in high-speed train (HST) scenarios. Considerable research has bee

Zhihao Zhang, Lanzheng Liu, Chen Chen, Huiba Li

IP lookup via Longest Prefix Match (LPM) is critical for packet forwarding. Unfortunately, conventional lookup algorithms are inefficient for IPv6 Forwarding Information Bases (FIBs), which are characterized by a set of long prefixes with diverse lengths. We observe that LPM inherently represents a two-dimensional (2D) search problem over both prefix values

Inseok Jeon, Minhyeok Lee, Seunghoon Lee, Minseok Kang

Video outpainting aims to expand the visible content of a video beyond the original frame boundaries while preserving spatial fidelity and temporal coherence across frames. Existing methods primarily rely on large-scale generative models, such as diffusion models. However, generationbased approaches suffer from implicit temporal modeling and limited spatial

Yu-Ting Lin, Hsin-Po Wang

Recently, Abo Khamis et al. showed how to upper bound the size of a join of multiple tables, a problem essential to query optimization in database theory. They unified earlier works by the following information-theoretical framework. 1. Let $(X_1,..., X_n)$ be a row selected from the join uniformly at random. 2. The size of the join is now $\exp(H(X_1,..., X

Chen Wang, Lai Wei, Yanzhi Zhang, Chenyang Shao

Recent advances in reinforcement learning (RL) have improved the reasoning capabilities of large language models (LLMs) and vision-language models (VLMs). However, the widely used Group Relative Policy Optimization (GRPO) consistently suffers from entropy collapse, causing the policy to converge prematurely and lose diversity. Existing exploration methods in

Anusree M, Akhila Henry, Pramod P Nair

Convolutional neural networks (CNNs) often exhibit poor generalisation in limited training data scenarios due to overfitting and insufficient feature diversity. In this work, a simple and effective chaos-based feature transformation is proposed to enhance CNN performance without increasing model complexity. The method applies nonlinear transformations using

Seyun Bae, Seokhan Lee, Eunho Yang

The inability to filter out in advance all potentially problematic data from the pre-training of large language models has given rise to the need for methods for unlearning specific pieces of knowledge after training. Existing techniques overlook the need for continuous and immediate action, causing them to suffer from degraded utility as updates accumulate

Weiwei Zhuang, Wangze Xie, Qi Zhang, Xia Du

Adversarial attacks pose a severe threat to the reliability of deep learning models in remote sensing (RS) image classification. Most existing methods rely on direct pixel-wise perturbations, failing to exploit the inherent atmospheric characteristics of RS imagery or survive real-world image degradations. In this paper, we propose FogFool, a physically plau

Xiaozhen Yang, Xiaoting Fu, Mingjie Jian, Jingkun Zhao

Synthetic-template subtraction is widely used to measure chromospheric activity in large spectroscopic surveys. However, many solar-like FGK stars show systematically negative Ca II infrared triplet (IRT) residual indices, implying that the observed line cores are deeper than those predicted by parameter-matched templates. We investigate this effect using so

Shiyuan Huang, Li Liu, Jincheng He, Leilani H. Gilpin

When faced with complex spatial problems, humans naturally sketch layouts to organize their thinking, and the act of drawing further sharpens their understanding. In this work, we ask whether a similar principle holds for Large Language Models (LLMs): can learning to construct explicit visual layouts from spatial descriptions instill genuine spatial understa

Seok Hyun Byun, Svetlana Poznanović

In this paper, we consider a two-parameter ($l$ and $a$) generalization of a sequence that Glasby and Paseman considered. Based on computer experiments, we conjecture its unimodality, log-concavity, peak positions, and the asymptotic behavior of the maximum values. Then we prove this conjecture for the case where $l=2$ and $a=1$. We finish the paper by makin

Cheng Ran, Zhenkang Lu, Shao-Feng Wu

We investigate an analytical framework for reconstructing bulk geometries from pole-skipping data. Previously, this method enabled the recursive recovery of near-horizon metric derivatives in static, planar-symmetric black holes. Building on this framework, we systematically extend it to more intricate geometries, specifically static topological black holes

Li Liu, Jiaming Qu, Marc Jowell Bagaoisan, David T. Lee

Most existing assistive navigation tools focus on providing real-time guidance for Blind and Low-Vision (BLV) people, but few support building a holistic spatial understanding of unfamiliar environments before travel. Such cognitive map construction (e.g., knowing that a fountain is south of a tower and west of a hotel) is important for pre-travel planning,

Gunther Uhlmann, Yuchao Yi, Jian Zhai

We consider an inverse problem for the compressible Euler's equations in polytropic fluid. We show that by taking active measurements near a particle trajectory one can determine the background flow in a set where pressure waves can propagate from and return to the particle trajectory, under the additional assumption that the flow has nonzero vorticity.

Michael R. Chang, Anna Candotti, Karl von Ellenrieder, Enrico Tomelleri

We present a curated multi-platform LiDAR reference dataset from an instrumented ICOS forest plot, explicitly designed to support calibration, benchmarking, and integration of 3D structural data with ecological observations and standard allometric models. The dataset integrates UAV-borne laser scanning (ULS) to measure canopy coverage, terrestrial laser scan

Nahyun Lee, Guijin Son

Multiple choice evaluation is widely used for benchmarking large language models, yet near ceiling accuracy in low option settings can be sustained by shortcut strategies that obscure true competence. Therefore, we propose a massive option evaluation protocol that scales the candidate set to one hundred options and sharply reduces the impact of chance perfor

Jason Li

We present a randomized augmenting paths-based algorithm to compute the maximum flow in a directed, uncapacitated graph in almost $m+nF$ time, matching the algorithm of Karger and Levine for undirected graphs (SICOMP 2015). Combined with an initial $\sqrt n$ rounds of blocking flow to reduce the value of $F$, we obtain a maximum flow algorithm with running t

Chu Zhou, Siqi Yang, Kailong Zhang, Heng Guo

Conventional RGB-based high dynamic range (HDR) imaging faces a fundamental trade-off between motion artifacts in multi-exposure captures and irreversible information loss in single-shot techniques. Modulo sensors offer a promising alternative by encoding theoretically unbounded dynamic range into wrapped measurements. However, existing modulo solutions rema

Geonhui Jang, Dongyoon Han, YoungJoon Yoo

Effective code generation requires both model capability and a problem representation that carefully structures how models reason and plan. Existing approaches augment reasoning steps or inject specific structure into how models think, but leave scattered problem conditions unchanged. Inspired by the way humans organize fragmented information into coherent e

Inseok Jeon, Suhwan Cho, Minhyeok Lee, Seunghoon Lee

Recent advances in unsupervised video object segmentation have highlighted the potential of two-stream architectures that integrate appearance and motion cues. However, fully leveraging these complementary sources of information requires effectively modeling their interdependencies. In this paper, we introduce cross-modality token modulation, a novel approac

Haoyi Sun, Xiaoxiao Wang, Ning Mao, Qian Wang

Vision-Language Models (VLMs) have shown remarkable capabilities in joint vision-language understanding, but their large scale poses significant challenges for deployment in resource-constrained scenarios. Knowledge Distillation (KD) offers a viable way to improve model capabilities without increasing model size or data requirements, making deployment more e

Liangda Fang, Yaohui Luo, Delong Li, Xuanxiang Huang

The exact cover problem is a classical NP-hard problem with broad applications in the area of AI. Algorithm DXZ is a method to count exact covers representing by zero-suppressed binary decision diagrams (ZBDDs). In this paper, we propose a zero-suppressed variant of decision decomposable negation normal form (in short, decision-ZDNNF), which is strictly more

Yuseon Choi, Jingu Lee, Jungjun Oh, Sunjoo Whang

Mixture-of-Experts (MoE) models have become the dominant architecture for large-scale language models, yet on-premises serving remains fundamentally memory-bound as batching turns sparse per-token compute into dense memory activation. Memory-centric architectures (PIM, NMP) improve bandwidth but leave compute underutilized under MoE's low arithmetic intensit

Paul C. Bell, George Kenison, Reino Niskanen, Igor Potapov

Embeddings of word structures into matrix semigroups provide a natural bridge between combinatorics on words and linear algebra. However, low-dimensional matrix semigroups impose strong structural restrictions on possible embeddings. Certain finitely generated groups admit faithful representations in SL(2, C) and other similar matrix groups. On the other han

Sanidhya Vijayvargiya, Vijay Viswanathan, Graham Neubig

Humans often specify tasks incompletely, so assistants must know when and how to ask clarifying questions. However, effective clarification remains challenging in software engineering tasks as not all missing information is equally valuable, and questions must target information users can realistically provide. We study clarification in real software enginee

Muhammad Nadeem, Xiaolin Wang

This study maps the quantum landscape of superconducting diodes (SDs) \cite{nadeem23} onto the quantum technology architecture, which is currently constrained by fundamental challenges in control and scalability. In the existing non-integrated quantum technology hardware, control and scalability related issues emerge at two fronts: First, nonlinear and nonre

Junfeng Li, Wenyang Zhou, Xueheng Li, Xuanhua He

In this work, we propose a Multigrain-aware Semantic Prototype Scanning paradigm for pan-sharpening, built upon a high-order RWKV architecture and a tri-token prompting mechanism derived from semantic clustering. Specifically, our method contains three key components: 1) Multigrain-aware Semantic Prototype Scanning. Although RWKV offers a efficient linear-co

Jiamei Wu, Ce Zhang, Zhipeng Cai, Jingsen Kong

Conformal prediction (CP) has attracted broad attention as a simple and flexible framework for uncertainty quantification through prediction sets. In this work, we study how to deploy CP under differential privacy (DP) in a statistically efficient manner. We first introduce differential CP, a non-splitting conformal procedure that avoids the efficiency loss

Kunio Kaneta, Tomo Takahashi, Natsumi Watanabe

The standard cosmological paradigm assumes that the inflaton field becomes dynamically negligible during the post-reheating evolution of the Universe. We demonstrate that this assumption fails for a broad class of inflationary models where the potential behaves as a monomial form $V(ϕ) \propto ϕ^k$ (with $k \ge 4$) around the minimum. In such scenarios, the

Dhruvin Dungrani, Disha Dungrani

In computational paralinguistics, detecting cognitive load and deception from speech signals is a heavily researched domain. Recent efforts have attempted to apply these acoustic frameworks to corporate earnings calls to predict catastrophic stock market volatility. In this study, we empirically investigate the limits of acoustic feature extraction (pitch, j

Gilad Gour

Single-shot quantum information theory is governed not only by entropy exponents, but also by the finite-resource constants that multiply them. These constants directly affect the quantitative performance of decoupling, covering, convex-splitting, position-based decoding, and one-shot communication protocols, yet they are often inherited from nonoptimal scal

Sumit Mukherjee, Juan Shu, Nairwita Mazumder, Tate Kernell

Clinical value set authoring -- the task of identifying all codes in a standardized vocabulary that define a clinical concept -- is a recurring bottleneck in clinical quality measurement and phenotyping. A natural approach is to prompt a large language model (LLM) to generate the required codes directly, but structured clinical vocabularies are large, versio

Xiangrui Xiong, Hang Liang, Baiyang Chen, Zifei Pan

Learning Path Recommendation (LPR) is critical for personalized education, yet current methods often fail to account for historical interaction uncertainty (e.g., lucky guesses or accidental slips) and lack adaptability to diverse learning goals. We propose U-GLAD (Uncertainty-aware Generative Learning Path Recommendation with Cognition-Adaptive Diffusion).

Walaa Amer, Uday das, Fadi Kurdahi

Self-speculative decoding is an inference technique for large language models designed to speed up generation without sacrificing output quality. It combines fast, approximate decoding using a compact version of the model as a draft model with selective re-evaluation by the full target model. Some existing methods form the draft model by dynamically learning

Cunyuan Jiang

Solid phase of dense granular matter is inevitable because of jamming transition when the packing fraction or the pressure suffered is high enough. The experiment suggests that active Brownian granular matter will keep fluid phase even under the highest packing fraction (higher than the packing fraction of crystallization) if crystallization is prevented by

Zijian Zhang, Aiwei Yin, Amaan Baweja, Jiaru Bai

AI for science promises to accelerate the discovery process. The advent of large language models (LLMs) and agentic workflows enables the expediting of a growing range of scientific tasks. However, most of the current generation of agentic systems depend on static, hand-curated toolsets that hinder adaptation to new domains and evolving libraries. We present

Izumi Hachisu, Mariko Kato

We present the maximum ejecta mass $(M_{\rm ej})_{\rm max}$ and the maximum ratio of ejecta mass and accreted mass $(M_{\rm ej}/M_{\rm acc})_{\rm max}$ of a nova for various white dwarf (WD) masses ($M_{\rm WD}=0.6$ - 1.38 $M_\odot$) and mass accretion rates ($\dot{M}_{\rm acc}=1\times 10^{-11}$ - $3\times 10^{-7} ~M_\odot$ yr$^{-1}$) based on the energy bal

Dapeng Wu, Shun Lei, Wei Tan, Guangzheng Li

Recent advancements in Text-to-Song generation have enabled realistic musical content production, yet existing evaluation benchmarks lack the professional granularity to capture multi-dimensional aesthetic nuances. In this paper, we propose SongBench, a specialized framework for fine-grained song assessment across seven key dimensions: Vocal, Instrument, Mel

Ha Thanh Nguyen, Wachara Fungwacharakorn, Sabine Wehnert, May Myo Zin

We study the overall process of automatic formalization of GDPR provisions using large language models, within a human-in-the-loop verification framework. Rather than aiming for full autonomy, we adopt a role-specialized workflow in which LLM-based AI components, operating in a multi-agent setting with iterative feedback, generate legal scenarios, formal rul

Abhinav Mahajan, Abhikhya Tripathy, Sudeeksha Reddy Pala, Vaibhav Methi

Graphic design creation involves harmoniously assembling multimodal components such as images, text, logos, and other visual assets collected from diverse sources, into a visually-appealing and cohesive design. Recent methods have largely focused on layout prediction or complementary element generation, while retaining input elements exactly, implicitly assu

Meng Chen, Kun Wang, Li Lu, Jiaheng Zhang

Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text. This integration, however, expands the attack surface beyond text and introduces vulnerabilities in the continuous, high-dimensional audio channel. While prior work studied audio jailbreaks, the security risks of malicious audio injection an

Yian Wang, Yuen Chen, Agam Goyal, Hari Sundaram

Large language models (LLMs) frequently generate toxic content, posing significant risks for safe deployment. Current mitigation strategies often degrade generation quality or require costly human annotation. We propose CAUSALDETOX, a framework that identifies and intervenes on the specific attention heads causally responsible for toxic generation. Using the

Tian Xie, Rikuto Fukumori, Wai-Keong Mok, Jiahui Li

Cavity quantum electrodynamics (QED) with quantum emitters coupled to resonators provides a powerful platform for engineering light-matter interactions and exploring collective phenomena. In particular, superradiance, arising from collective quantum interference among emitters, has been explored as a route to ultrastable continuous radiation. However, engine

Xiu-Wu Wang, Zhi-Gang Wang, Guo-Liang Yu

In the present work, we study the $Λ_cΣ_c$ dibaryon and $\barΛ_cΣ_c\pm \barΣ_cΛ_c$ baryonium states via the QCD sum rules. We construct four (eight) currents with definite $J^P$ ($J^{PC}$) to interpolate the dibaryon (baryonium) states and obtain twelve QCD sum rules. For the dibaryon states, the state with the $J^P=1^+$ lies below the $Λ_cΣ_c$ threshold, an

Ibne Farabi Shihab

We study the communication complexity of distributed offline dynamic programming, where a fixed batch dataset is partitioned across (M) machines connected by the data-induced dependency graph. We compare two paradigms: direct boundary-value propagation, which follows Bellman dependencies, and gossip averaging, which mixes local estimates. Our results show th

Joshua Tint

This position paper argues that recent progress with diversity in NLP is disproportionately concentrated on a small number of areas surrounding fairness. We further argue that this is the result of a number of incentives, biases, and barriers which come together to disenfranchise marginalized researchers in non-fairness fields, or to move them into fairness-

Yitong Shou, Manhao Guan

While Large Language Models (LLMs) demonstrate increasingly sophisticated affective capabilities, the internal mechanisms by which they process complex emotions remain unclear. Existing interpretability approaches often treat models as black boxes or focus on coarse-grained basic emotions, leaving the cognitive structure of more complex affective states unde

Amir El-Ghoussani, Marc Hölle, Gustavo Carneiro, Vasileios Belagiannis

We address the problem of prompt-guided image editing in visual autoregressive models. Given a source image and a target text prompt, we aim to modify the source image according to the target prompt, while preserving all regions which are unrelated to the requested edit. To this end, we present Masked Logit Nudging, which uses the source image token maps to

Shreesha G. Bhat, Tony Hong, Michael Noguera, Ramnatthan Alagappan

In modern data-streaming systems, alongside traditional programs, a new type of entity has emerged that can interact with streaming data: AI agents. Unlike traditional programs, AI agents use LLM reasoning to accomplish high-level tasks specified in natural language over streaming data. Unfortunately, current streaming systems cannot fully support agents: th

Aman Panjwani

The deployment of Large Language Models in agentic, multi-turn conversational settings has introduced a class of privacy vulnerabilities that existing protection mechanisms are not designed to address. Current approaches to Personally Identifiable Information (PII) masking operate on a per-turn basis, scanning each user message in isolation and replacing det

Dhruv Hariharan, Pavel Tonkaev, Felix Ulrich Brikh, Brijesh Kumar

Chiral photonics provides powerful routes for controlling the light handedness, yet nonlinear chiral responses are typically associated with intricate three-dimensional systems. Here, we demonstrate that strong nonlinear chirality can emerge and be precisely tuned in planar metasurfaces. We study free-standing membrane metasurfaces composed of periodic latti

Diego Martínez Collipal, Swayamtrupta Panda

Variability in active galactic nuclei (AGN) probes the physics of accretion onto supermassive black holes. This variability is characterized using metrics derived from the flux distributions of temporally separated epochs. We studied the stability of two variability metrics, the Stetson index "J" and the smoothness "s", against baseline, cadence, and host ga

Feihu Huang, Guanyi Zhang, Songcan Chen

Lion optimizer is a popular learning-based optimization algorithm in machine learning, which shows impressive performance in training many deep learning models. Although convergence property of the Lion optimizer has been studied, its generalization analysis is still missing. To fill this gap, we study generalization property of the Lion via algorithmic stab

Afia Farjana, Zaiyu Cheng, Antonio Mastropaolo

Software documentation is essential for program comprehension, developer onboarding, code review, and long-term maintenance. Yet producing quality documentation manually is time-consuming and frequently yields incomplete or inconsistent results. Large language models (LLMs) offer a promising solution by automatically generating natural language descriptions

Daichi Takeuchi

In this article, we develop a positive characteristic analogue of the Bernstein--Sato theory for holonomic D-modules in the complex setting. We work with D-modules on a Noetherian regular $F$-finite $\mathbb{F}_p$-scheme $X$, and define their Bernstein--Sato roots as $p$-adic integers. When the D-module is the structure sheaf $O_X$, this recovers Bitoun's de

Fernando Spadea, Oshani Seneviratne

Decentralized Finance (DeFi) lending protocols like Aave v3 rely on over-collateralization to secure loans, yet users frequently face liquidation due to volatile market conditions. Existing risk management tools utilize static health-factor thresholds, which are reactive and fail to distinguish between administrative "dust" cleanup and genuine insolvency. In

Ruiqi Wang, Qi Yu, Jie Ma, Hanlin Wu

High-resolution (HR) land-cover mapping is often constrained by the high cost of dense HR annotations. We revisit this problem from the perspective of map super-resolution, which enhances coarse low-resolution (LR) land-cover products into HR maps at the resolution of the input imagery. Existing weakly supervised methods can leverage LR labels, but they typi

Jing Xiao, Dongqi Wu, Liwei Pan, Yawen Luo

Heterogeneous sequential recommendation (HSR) aims to learn dynamic behavior dependencies from the diverse behaviors of user-item interactions to facilitate precise sequential recommendation. Despite many efforts yielding promising achievements, there are still challenges in modeling heterogeneous behavior data. One significant issue is the inherent sparsity

Xiangyu Liu, Feng Gao, Xiaomei Zhang, Yong Zhang

Existing audio-driven video digital human generation models rely on multi-step denoising, resulting in substantial computational overhead that severely limits their deployment in real-world settings. While one-step distillation approaches can significantly accelerate inference, they often suffer from training instability. To address this challenge, we propos

Kumarjit Pathak

Industrial experimentation requires both factor screening to identify critical variables and response optimization to find optimal operating conditions. Traditional approaches treat these as separate phases, necessitating costly sequential experimentation and full experimental redesign between phases. This paper introduces HASOD (Hybrid Adaptive Screening-Op

Ryoei Ota, Shunsuke Nishimura, Koki Honda, Takeyuki Tsuji

Understanding and controlling vortex motion in superconductors are important both for suppressing dissipation in superconducting devices and for device applications that exploit vortices. In this work, we quantitatively imaged the stray magnetic field distribution of vortices in an NbN thin film by wide-field magnetic imaging using a perfectly aligned diamon

Md Arid Hasan, Azhagu Meena SP, Aditya Khan, Abu Md Akteruzzaman Bhuiyan

Large language models (LLMs) show promise in generating supportive responses for mental health and counseling applications. However, their responses often lack cultural sensitivity, contextual grounding, and clinically appropriate guidance. This work addresses the gap of how to systematically incorporate domain-specific, clinically validated knowledge into L

Haotian Wu, Yue Cheng, Shan Bian

With the rapid advancement of deep learning in image generation, facial forgery techniques have achieved unprecedented realism, posing serious threats to cybersecurity and information authenticity. Most existing deepfake detection approaches rely on the reconstruction of isolated facial attributes without fully exploiting the complementary nature of multi-mo

Wen Tao, Wan-Tong Li, Shigui Ruan, Wen-Bing Xu

This paper is concerned with the spreading speeds of nonlocal dispersal predator-prey systems in shifting habitats under general initial conditions. By employing geometric optics techniques and theory of viscosity solutions, we reformulate the problem into the study of Hamilton-Jacobi equations. Through a detailed analysis of the structure of viscosity solut

Hsin-Hsiung Huang, Ruitao Liu, Liangliang Zhang, Shao-Hsuan Wang

Principal coordinates analysis (PCoA) is a standard exploratory tool for microbiome beta-diversity studies, but its axes are defined by pairwise dissimilarities and therefore do not directly identify the taxa driving an ordination. We propose Bayesian sparse principal coordinates analysis (BSPCoA), a post hoc framework that approximates the leading principal

Hongyuan Qi, Wenjin Hou, Hehe Fan, Jun Xiao

Deepfake detectors face growing challenges in generalization as new image synthesis techniques emerge. In particular, deepfakes generated by diffusion models are highly photorealistic and often evade detectors trained on GAN-based forgeries. This paper addresses the generalization problem in deepfake detection by leveraging diffusion noise characteristics. W

Tyler Tracy, Ram Potham, Nick Kuhn, Myles Heller

We introduce LinuxArena, a control setting in which agents operate directly on live, multi-service production environments. LinuxArena contains 20 environments, 1,671 main tasks representing legitimate software engineering work, and 184 side tasks representing safety failures such as data exfiltration and backdooring, making it the largest and most diverse c