Papers
Research papers from arXiv and related sources
Neuro-Symbolic Artificial Intelligence: A Task-Directed Survey in the Black-Box Models Era
The integration of symbolic computing with neural networks has intrigued researchers since the first theorizations of Artificial intelligence (AI). The ability of Neuro-Symbolic (NeSy) methods to i...
Giovanni Pio Delvecchio, Lorenzo Molfetta, Gianluca Moro
Saarthi for AGI: Towards Domain-Specific General Intelligence for Formal Verification
Saarthi is an agentic AI framework that uses multi-agent collaboration to perform end-to-end formal verification. Even though the framework provides a complete flow from specification to coverage c...
Aman Kumar, Deepak Narayan Gadde, Luu Danh Minh, Vaisakh Naduvodi Viswambharan, Keerthan Kopparam...
Data Unfolding: From Problem Formulation to Result Assessment
Experimental data in particle and nuclear physics, particle astrophysics, and radiation protection dosimetry are collected using experimental facilities that consist of a complex system of sensors,...
Nikolay D. Gagunashvili
Testing gravitational wave polarizations with LISA
In this paper we quantify the ability of the Laser Interferometer Space Antenna (LISA) to test the presence of non-tensorial polarizations as well as modifications to the tensor ones in gravitation...
Shingo Akama, Maxence Corman, Paola C. M. Delgado, Alice Garoffolo, Macarena Lagos, Alberto Mangi...
Conditioned Activation Transport for T2I Safety Steering
Despite their impressive capabilities, current Text-to-Image (T2I) models remain prone to generating unsafe and toxic content. While activation steering offers a promising inference-time interventi...
Maciej Chrabąszcz, Aleksander Szymczyk, Jan Dubiński, Tomasz Trzciński, Franziska Boenisch, Adam ...
An Investigation Into Various Approaches For Bengali Long-Form Speech Transcription and Bengali Speaker Diarization
Bengali remains a low-resource language in speech technology, especially for complex tasks like long-form transcription and speaker diarization. This paper presents a multistage approach developed ...
Epshita Jahan, Khandoker Md Tanjinul Islam, Pritom Biswas, Tafsir Al Nafin
Weak-Strong Uniqueness for a Rigid Body Immersed in an Inviscid Compressible Fluid
We consider the coupled motion of a free rigid body immersed in an inviscid compressible isentropic fluid. By means of a vanishing viscosity limit, we obtain the local-in-time existence of a dissip...
Qianfeng Li, Emil Wiedemann
From Language to Action: Can LLM-Based Agents Be Used for Embodied Robot Cognition?
In order to flexibly act in an everyday environment, a robotic agent needs a variety of cognitive capabilities that enable it to reason about plans and perform execution recovery. Large language mo...
Shinas Shaji, Fabian Huppertz, Alex Mitrevski, Sebastian Houben
Agentic AI-based Coverage Closure for Formal Verification
Coverage closure is a critical requirement in Integrated Chip (IC) development process and key metric for verification sign-off. However, traditional exhaustive approaches often fail to achieve ful...
Sivaram Pothireddypalli, Ashish Raman, Deepak Narayan Gadde, Aman Kumar
Channel-Adaptive Edge AI: Maximizing Inference Throughput by Adapting Computational Complexity to Channel States
\emph{Integrated communication and computation} (IC$^2$) has emerged as a new paradigm for enabling efficient edge inference in sixth-generation (6G) networks. However, the design of IC$^2$ technol...
Jierui Zhang, Jianhao Huang, Kaibin Huang
The Household Impact of Generative AI: Evidence from Internet Browsing Behavior
This paper studies the impact of generative AI on U.S. households' task allocation at home, using detailed Internet browsing data from a large sample of home devices between 2021 and 2024. Leveragi...
Michael Blank, Gregor Schubert, Miao Ben Zhang
APRES: An Agentic Paper Revision and Evaluation System
Scientific discoveries must be communicated clearly to realize their full potential. Without effective communication, even the most groundbreaking findings risk being overlooked or misunderstood. T...
Bingchen Zhao, Jenny Zhang, Chenxi Whitehouse, Minqi Jiang, Michael Shvartsman, Abhishek Charnali...
How to Model AI Agents as Personas?: Applying the Persona Ecosystem Playground to 41,300 Posts on Moltbook for Behavioral Insights
AI agents are increasingly active on social media platforms, generating content and interacting with one another at scale. Yet the behavioral diversity of these agents remains poorly understood, an...
Danial Amin, Joni Salminen, Bernard J. Jansen
UniSkill: A Dataset for Matching University Curricula to Professional Competencies
Skill extraction and recommendation systems have been studied from recruiter, applicant, and education perspectives. While AI applications in job advertisements have received broad attention, defic...
Nurlan Musazade, Joszef Mezei, Mike Zhang
Joint Training Across Multiple Activation Sparsity Regimes
Generalization in deep neural networks remains only partially understood. Inspired by the stronger generalization tendency of biological systems, we explore the hypothesis that robust internal repr...
Haotian Wang
Estimating the dynamical masses of dwarf galaxies in the presence of binary-star contamination
Ultra-faint dwarf galaxies (UFDs) show extreme dynamical mass-to-light ratios of approximately 100-5000 in solar units within the half-light radius, making them critical tests for cosmological mode...
José María Arroyo-Polonio, Giuseppina Battaglia, Guillaume F. Thomas
Behavior Change as a Signal for Identifying Social Media Manipulation
Social media accounts engaging in online manipulation can change their behaviors for re-purposing or to evade detection. Existing detection systems are built on features that do not exploit such be...
Isuru Ariyarathne, Gangani Ariyarathne, Alessandro Flammini, Filippo Menczer, Alexander C. Nwala
The Science Data Lake: A Unified Open Infrastructure Integrating 293 Million Papers Across Eight Scholarly Sources with Embedding-Based Ontology Alignment
Scholarly data are largely fragmented across siloed databases with divergent metadata and missing linkages among them. We present the Science Data Lake, a locally-deployable infrastructure built on...
Jonas Wilinski
RippleGUItester: Change-Aware Exploratory Testing
Software systems evolve continuously through frequent code changes, yet such changes often introduce unintended bugs despite extensive testing and code review. Existing testing approaches are large...
Yanqi Su, Michael Pradel, Chunyang Chen
AI Space Physics: Constitutive boundary semantics for open AI institutions
Agentic AI deployments increasingly behave as persistent institutions rather than one-shot inference endpoints: they accumulate state, invoke external tools, coordinate multiple runtimes, and modif...
Oleg Romanchuk, Roman Bondar