Papers
Research papers from arXiv and related sources
Intelligent Co-Design: An Interactive LLM Framework for Interior Spatial Design via Multi-Modal Agents
In architectural interior design, miscommunication frequently arises as clients lack design knowledge, while designers struggle to explain complex spatial relationships, leading to delayed timeline...
Ren Jian Lim, Rushi Dai
The Neuroscience of Transformers
Neuroscience has long informed the development of artificial neural networks, but the success of modern architectures invites, in turn, the converse: can modern networks teach us lessons about brai...
Peter Koenig, Mario Negrello
Comparative Analysis of SRAM PUF Temperature Susceptibility on Embedded Systems
An SRAM Physical Unclonable Function (PUF) can distinguish SRAM modules by analyzing the inherent randomness of their start-up behavior. However, the effectiveness of this technique varies dependin...
Martina Zeinzinger, Josef Langer, Florian Eibensteiner, Phillip Petz, Lucas Drack, Daniel Dorfmei...
PYTHEN: A Flexible Framework for Legal Reasoning in Python
This paper introduces PYTHEN, a novel Python-based framework for defeasible legal reasoning. PYTHEN is designed to model the inherently defeasible nature of legal argumentation, providing a flexibl...
Ha-Thanh Nguyen, Ken Satoh
CCTU: A Benchmark for Tool Use under Complex Constraints
Solving problems through tool use under explicit constraints constitutes a highly challenging yet unavoidable scenario for large language models (LLMs), requiring capabilities such as function call...
Junjie Ye, Guoqiang Zhang, Wenjie Fu, Tao Gui, Qi Zhang, Xuanjing Huang
The Impact of AI-Assisted Development on Software Security: A Study of Gemini and Developer Experience
The ongoing shortage of skilled developers, particularly in security-critical software development, has led organizations to increasingly adopt AI-powered development tools to boost productivity an...
Nadine Jost, Benjamin Berens, Manuel Karl, Stefan Albert Horstmann, Martin Johns, Alena Naiakshina
Evolutionary Transfer Learning for Dragonchess
Dragonchess, a three-dimensional chess variant introduced by Gary Gygax, presents unique strategic and computational challenges that make it an ideal environment for studying the transfer of artifi...
Jim O'Connor, Annika Hoag, Sarah Goyette, Gary B. Parker
Nonlinear Model Order Reduction for Coupled Aeroelastic-Flight Dynamic Systems
A systematic approach to nonlinear model order reduction (NMOR) of coupled fluid-structureflight dynamics systems of arbitrary fidelity is presented. The technique employs a Taylor series expansion...
Nikolaos D. Tantaroudas, Andrea Da Ronch, Ilias Karachalios, Kenneth J. Badcock
Datasets for Verb Alternations across Languages: BLM Templates and Data Augmentation Strategies
Large language models (LLMs) have shown remarkable performance across various sentence-based linguistic phenomena, yet their ability to capture cross-sentence paradigmatic patterns, such as verb al...
Giuseppe Samo, Paola Merlo
Breakdown of the isotropic asymptotic approximation in two-colour photoionisation
The Wigner delay is defined as the energy derivative of the scattering phase of a particle in a given potential, unveiling the time taken (or gained) due to the interaction. The characterisation of...
Sooraj Rajendran, Miguel Benito de Lama, Praveen Kumar Maroju, Michele Di Fraia, Oksana Plekan, D...
Scalable Simulation-Based Model Inference with Test-Time Complexity Control
Simulation plays a central role in scientific discovery. In many applications, the bottleneck is no longer running a simulator; it is choosing among large families of plausible simulators, each cor...
Manuel Gloeckler, J. P. Manzano-Patrón, Stamatios N. Sotiropoulos, Cornelius Schröder, Jakob H. M...
ReLU Barrier Functions for Nonlinear Systems with Constrained Control: A Union of Invariant Sets Approach
Certifying safety for nonlinear systems with polytopic input constraints is challenging because CBF synthesis must ensure control admissibility under saturation. We propose an approximation--verifi...
Pouya Samanipour, Hasan A. Poonawala
Algorithms for Deciding the Safety of States in Fully Observable Non-deterministic Problems: Technical Report
Learned action policies are increasingly popular in sequential decision-making, but suffer from a lack of safety guarantees. Recent work introduced a pipeline for testing the safety of such policie...
Johannes Schmalz, Chaahat Jain
Design and operation of a spark chamber for vacuum ultraviolet light production
Noble liquids, notably argon and xenon, are utilised as both detector media and as the detector target for dark matter and neutrino physics experiments. When the noble liquid is excited by particle...
Silas Bosco, Jonas Bürgi, Livio Calivers, Richard Diurba, Johannes Furrer, Jan Kunzmann, Saba Par...
From Documents to Spans: Code-Centric Learning for LLM-based ICD Coding
ICD coding is a critical yet challenging task in healthcare. Recently, LLM-based methods demonstrate stronger generalization than discriminative methods in ICD coding. However, fine-tuning LLMs for...
Xu Zhang, Wenxin Ma, Chenxu Wu, Rongsheng Wang, Kun Zhang, S. Kevin Zhou
Exemplar Diffusion: Improving Medical Object Detection with Opportunistic Labels
We present a framework to take advantage of existing labels at inference, called \textit{exemplars}, in order to improve the performance of object detection in medical images. The method, \textit{e...
Victor Wåhlstrand, Jennifer Alvén, Ida Häggström
Probe-then-Plan: Environment-Aware Planning for Industrial E-commerce Search
Modern e-commerce search is evolving to resolve complex user intents. While Large Language Models (LLMs) offer strong reasoning, existing LLM-based paradigms face a fundamental blindness-latency di...
Mengxiang Chen, Zhouwei Zhai, Jin Li
Directional Embedding Smoothing for Robust Vision Language Models
The safety and reliability of vision-language models (VLMs) are a crucial part of deploying trustworthy agentic AI systems. However, VLMs remain vulnerable to jailbreaking attacks that undermine th...
Ye Wang, Jing Liu, Toshiaki Koike-Akino
SAGE: Multi-Agent Self-Evolution for LLM Reasoning
Reinforcement learning with verifiable rewards improves reasoning in large language models (LLMs), but many methods still rely on large human-labeled datasets. While self-play reduces this dependen...
Yulin Peng, Xinxin Zhu, Chenxing Wei, Nianbo Zeng, Leilei Wang, Ying Tiffany He, F. Richard Yu
A Methodology for Dynamic Parameters Identification of 3-DOF Parallel Robots in Terms of Relevant Parameters
The identification of dynamic parameters in mechanical systems is important for improving model-based control as well as for performing realistic dynamic simulations. Generally, when identification...
Miguel Díaz-Rodríguez, Vicente Mata, Angel Valera, Alvaro Page