Papers
Research papers from arXiv and related sources
Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge: A keynote at ECIR 2025
Language Models (LMs) acquire parametric knowledge from their training process, embedding it within their weights. The increasing scalability of LMs, however, poses significant challenges for under...
Isabelle Augenstein
MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants
With the rapid advancement of Large Language Models (LLMs) in code generation, human-AI interaction is evolving from static text responses to dynamic, interactive HTML-based applications, which we ...
Zuhao Zhang, Chengyue Yu, Yuante Li, Chenyi Zhuang, Linjian Mo, Shuai Li
MM-tau-p$^2$: Persona-Adaptive Prompting for Robust Multi-Modal Agent Evaluation in Dual-Control Settings
Current evaluation frameworks and benchmarks for LLM powered agents focus on text chat driven agents, these frameworks do not expose the persona of user to the agent, thus operating in a user agnos...
Anupam Purwar, Aditya Choudhary
PRECEPT: Planning Resilience via Experience, Context Engineering & Probing Trajectories A Unified Framework for Test-Time Adaptation with Compositional Rule Learning and Pareto-Guided Prompt Evolution
LLM agents that store knowledge as natural language suffer steep retrieval degradation as condition count grows, often struggle to compose learned rules reliably, and typically lack explicit mechan...
Arash Shahmansoori
Tracking Cancer Through Text: Longitudinal Extraction From Radiology Reports Using Open-Source Large Language Models
Radiology reports capture crucial longitudinal information on tumor burden, treatment response, and disease progression, yet their unstructured narrative format complicates automated analysis. Whil...
Luc Builtjes, Alessa Hering
X-GS: An Extensible Open Framework Unifying 3DGS Architectures with Downstream Multimodal Models
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, subsequently extending into numerous spatial AI applications. However, most existing 3DGS methods are isol...
Yueen Ma, Irwin King
On the last time and the number of times an estimator is more than epsilon from its target value
Suppose $\widehatθ_n$ is a strongly consistent estimator for $θ_0$ in some i.i.d. situation. Let $N_\varepsilon$ and $Q_\varepsilon$ be respectively the last $n$ and the total number of $n$ for whi...
Nils Lid Hjort, Grete Fenstad
The Architecture of Inter-Level Representation
Inter-level connections in science routinely require constructs that neither of the connected theories contains. Statistical mechanics requires assumptions such as the Stosszahlansatz to generate t...
Harry Sticker
Context Engineering: From Prompts to Corporate Multi-Agent Architecture
As artificial intelligence (AI) systems evolve from stateless chatbots to autonomous multi-step agents, prompt engineering (PE), the discipline of crafting individual queries, proves necessary but ...
Vera V. Vishnyakova
A saccade-inspired approach to image classification using visiontransformer attention maps
Human vision achieves remarkable perceptual performance while operating under strict metabolic constraints. A key ingredient is the selective attention mechanism, driven by rapid saccadic eye movem...
Matthis Dallain, Laurent Rodriguez, Laurent Udo Perrinet, Benoît Miramond
Analytic treatment of a polaron in a nonparabolic conduction band
We develop and compare several analytical approximations for the polaron problem in finite-width, non-parabolic conduction bands. The main focus of the work is an extension of the Feynman variation...
S. N. Klimin, J. Tempere, M. Houtput, I. Zappacosta, S. Ragni, T. Hahn, L. Celiberti, C. Franchin...
A Variational Latent Equilibrium for Learning in Cortex
Brains remain unrivaled in their ability to recognize and generate complex spatiotemporal patterns. While AI is able to reproduce some of these capabilities, deep learning algorithms remain largely...
Simon Brandt, Paul Haider, Walter Senn, Federico Benitez, Mihai A. Petrovici
Preparing Students for AI-Driven Agile Development: A Project-Based AI Engineering Curriculum
Generative AI and agentic tools are reshaping agile software development, yet many engineering curricula still teach agile methods and AI competencies separately and largely lecture-based. This pap...
Andreas Rausch, Stefan Wittek, Tobias Geger, David Inkermann
Build, Borrow, or Just Fine-Tune? A Political Scientist's Guide to Choosing NLP Models
Political scientists increasingly face a consequential choice when adopting natural language processing tools: build a domain-specific model from scratch, borrow and adapt an existing one, or simpl...
Shreyas Meher
Benchmarking Dataset for Presence-Only Passive Reconnaissance in Wireless Smart-Grid Communications
Benchmarking presence-only passive reconnaissance in smart-grid communications is challenging because the adversary is receive-only, yet nearby observers can still alter propagation through additio...
Bochra Al Agha, Razane Tajeddine
Routing without Forgetting
Continual learning in transformers is commonly addressed through parameter-efficient adaptation: prompts, adapters, or LoRA modules are specialized per task while the backbone remains frozen. Altho...
Alessio Masano, Giovanni Bellitto, Dipam Goswani, Joost Van de Weijer, Concetto Spampinato
SCDP: Learning Humanoid Locomotion from Partial Observations via Mixed-Observation Distillation
Distilling humanoid locomotion control from offline datasets into deployable policies remains a challenge, as existing methods rely on privileged full-body states that require complex and often unr...
Milo Carroll, Tianhu Peng, Lingfan Bao, Chengxu Zhou, Zhibin Li
a-TMFG: Scalable Triangulated Maximally Filtered Graphs via Approximate Nearest Neighbors
The traditional Triangular Maximally Filtered Graph (TMFG) construction requires pre-computation and storage of a dense correlation matrix; this limits its applicability to small and medium-sized d...
Lionel Yelibi
ALARM: Audio-Language Alignment for Reasoning Models
Large audio language models (ALMs) extend LLMs with auditory understanding. A common approach freezes the LLM and trains only an adapter on self-generated targets. However, this fails for reasoning...
Petr Grinberg, Hassan Shahmohammadi
GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision
While Vision-Language Models (VLMs) have significantly advanced remote sensing interpretation, enabling them to perform complex, step-by-step reasoning remains highly challenging. Recent efforts to...
Lang Sun, Ronghao Fu, Zhuoran Duan, Haoran Liu, Xueyan Liu, Bo Yang