Papers
Research papers from arXiv and related sources
Test-Time Attention Purification for Backdoored Large Vision Language Models
Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the tra...
Zhifang Zhang, Bojun Yang, Shuo He, Weitong Chen, Wei Emma Zhang, Olaf Maennel, Lei Feng, Miao Xu
Fair Lung Disease Diagnosis from Chest CT via Gender-Adversarial Attention Multiple Instance Learning
We present a fairness-aware framework for multi-class lung disease diagnosis from chest CT volumes, developed for the Fair Disease Diagnosis Challenge at the PHAROS-AIF-MIH Workshop (CVPR 2026). Th...
Aditya Parikh, Aasa Feragen
Is Human Annotation Necessary? Iterative MBR Distillation for Error Span Detection in Machine Translation
Error Span Detection (ESD) is a crucial subtask in Machine Translation (MT) evaluation, aiming to identify the location and severity of translation errors. While fine-tuning models on human-annotat...
Boxuan Lyu, Haiyue Song, Zhi Qu
On the timescales of controlled termination of tokamak plasmas
The RAPTOR code is used to model how the time required for controlled termination of Ohmic plasmas scales from present tokamaks like TCV and JET, to reactor-grade tokamaks like ITER and DEMO. We sh...
Simon Van Mulders, Olivier Sauter
Generative Horcrux: Designing AI Carriers for Afterlife Selves
As generative AI technologies rapidly advance, AI agents are gaining the ability not only to collect data and perform tasks but also to respond to environments and evolve over time. This shift open...
Zhen-Chi Lai, Yu-Ting Cheng, Pei-Ying Lin, Chiao-Wei Ho, Janet Yi-Ching Huang
Tied-array beam flatfielding
Context. Multi-element phased-array radio telescopes use digital beamforming to widen their field-of-view with numerous tied-array beams (TABs). These beams share bandpass variations and radio freq...
Dirk Kuiper, Cees Bassa, Ziggy Pleunis, Jason Hessels
Long-form RewardBench: Evaluating Reward Models for Long-form Generation
The widespread adoption of reinforcement learning-based alignment highlights the growing importance of reward models. Various benchmarks have been built to evaluate reward models in various domains...
Hui Huang, Yancheng He, Wei Liu, Muyun Yang, Jiaheng Liu, Kehai Chen, Bing Xu, Conghui Zhu, Hailo...
Recent electroweak measurements from the CMS experiment
Recent measurements of electroweak phenomena from the Compact Muon Solenoid (CMS) experiment at the Large Hadron Collider are summarized. The standard model of particle physics was tested through h...
Cristina-Andreea Alexe
Delta1 with LLM: symbolic and neural integration for credible and explainable reasoning
Neuro-symbolic reasoning increasingly demands frameworks that unite the formal rigor of logic with the interpretability of large language models (LLMs). We introduce an end to end explainability by...
Yang Xu, Jun Liu, Shuwei Chen, Chris Nugent, Hailing Guo
MotionAnymesh: Physics-Grounded Articulation for Simulation-Ready Digital Twins
Converting static 3D meshes into interactable articulated assets is crucial for embodied AI and robotic simulation. However, existing zero-shot pipelines struggle with complex assets due to a criti...
WenBo Xu, Liu Liu, Li Zhang, Dan Guo, RuoNan Liu
Can Fairness Be Prompted? Prompt-Based Debiasing Strategies in High-Stakes Recommendations
Large Language Models (LLMs) can infer sensitive attributes such as gender or age from indirect cues like names and pronouns, potentially biasing recommendations. While several debiasing methods ex...
Mihaela Rotar, Theresia Veronika Rampisela, Maria Maistro
Photonic Exponential Approximation via Cascaded TFLN Microring Resonators toward Softmax
The rapid growth of large-scale AI models has intensified energy consumption and data-movement challenges in modern datacenters. Photonic accelerators offer a promising path by executing the line...
Hyoseok Park, Yeonsang Park
Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization
Large Language Model (LLM)-driven Multi-Agent Systems (MAS) have demonstrated strong capability in complex reasoning and tool use, and heterogeneous agent pools further broaden the quality--cost tr...
Xudong Wang, Chaoning Zhang, Jiaquan Zhang, Chenghao Li, Qigan Sun, Sung-Ho Bae, Peng Wang, Ning ...
DS$^2$-Instruct: Domain-Specific Data Synthesis for Large Language Models Instruction Tuning
Adapting Large Language Models (LLMs) to specialized domains requires high-quality instruction tuning datasets, which are expensive to create through human annotation. Existing data synthesis metho...
Ruiyao Xu, Noelle I. Samia, Han Liu
Teaching Agile Requirements Engineering: A Stakeholder Simulation with Generative AI
Context: The active involvement of users and customers in agile software development remains a persistent challenge in practice. For this reason, it is important that students in higher education b...
Eva-Maria Schön, Michael Neumann, Tiago Silva da Silva
DirPA: Addressing Prior Shift in Imbalanced Few-shot Crop-type Classification
Real-world agricultural monitoring is often hampered by severe class imbalance and high label acquisition costs, resulting in significant data scarcity. In few-shot learning (FSL) -- a framework sp...
Joana Reuss, Ekaterina Gikalo, Marco Körner
Human-Centered Evaluation of an LLM-Based Process Modeling Copilot: A Mixed-Methods Study with Domain Experts
Integrating Large Language Models (LLMs) into business process management tools promises to democratize Business Process Model and Notation (BPMN) modeling for non-experts. While automated framewor...
Chantale Lauer, Peter Pfeiffer, Nijat Mehdiyev
Development of a Methodology for the Automated Spatial Mapping of Heterogeneous Elastoplastic Properties of Welded Joints
Knowledge of the mechanical properties of materials is required for the design and analysis of engineering products, however, the characterisation of heterogeneous properties using traditional tech...
Robert Hamill, Allan Harte, Aleksander Marek, Fabrice Pierron
A protocol for evaluating robustness to H&E staining variation in computational pathology models
Sensitivity to staining variation remains a major barrier to deploying computational pathology (CPath) models as hematoxylin and eosin (H&E) staining varies across laboratories, requiring systemati...
Lydia A. Schönpflug, Nikki van den Berg, Sonali Andani, Nanda Horeweg, Jurriaan Barkey Wolf, Tjal...
Enhanced Drug-drug Interaction Prediction Using Adaptive Knowledge Integration
Drug-drug interaction event (DDIE) prediction is crucial for preventing adverse reactions and ensuring optimal therapeutic outcomes. However, existing methods often face challenges with imbalanced ...
Pengfei Liu, Jun Tao, Zhixiang Ren