Quantum machine learning (QML) is increasingly explored for medical classification, yet its behaviour under subgroup-aware fairness criteria remains understudied. We present an empirical fairness audit of classical and quantum classifiers for medical imaging, assuming QML is not inherently fair. Two scenarios are evalu...
Giovanni dos Santos Franco, Felipe Mahlow, Ellison Fernando Cardoso et al.· 0 citations
Recent work has hypothesised that large language models may represent some concepts as multi-dimensional manifolds instead of single directions. Using these manifolds to interpret or steer representations often assumes that moving along them corresponds to a continuous change in the represented concept. In this work, w...
Diksha Gupta, Rieke Fruengel, Stefan Heimersheim· 0 citations
Language model assistants sometimes change a correct answer when the user suggests a wrong one. The behavior, called sycophancy, is usually attributed to preference-based post-training, yet early measurements found it in pretrained models. We ask where it comes from by measuring it at every available stage of training:...
Jiarui Yao, Shweta Parihar, Nghia Bui et al.· 0 citations
Cone-beam computed tomography (CBCT) is widely used for image-guided radiotherapy, but reducing the number of projections to lower dose and scan time makes reconstruction increasingly ill-posed. We present EUReCA (End-to-end Unified REconstruction across Clinical Acquisitions), a geometry-aware feed-forward model for v...
Jie-Ning Zhu, Cheng-Zhu Zhang, Jason Fan et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Modern agent frameworks allow users to provide Markdown files containing system prompts, tool descriptions, and skill definitions (e.g., SKILL.md), which are incorporated into the agent's context during initialization. In this work, we investigate whether this configuration mechanism can also serve as an injection chan...
Agent skills, reusable instruction packages centred on a SKILL.md file, extend AI agents on demand, and a single line in a widely copied skill reaches every agent that loads it. Some lines are oversight-loosening directives: they tell the agent to proceed without approval, to bypass checks with --no-verify, or to keep...
This work studies context-aware selective transfer learning for multi-well groundwater anomaly forecasting in the Netherlands. Source-domain pretraining can raise average accuracy but is not uniformly reliable: it degrades performance on a substantial fraction of heterogeneous wells. Context-Aware Selective Learning (C...
Yaxuan Wu, Ali Mohammed Mansoor Alsahag, Seyed Sahand Mohammadi Ziabari· 0 citations
A key challenge of RAG systems is retrieving information from enterprise documents created by multiple teams over time, where it is not possible to enrich the information using the latest information and metadata available outside the scope of organizational documentation responsibility. We investigated whether using a...
In machine learning, symbolic reasoning approaches often rely on static architectures that hinder integration into deep neural networks and gradient-based optimization. To address this, we introduce the Native Predicate Neuron, a differentiable logic-reasoning neural module that enriches standard architectures with sym...
Ioannis Konstantoulas, Iliana Loi, Kyriakos Sgarbas· 0 citations
Modern image generators can produce complex visual artifacts, including diagrams, interfaces, and records that combine text, graphics, and layout to convey detailed information. They may refuse requests for overtly harmful imagery yet still generate artifacts that guide dangerous actions or support deception. We call t...
Zi-Hao Zhu, Yuansan Liu, Siwei Lyu et al.· 0 citations
Recent advances in large language models (LLMs) have improved Verilog generation. However, most training pipelines distill natural-language reasoning traces whose intermediate design decisions are weakly structured and are primarily selected according to the correctness of the final generated RTL. We present MCTS-SFT,...
Matthew DeLorenzo, Kevin Tieu, Prithwish Jana et al.· 0 citations
DuQUAD is proposed, a multi-document QA framework that mitigates positional bias through dual-view reasoning and quality-aware evidence pruning, and substantially reducing computational cost compared to existing multi-agent frameworks.
Yeonjun Choi, Seyeong Jeong, Jong Wook Kim et al.· Proceedings of the 2026 Conf...· 0 citations
