Institution profile

University of Hamburg

Academic institutioneurope · de
Official website
Research library308linked papers
Opportunities0open roles
Selected work

Representative Papers

Unified Source-Free Domain Adaptation

Mar 12, 2024arXiv.org

Existing source-free domain adaptation (SFDA) methods are constrained to specific settings—e.g., closed-set, open-set, biased-set, or generalized SFDA—and rely on target-domain priors, limiting their applicability and theoretical grounding. Method: This work introduces Unified SFDA, the first formal problem formulation of SFDA that requires neither source data nor target-domain prior knowledge. From a causal perspective, it models the generative relationship between latent variables and decisions, proposing the Latent Causal Factor Discovery (LCFD) framework. LCFD integrates vision-language pretrained models (e.g., CLIP) with a causally motivated information bottleneck objective to achieve theoretically guaranteed representation disentanglement. Contribution/Results: Unified SFDA establishes a general, prior-free SFDA paradigm. It achieves state-of-the-art performance across all major SFDA benchmarks and significantly improves out-of-distribution generalization, demonstrating robustness to unseen domain shifts without access to source data or target annotations.

6 citations1 influentialRead paper

Does GenAI Make Usability Testing Obsolete?

Nov 01, 2024arXiv.org

Traditional usability testing is resource-intensive, posing challenges for small development teams seeking early detection of usability issues in iOS mobile applications. Method: We propose UX-LLM, a novel tool that integrates multimodal large vision-language models (VLMs) into mobile UI analysis—jointly processing interface screenshots and source code to enable code-aware, navigation-path-agnostic identification of subtle usability defects. Contribution/Results: Evaluated via expert assessment and focus groups on two medium-complexity open-source iOS apps, UX-LLM achieves 61–66% precision and 35–38% recall, uncovering previously undetected usability issues. Rather than replacing conventional usability testing, UX-LLM serves as a lightweight, early-stage, and interpretable complement—enhancing efficiency and accessibility of usability assurance without requiring extensive human effort or domain-specific test scripts.

1 citationsRead paper

A Comprehensive Survey on Enterprise Financial Risk Analysis from Big Data Perspective

Nov 28, 2022

This study addresses the lack of systematic integration and up-to-date synthesis in corporate financial risk analysis. We conduct the first comprehensive, big-data-informed systematic review of over 250 representative publications spanning 1968–2023. Methodologically, we propose an interdisciplinary classification framework that bridges financial management and artificial intelligence, structuring methodologies along four dimensions: risk typology, analytical granularity, intelligent modeling paradigms, and evaluation metrics. Our analysis traces evolutionary trajectories, identifying twelve dominant modeling approaches and seven emerging research frontiers. Innovatively, we integrate machine learning, knowledge graphs, text mining, and multi-source heterogeneous data fusion to enhance model dynamism, interpretability, and auditability. The resulting framework provides a rigorous, authoritative reference for researchers and practitioners, advancing financial risk management toward intelligence-driven, real-time, and mechanism-aware decision support.

1 citationsRead paper
Recent publications

Latest Papers