3 citations · 6 across the 18 of their papers we have counts for
20 papers
TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language Models
Zeyi Shao, Haowen Hua, Jiaxin Zhang +3
Prompt learning adapts vision-language models, such as CLIP, by adjusting a small set of context tokens. However, under few-shot supervision, even moderate label noise can disrupt…
Evolutionary Soups: Evolving Mixture-of-Experts for Multi-Objective LLM Alignment
Lingxiao Kong, Steffen Staab, Cong Yang +2
Large language models are increasingly required to generate responses that satisfy multiple competing objectives. Since optimal trade-offs depend on both user preferences and input…
Automated Construction of FAIR Digital Object Knowledge Graphs from Flat Cultural Heritage Records
Zeyd Boukhers, Lingxiao Kong, Xenophon Zabulis +1
The FAIR Digital Object (FDO) framework mandates that metadata attribute values be expressed as persistent identifiers (PIDs) wherever possible, to produce a fully machine-actionab…
ICAN-Deploy: Identity-Stable Canary Deployment for Safety-Critical Embodied Agents
Xue Qin, Simin Luan, John See +3
Canary deployment routes a fraction of traffic to a new software version, monitors metrics, and rolls back on regression. Mainstream controllers (Argo Rollouts, Spinnaker, Flagger)…
Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with a Proof-of-Concept Evaluation on Embodied Agents
Xue Qin, Simin Luan, John See +3
Systems built from versioned AI components need lifecycle-time governance over how a new module version is admitted, monitored, and withdrawn. Established deployment patterns (cana…
Autonomous FAIR Digital Objects: From Passive Assertions to Active Knowledge
Zeyd Boukhers, Oya Beyan, Cong Yang +1
Scientific knowledge on the Web is published as passive assertions and cannot decide when to validate evidence, reconcile contradictions, or update confidence as findings accumulat…
Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters
Lingxiao Kong, Cong Yang, Oya Deniz Beyan +1
Despite significant advances in Reinforcement Learning (RL), model performance remains highly sensitive to algorithm and hyperparameter configurations, while generalization gaps ac…
RSGen: Enhancing Layout-Driven Remote Sensing Image Generation with Diverse Edge Guidance
Xianbao Hou, Yonghao He, Zeyd Boukhers +4
Diffusion models have significantly mitigated the impact of annotated data scarcity in remote sensing (RS). Although recent approaches have successfully harnessed these models to e…
Multi-Objective Reinforcement Learning for Large Language Model Optimization: Visionary Perspective
Lingxiao Kong, Cong Yang, Oya Deniz Beyan +1
Multi-Objective Reinforcement Learning (MORL) presents significant challenges and opportunities for optimizing multiple objectives in Large Language Models (LLMs). We introduce a M…
MoiréNet: A Compact Dual-Domain Network for Image Demoiréing
Shuwei Guo, Simin Luan, Yan Ke +3
Moiré patterns arise from spectral aliasing between display pixel lattices and camera sensor grids, manifesting as anisotropic, multi-scale artifacts that pose significant challeng…
Towards Systematic Specification and Verification of Fairness Requirements: A Position Paper
Qusai Ramadan, Jukka Ruohonen, Abhishek Tiwari +2
Decisions suggested by improperly designed software systems might be prone to discriminate against people based on protected characteristics, such as gender and ethnicity. Previous…
A Unified Framework for Cultural Heritage Data Historicity and Migration: The ARGUS Approach
Lingxiao Kong, Apostolos Sarris, Miltiadis Polidorou +6
Cultural heritage preservation faces significant challenges in managing diverse, multi-source, and multi-scale data for effective monitoring and conservation. This paper documents…
InstaDA: Augmenting Instance Segmentation Data with Dual-Agent System
Xianbao Hou, Yonghao He, Zeyd Boukhers +4
Acquiring high-quality instance segmentation data is challenging due to the labor-intensive nature of the annotation process and significant class imbalances within datasets. Recen…
Unleashing Semantic and Geometric Priors for 3D Scene Completion
Shiyuan Chen, Wei Sui, Bohao Zhang +3
Camera-based 3D semantic scene completion (SSC) provides dense geometric and semantic perception for autonomous driving and robotic navigation. However, existing methods rely on a…
Exploring the Limits of Model Compression in LLMs: A Knowledge Distillation Study on QA Tasks
Joyeeta Datta, Niclas Doll, Qusai Ramadan +1
Large Language Models (LLMs) have demonstrated outstanding performance across a range of NLP tasks, however, their computational demands hinder their deployment in real-world, reso…
EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning
Lingxiao Kong, Cong Yang, Susanne Neufang +2
Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, in…
ELMTEX: Fine-Tuning Large Language Models for Structured Clinical Information Extraction. A Case Study on Clinical Reports
Aynur Guluzade, Naguib Heiba, Zeyd Boukhers +4
Europe's healthcare systems require enhanced interoperability and digitalization, driving a demand for innovative solutions to process legacy clinical data. This paper presents the…
Comparison of Feature Learning Methods for Metadata Extraction from PDF Scholarly Documents
Zeyd Boukhers, Cong Yang
The availability of metadata for scientific documents is pivotal in propelling scientific knowledge forward and for adhering to the FAIR principles (i.e. Findability, Accessibility…
Large Language Model in Medical Informatics: Direct Classification and Enhanced Text Representations for Automatic ICD Coding
Zeyd Boukhers, AmeerAli Khan, Qusai Ramadan +1
Addressing the complexity of accurately classifying International Classification of Diseases (ICD) codes from medical discharge summaries is challenging due to the intricate nature…
SuperEdge: Towards a Generalization Model for Self-Supervised Edge Detection
Leng Kai, Zhang Zhijie, Liu Jie +4
Edge detection is a fundamental technique in various computer vision tasks. Edges are indeed effectively delineated by pixel discontinuity and can offer reliable structural informa…