activity
20242026
collaborators

16 papers

cs.DB2026

Semantic Intelligence Against CSAM: The PreventCSA@EU Ontology Framework for Classification and Investigation

Elias Tzortzakakis, Emmanouela Kokolaki, Evangelia Daskalaki +1

This work presents the PreventCSA@EU ontology, a semantically grounded framework designed to support the identification, classification, annotation, and analysis of online Child Se…

cs.SE2026

VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents

JunJia Guo, Yuhang Yao, Jiawei +2

We present VISTA (VIsual Spec-To-App Benchmark), a benchmark for evaluating the end-to-end web-app generation capabilities of LLM-based agents. Unlike prior code generation benchma…

cs.LG2026

Looped World Models

Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang +28

Current world models face a fundamental tension: faithful long-horizon simulation demands deep computation, but deeper models are expensive to deploy and prone to compounding error…

cs.CL2026

Not All Skills Help: Measuring and Repairing Agent Knowledge

Yixuan Wang, Yiyang Zhou, Yiming Liang +4

LLM agents can improve without weight updates by accumulating natural-language skills from experience, but current systems entrust every decision about which skills to keep and how…

cs.AI2026

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

Jiaqi Liu, Shi Qiu, Mairui Li +33

Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail…

cs.CV2026

Seeing without Looking: Do Vision-Language Benchmarks Really Test Vision?

Zixuan Lan, Luzhe Sun, Matthew R. Walter +1

Benchmark accuracy is often implicitly assumed to reflect grounded visual understanding in vision-language models (VLMs), yet it remains unclear to what extent such scores truly re…