YouZum

Notizie

Notizie

DanaBot takedown shows how agentic AI cut months of SOC analysis to weeks

Agentic AI played a decisive role in dismantling DanaBot, a Russian malware platform responsible for...

CURE: A Reinforcement Learning Framework for Co-Evolving Code and Unit Test Generation in LLMs

Introduction Large Language Models (LLMs) have shown substantial improvements in reasoning and precision through reinforcement...

CTISum: A New Benchmark Dataset For Cyber Threat Intelligence Summarization

arXiv:2408.06576v2 Announce Type: replace Abstract: Cyber Threat Intelligence (CTI) summarization involves generating concise and accurate...

CTGT wins Best Presentation Style award at VB Transform 2025

San Francisco-based CTGT, a startup focused on making AI more trustworthy through feature-level model customization...

Creativity in AI: Progresses and Challenges

arXiv:2410.17218v5 Announce Type: replace-cross Abstract: Creativity is the ability to produce novel, useful, and surprising...

CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought

arXiv:2502.17214v2 Announce Type: replace Abstract: Large language models (LLMs) excel in many tasks but struggle...

Conversation Forests: The Key to Fine Tuning Large Language Models for Multi-Turn Medical Conversations is Branching

arXiv:2507.04099v2 Announce Type: replace Abstract: Fine-tuning methods such as Direct Preference Optimization (DPO) and Group...

Context Selection and Rewriting for Video-based Educational Question Generation

arXiv:2504.19406v2 Announce Type: replace Abstract: Educational question generation (EQG) is a crucial component of intelligent...

Computational Analysis of Character Development in Holocaust Testimonies

arXiv:2412.17063v3 Announce Type: replace Abstract: This work presents a computational approach to analyze character development...

Completing A Systematic Review in Hours instead of Months with Interactive AI Agents

arXiv:2504.14822v2 Announce Type: replace-cross Abstract: Systematic reviews (SRs) are vital for evidence-based practice in high...

Comparison of different Unique hard attention transformer models by the formal languages they can recognize

arXiv:2506.03370v1 Announce Type: cross Abstract: This note is a survey of various results on the...
it_IT