Article-Journal

FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
A prompt-only workflow steering attack and defense for LLM-based multi-agent systems.
PDF Cite DOI arXiv
FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
Quantitative Computational Validation of Nanoscale Interactions between Drug Molecules and Diabetic Wound-Related Proteins for Drug Discovery
An ACS Nano Medicine article combining AI literature mining and nanoscale modeling for diabetic wound drug discovery.
Cite DOI ACS
Quantitative Computational Validation of Nanoscale Interactions between Drug Molecules and Diabetic Wound-Related Proteins for Drug Discovery
GitSearch: Enhancing Community Notes Generation with Gap-Informed Targeted Search
An arXiv preprint on targeted search for Community Notes generation.
PDF Cite Code DOI arXiv
GitSearch: Enhancing Community Notes Generation with Gap-Informed Targeted Search
Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems
An arXiv preprint on history-aware trust modeling for LLM-based multi-agent systems.
PDF Cite DOI arXiv
Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems
What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews
An arXiv preprint on detecting and correcting misleading omissions in multimodal news previews.
PDF Cite Code DOI arXiv
What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews
The Facade of Truth: Uncovering and Mitigating LLM Susceptibility to Deceptive Evidence
An arXiv preprint on LLM susceptibility to deceptive evidence and mitigation through intent shielding.
PDF Cite DOI arXiv
The Facade of Truth: Uncovering and Mitigating LLM Susceptibility to Deceptive Evidence
Misinformation, Disinformation, and Generative AI: Implications for Perception and Policy
A multidisciplinary framework for understanding how generative AI reshapes misinformation creation, consumption, and policy responses.
Cite DOI URL
Misinformation, Disinformation, and Generative AI: Implications for Perception and Policy
Evaluating Sakana's AI Scientist for Autonomous Research: Wishful Thinking or an Emerging Reality Towards 'Artificial Research Intelligence' (ARI)?
An arXiv evaluation of Sakana AI Scientist that identifies limitations in novelty assessment, experiment execution, and generated manuscripts.
Cite DOI URL
Evaluating Sakana's AI Scientist for Autonomous Research: Wishful Thinking or an Emerging Reality Towards 'Artificial Research Intelligence' (ARI)?
KeYric: Unsupervised Keywords Extraction and Expansion from Music for Coherent Lyrics Generation
KeYric improves symbolic-music-to-lyrics generation by extracting and expanding keyword skeletons for coherent, musically matched lyrics.
Cite DOI URL
KeYric: Unsupervised Keywords Extraction and Expansion from Music for Coherent Lyrics Generation
Scientific document processing: challenges for modern learning methods
Neural network models enjoy success on language tasks related to Web documents, including news and Wikipedia articles. However, the …
Cite DOI URL