A Clinician-Friendly Platform for Ophthalmic Image Analysis Without Technical Barriers

Kavli Affiliate: Ting Xu | First 5 Authors: Meng Wang, Tian Lin, Qingshan Hou, Aidi Lin, Jingcheng Wang | Summary: Artificial intelligence (AI) shows remarkable potential in medical imaging diagnostics, but current models typically require retraining when deployed across different clinical centers, limiting their widespread adoption. We introduce GlobeReady, a clinician-friendly AI platform that enables […]


Continue.. A Clinician-Friendly Platform for Ophthalmic Image Analysis Without Technical Barriers

AlignRAG: An Adaptable Framework for Resolving Misalignments in Retrieval-Aware Reasoning of RAG

Kavli Affiliate: Xiang Zhang | First 5 Authors: Jiaqi Wei, Hao Zhou, Xiang Zhang, Di Zhang, Zijie Qiu | Summary: Retrieval-augmented generation (RAG) has emerged as a foundational paradigm for knowledge-grounded text generation. However, existing RAG pipelines often fail to ensure that the reasoning trajectories align with the evidential constraints imposed by retrieved content. In […]


Continue.. AlignRAG: An Adaptable Framework for Resolving Misalignments in Retrieval-Aware Reasoning of RAG

Planet as a Brain: Towards Internet of AgentSites based on AIOS Server

Kavli Affiliate: Xiang Zhang | First 5 Authors: Xiang Zhang, Yongfeng Zhang, , , | Summary: The internet is undergoing a historical transformation from the "Internet of Websites" to the "Internet of AgentSites." While traditional Websites served as the foundation for information hosting and dissemination, a new frontier is emerging where AgentSites serve as the […]


Continue.. Planet as a Brain: Towards Internet of AgentSites based on AIOS Server

Planet as a Brain: Towards Internet of AgentSites based on AIOS Server

Kavli Affiliate: Xiang Zhang | First 5 Authors: Xiang Zhang, Yongfeng Zhang, , , | Summary: The internet is undergoing a historical transformation from the "Internet of Websites" to the "Internet of AgentSites." While traditional Websites served as the foundation for information hosting and dissemination, a new frontier is emerging where AgentSites serve as the […]


Continue.. Planet as a Brain: Towards Internet of AgentSites based on AIOS Server

System of Agentic AI for the Discovery of Metal-Organic Frameworks

Kavli Affiliate: Kristin A. Persson | First 5 Authors: Theo Jaffrelot Inizan, Sherry Yang, Aaron Kaplan, Yen-hsu Lin, Jian Yin | Summary: Generative models and machine learning promise accelerated material discovery in MOFs for CO2 capture and water harvesting but face significant challenges navigating vast chemical spaces while ensuring synthetizability. Here, we present MOFGen, a […]


Continue.. System of Agentic AI for the Discovery of Metal-Organic Frameworks

Accurate Point Defect Energy Levels from Non-Empirical Screened Range-Separated Hybrid Functionals: the Case of Native Vacancies in ZnO

Kavli Affiliate: Jeffrey B. Neaton | First 5 Authors: Sijia Ke, Stephen E. Gant, Leeor Kronik, Jeffrey B. Neaton, | Summary: We use density functional theory (DFT) with non-empirically tuned screened range-separated hybrid (SRSH) functionals to calculate the electronic properties of native zinc and oxygen vacancy point defects in ZnO, and we predict their defect […]


Continue.. Accurate Point Defect Energy Levels from Non-Empirical Screened Range-Separated Hybrid Functionals: the Case of Native Vacancies in ZnO

Towards High-Voltage Cathodes for Zinc-Ion Batteries: Discovery Pipeline and Material Design Rules

Kavli Affiliate: Kristin A. Persson | First 5 Authors: Roberta Pascazio, Qian Chen, Haoming Howard Li, Aaron D. Kaplan, Kristin A. Persson | Summary: Efficient energy storage systems are crucial to address the intermittency of renewable energy sources. As multivalent batteries, Zn-ion batteries (ZIBs), while inherently low voltage, offer a promising low cost alternative to […]


Continue.. Towards High-Voltage Cathodes for Zinc-Ion Batteries: Discovery Pipeline and Material Design Rules

Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection

Kavli Affiliate: Wei Gao | First 5 Authors: Haoming Wang, Boyuan Yang, Xiangyu Yin, Wei Gao, | Summary: Personalization of Large Language Models (LLMs) is important in practical applications to accommodate the individual needs of different mobile users. Due to data privacy concerns, LLM personalization often needs to be locally done at the user’s mobile […]


Continue.. Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection

Measuring Casimir Force Across a Superconducting Transition

Kavli Affiliate: Sander Otte | First 5 Authors: Minxing Xu, Robbie J. G. Elbertse, Ata Keşkekler, Giuseppe Bimonte, Jinwon Lee | Summary: The Casimir effect and superconductivity are foundational quantum phenomena whose interaction remains an open question in physics. How Casimir forces behave across a superconducting transition remains unresolved, owing to the experimental difficulty of […]


Continue.. Measuring Casimir Force Across a Superconducting Transition

AutoStyle-TTS: Retrieval-Augmented Generation based Automatic Style Matching Text-to-Speech Synthesis

Kavli Affiliate: Dan Luo | First 5 Authors: Dan Luo, Chengyuan Ma, Weiqin Li, Jun Wang, Wei Chen | Summary: With the advancement of speech synthesis technology, users have higher expectations for the naturalness and expressiveness of synthesized speech. But previous research ignores the importance of prompt selection. This study proposes a text-to-speech (TTS) framework […]


Continue.. AutoStyle-TTS: Retrieval-Augmented Generation based Automatic Style Matching Text-to-Speech Synthesis