Protein engineering has evolved from modifying naturally occurring proteins toward modular, computational, and AI-assisted approaches for designing new molecular functions. Chimeric and fusion protein engineering has demonstrated that functional elements from different proteins can be reorganized into novel architectures, while advances in computational design, structure prediction, and artificial intelligence have expanded the sequence and structural space accessible to engineering. Building on these developments, this review examines cross-kingdom chimeric protein engineering as a proposed extension of modular protein engineering in which functionally relevant elements from evolutionarily distant biological systems are deliberately integrated into a single protein architecture. The scientific rationale, potential opportunities, and major design challenges are discussed, with emphasis on protein folding and stability, domain and interface compatibility, linker architecture, regulatory and cellular context, and unintended molecular interactions. The review further considers computational and AI-assisted approaches for donor selection, sequence and structural analysis, architecture design, candidate prioritization, and iterative optimization. However, computational plausibility alone cannot establish biological function experimental validation therefore remains essential, progressing from biochemical and structural characterization to cellular and functional evaluation with appropriate controls. The review also examines India’s capabilities relevant to advanced protein design, including computational biology, structural biology, protein engineering, synthetic biology, and related bio manufacturing, while identifying interdisciplinary integration and specialized expertise as important opportunities. Finally, a framework is proposed to strengthen design build test learn capabilities in India and support systematic investigation of cross-kingdom protein engineering as a scientifically testable research direction.
GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations...
Xiaotian Zhang, Chun-yan Li, Yi Zong et al.· arXiv.org· 216 citations· ⚡17
This work investigates the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection and finds that the MTEs are biased, significantly favoring White-associated names in 85% of cases and female-associated names in only 11.1% of cases.
This paper presents a comprehensive overview of the Ultralytics YOLO family, emphasizing architectural evolution, benchmarking, deployment, and emerging directions from YOLOv5 through YOLO27, and examines detection, segmentation, depth, classification, pose, oriented detection, tracking, export, quantization, and deplo...
The comparison of adopter and non-adopter sample reveals three potential adoption inhibitor, security, data privacy, and portability, which underlines the importance of the technical and security perspectives for research investigating the adoption of technology.
Nattakarn Phaphoom, Xiaofeng Wang, S. Samuel et al.· Journal of Systems and Softw...· 111 citations· ⚡8
A novel threat is unveiled in which attackers steer the RAG system's response by injecting malicious passages into its knowledge base, enabling the attacker to steer the response without altering the user input or modifying the RAG weights.
Jiaqi Xue, Meng Zheng, Yebowen Hu et al.· arXiv.org· 109 citations· ⚡8
This work revisits schema linking when using the latest generation of large language models (LLMs) and finds empirically that newer models are adept at utilizing relevant schema elements during generation even in the presence of large numbers of irrelevant ones.
Karime Maamari, Fadhil Abubaker, Daniel Jaroslawicz et al.· arXiv.org· 109 citations· ⚡19
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.