Dr Shuxiang Cao

Abstract:

The volume and complexity of scientific literature are expanding rapidly, making it increasingly difficult to extract and synthesise information across studies. This challenge is particularly acute in the biological sciences, where evidence spans multiple levels of organisation and heterogeneous experimental designs. Large Language Model (LLM) pipelines offer a scalable route to evidence synthesis, but many existing approaches lack transparency, modularity, and effective mechanisms for human oversight. We present MetaBeeAI, an open-source, modular pipeline that integrates established LLM techniques into a coherent, auditable workflow for structured data extraction in biology. MetaBeeAI combines modular prompting, multi-pass extraction, and expert-in-the-loop validation within an interface that presents model outputs alongside source text, enabling inspection, correction, and iterative refinement. The pipeline produces machine-readable records of prompts, configurations, and expert annotations, supporting reproducibility and continuous improvement. We apply MetaBeeAI to 924 research papers on bees and pesticides, extracting structured information on species, compounds, exposure designs, and experimental context. Evaluation demonstrates improved consistency, convergence with expert judgement, and robustness across heterogeneous biological studies, highlighting the value of expert-guided refinement. MetaBeeAI provides a transparent and extensible framework for scalable evidence synthesis, supporting reliable integration of LLMs into biological research workflows.

Abstract:

Superconducting quantum circuits are a key platform for advancing quantum information processing and simulation. Scaling efforts currently encounter challenges such as Josephson-junction fabrication yield, design frequency targeting, and long-range crosstalk arising both from spurious microwave modes and intrinsic interactions between qubits. We demonstrate a scalable 4x4 square lattice with low crosstalk, comprising 16 fixed-frequency transmon qubits with nearest-neighbor capacitive coupling that is implemented in a tileable, 3D-integrated circuit architecture with off-chip inductive shunting to mitigate spurious enclosure modes. We report on the design and comprehensive characterization, and show that our implementation achieves targeted device parameters with very low frequency spreads, long-range parasitic couplings and simultaneous single-qubit gate errors across the device. Our results provide a promising pathway toward a scalable superconducting square lattice topology for quantum error correction and simulation.

Abstract:

Artificial intelligence (AI) advancements over the past few years have had an unprecedented and revolutionary impact across everyday application areas. Its significance also extends to technical challenges within science and engineering, including the nascent field of quantum computing (QC). The counterintuitive nature and high-dimensional mathematics of QC make it a prime candidate for AI’s data-driven learning capabilities, and in fact, many of QC’s biggest scaling challenges may ultimately rest on developments in AI. However, bringing leading techniques from AI to QC requires drawing on disparate expertise from arguably two of the most advanced and esoteric areas of computer science. Here we aim to encourage this cross-pollination by reviewing how state-of-the-art AI techniques are already advancing challenges across the hardware and software stack needed to develop useful QC - from device design to applications. We then close by examining its future opportunities and obstacles in this space.