Institution profile

University of Nottingham

Academic institutioneurope · gb
Official website
Research library274linked papers
Opportunities0open roles
Selected work

Representative Papers

AI chatbots versus human healthcare professionals: a systematic review and meta-analysis of empathy in patient care

Jun 09, 2025medRxiv

This study addresses the inconsistent and fragmented findings in current literature regarding the empathic performance of AI chatbots compared to human healthcare professionals. For the first time, it employs a systematic review and random-effects meta-analysis to quantitatively compare empathy in medical text-based interactions between large language model–based AI systems (e.g., ChatGPT-3.5/4) and humans. The analysis synthesizes data from 15 empirical studies published in 2023–2024, with risk of bias assessed using the ROBINS-I tool. Results demonstrate that AI significantly outperforms humans in empathy ratings (standardized mean difference = 0.87, 95% CI: 0.54–1.20, P < 0.00001), corresponding to an approximate two-point increase on a 10-point scale. This reveals a novel phenomenon wherein AI is perceived as more empathetic than human clinicians in specific healthcare communication contexts.

9 citations1 influentialRead paper

2-Coherent Internal Models of Homotopical Type Theory

Feb 28, 2025arXiv.org

Homotopy Type Theory (HoTT) lacks a unified semantic framework for internal model theory. Method: We introduce *wild higher Categories with Families* (wild higher CwFs), generalizing classical CwFs via a novel, first-defined *split 2-compatibility* condition. Syntax and standard models—e.g., universe types—are uniformly modeled as 2-compatible wild higher CwFs, and their internalized reflection is constructed. The semantics integrates higher category theory, precompatibility structures, and 2-compatible reflection techniques. Contribution: We achieve the first strictly 2-compatible internal reflection of HoTT within itself, establishing an internalized mapping from syntax to the universe model. This yields a coherence-sufficient internal model theory for dependent type theory, naturally subsuming lower-dimensional higher CwFs and container models as special cases. Our work advances the self-explanatory paradigm in type theory by providing a robust, internally definable semantic foundation for HoTT.

1 citations1 influentialRead paper

ERL-MPP: Evolutionary Reinforcement Learning with Multi-head Puzzle Perception for Solving Large-scale Jigsaw Puzzles of Eroded Gaps

Apr 11, 2025AAAI Conference on Artificial Intelligence

To address local misalignment and global structural instability caused by corrosive inter-piece gaps in large-scale jigsaw puzzle reconstruction, this paper proposes a joint framework comprising a Multi-Head Puzzle-Aware Network (MPPN) and Evolutionary Reinforcement Learning (EvoRL). MPPN employs a shared encoder with multiple puzzle-heads to extract gap-robust features, while integrating a discriminative head and an Actor-Critic architecture to model local assembly states. EvoRL introduces a history-aware evolutionary policy evaluator to efficiently search the ultra-large swap-action space. Our method achieves state-of-the-art performance on both JPLEG-5 (large-gap) and MIT (large-scale) benchmarks, significantly outperforming prior approaches in reconstruction accuracy and gap robustness. Notably, it is the first end-to-end learnable framework capable of reconstructing large-scale puzzles under severe corrosive gap conditions.

1 citationsRead paper

Optimal Sensor Placement Using Combinations of Hybrid Measurements for Source Localization

May 06, 2024International Radar Conference

This paper addresses the optimal sensor placement problem for static source localization under fusion of heterogeneous measurements—TDOA, RSS, AOA, and TOA. We establish a unified Cramér–Rao bound (CRB) analytical framework and, for the first time, derive and systematically compare the geometric observability constraints characterizing the optimal configurations for each measurement type. Leveraging the A-optimality criterion, we propose a hybrid-measurement-aware cooperative placement strategy, integrating geometric observability modeling with numerical optimization, validated via Monte Carlo simulations. Results demonstrate that the proposed strategy achieves mean-square error (MSE) performance approaching the theoretical CRB lower bound across diverse mixed-measurement combinations. In representative scenarios, it improves localization accuracy by 30%–50% over random or conventional placements, significantly enhancing information complementarity and robustness to measurement uncertainties and source geometry variations.

1 citationsRead paper
Recent publications

Latest Papers