Institution profile

University of Leicester

Academic institutioneurope · gb
Official website
Research library132linked 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

Filtered Approximate Nearest Neighbor Search Cost Estimation

Feb 06, 2026

This work addresses the highly variable search cost in hybrid queries arising from the coupling of vector similarity search and structured attribute filtering, which poses significant challenges for effective optimization. The paper proposes E2E, an end-to-end cost estimation framework that, for the first time, explicitly models the correlation between query vector distributions and attribute selectivity. This approach substantially improves the accuracy of cost prediction for filtered approximate nearest neighbor search. Leveraging this estimator, E2E enables an efficient early-termination strategy that achieves 2–3× retrieval speedup on real-world datasets while maintaining high recall. By integrating a deep learning–based cost model with vector indexing and structured filtering mechanisms, E2E establishes a novel paradigm for hybrid query optimization.

1 citationsRead paper

Fast High-dimensional Approximate Nearest Neighbor Search with Efficient Index Time and Space

Nov 09, 2024arXiv.org

To address the limitations of fixed-bit quantization, accuracy degradation, and high query latency in Approximate k-Nearest Neighbor (AKNN) search within high-dimensional Euclidean spaces, this paper proposes Multi-Granularity Residual Quantization (MRQ). MRQ decouples the number of quantization bits from vector dimensionality for the first time, enhances distance correction accuracy via data distribution modeling, and integrates adaptive vector quantization, data-driven distance correction, efficient quantized distance computation, and error-bound optimization. Compared with state-of-the-art graph-based and quantization-based methods (e.g., RaBitQ), MRQ achieves a threefold speedup in query latency while maintaining identical retrieval accuracy and reducing code length to one-third. This significantly improves index configurability and practical applicability for large-scale AKNN search.

1 citationsRead paper
Recent publications

Latest Papers

MITE-Net: SWaP-Optimized 4K Video Tiny Target Perception for Embodied Edge SAR

Aug 16, 2026

This study addresses feature loss and high-latency bottlenecks in 4K small object perception on edge devices by proposing MITE-Net, a SWaP-optimized cascaded architecture. The method integrates a bio-inspired, learning-free Temporal Motion Region Proposal Network (TTM-RPN) with an ultra-lightweight detection head containing fewer than 0.14M parameters, alongside a standardized SAR-Tiny evaluation benchmark. Deployed on a Jetson AGX Xavier platform, the system achieves real-time 4K processing at 30.33 FPS with a 100% search success rate and merely 3.19W power consumption. Demonstrating significantly superior energy efficiency and recall compared to YOLO baselines, this work effectively overcomes perception limitations under stringent resource constraints.

0 citationsRead paper