arXiv subjects

XiaoXiao Li

Publications and source records attributed to XiaoXiao Li.

3 recordsLinked to original sources

arXiv2025

EchoAgent: Guideline-Centric Reasoning Agent for Echocardiography Measurement and Interpretation

Purpose: Echocardiographic interpretation requires video-level reasoning and guideline-based measurement analysis, which current deep learning models for cardiac ultrasound do not support. We present EchoAgent, a framework that enables structured, interpretable automation for this domain. Methods: EchoAgent orchestrates specialized vision tools under Large Language Model (LLM) control to perform temporal localization, spatial measurement, and clinical interpretation. A key contribution is a measurement-feasibility prediction model that determines whether anatomical structures are reliably measurable in each frame, enabling autonomous tool selection. We curated a benchmark of diverse, clinically validated video-query pairs for evaluation. Results: EchoAgent achieves accurate, interpretable results despite added complexity of spatiotemporal video analysis. Outputs are grounded in visual evidence and clinical guidelines, supporting transparency and traceability. Conclusion: This work demonstrates the feasibility of agentic, guideline-aligned reasoning for echocardiographic video analysis, enabled by task-specific tools and full video-level automation. EchoAgent sets a new direction for trustworthy AI in cardiac ultrasound.

cs.CV↗

arXiv2025

Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm

In speaker diarization, traditional clustering-based methods remain widely used in real-world applications. However, these methods struggle with the complex distribution of speaker embeddings and overlapping speech segments. To address these limitations, we propose an Overlapping Community Detection method based on Graph Attention networks and the Label Propagation Algorithm (OCDGALP). The proposed framework comprises two key components: (1) a graph attention network that refines speaker embeddings and node connections by aggregating information from neighboring nodes, and (2) a label propagation algorithm that assigns multiple community labels to each node, enabling simultaneous clustering and overlapping community detection. Experimental results show that the proposed method significantly reduces the Diarization Error Rate (DER), achieving a state-of-the-art 15.94% DER on the DIHARD-III dataset without oracle Voice Activity Detection (VAD), and an impressive 11.07% with oracle VAD.

cs.SD↗

arXiv2023

Designs, permutations, and transitive groups

A notion of $t$-designs in the symmetric group on $n$ letters was introduced by Godsil in 1988. In particular $t$-transitive sets of permutations form a $t$-design. We derive special lower bounds for $t=1$ and $t=2$ by a power moment method. For general $n,t$ we give a %linear programming lower bound . For $n\ge 4$ and $t=2,$ this bound is strong enough to show a lower bound on the size of such $t$-designs of $n(n-1)\dots (n-t+1),$ which is best possible when sharply $t$-transitive sets of permutations exist. This shows, in particular, that tight $2$-designs do not exist.

math.CO↗