arXiv subjects

Yu Chao

Publications and source records attributed to Yu Chao.

3 recordsLinked to original sources

arXiv2026

DoDTrack: Indoor Mobile Devices Tracking via Difference-of-Doppler

In this paper, the Doppler frequency shift (DFS) is exploited as the only sensing parameter for low-cost indoor mobile device tracking. The existing trajectory tracking methods via DFS of Wi-Fi systems often require the knowledge of the starting position or additional information, like angle-of-arrival (AoA) and time-of-flight (ToF), to recover the trajectory of a moving target. This paper proposes the DoDTrack, a novel Difference-of-Doppler (DoD)-based tracking system, to track an active mobile device using a single receiver with distributed antennas. By comparing the signals received at the distributed receive antennas, which share the oscillator, the DoDs among the antennas can be detected robustly. Then, the reconstruction of the trajectory without prior knowledge of the trajectory starting position can be formulated as a minimum mean square error (MMSE) problem, which can be solved via alternating optimization. Particularly, the starting position and the trajectory shape are updated alternately in the proposed algorithm. In performance validation, we implemented the proposed DoDTrack design on a USRP-X310 platform, and assessed its estimation accuracy with various trajectory shapes in an indoor environment. Experimental results demonstrate that DoDTrack achieves a median tracking error of 0.34 m within a 6 m $\times$ 6 m sensing area, offering a high-precision and low-cost solution for active device tracking.

eess.SP↗

arXiv2025

LLM$\times$MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System

We introduce LLM x MapReduce-V3, a hierarchically modular agent system designed for long-form survey generation. Building on the prior work, LLM x MapReduce-V2, this version incorporates a multi-agent architecture where individual functional components, such as skeleton initialization, digest construction, and skeleton refinement, are implemented as independent model-context-protocol (MCP) servers. These atomic servers can be aggregated into higher-level servers, creating a hierarchically structured system. A high-level planner agent dynamically orchestrates the workflow by selecting appropriate modules based on their MCP tool descriptions and the execution history. This modular decomposition facilitates human-in-the-loop intervention, affording users greater control and customization over the research process. Through a multi-turn interaction, the system precisely captures the intended research perspectives to generate a comprehensive skeleton, which is then developed into an in-depth survey. Human evaluations demonstrate that our system surpasses representative baselines in both content depth and length, highlighting the strength of MCP-based modular planning.

cs.CL↗

arXiv2024

LLM$\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models

Enlarging the context window of large language models (LLMs) has become a crucial research area, particularly for applications involving extremely long texts. In this work, we propose a novel training-free framework for processing long texts, utilizing a divide-and-conquer strategy to achieve comprehensive document understanding. The proposed LLM$\times$MapReduce framework splits the entire document into several chunks for LLMs to read and then aggregates the intermediate answers to produce the final output. The main challenge for divide-and-conquer long text processing frameworks lies in the risk of losing essential long-range information when splitting the document, which can lead the model to produce incomplete or incorrect answers based on the segmented texts. Disrupted long-range information can be classified into two categories: inter-chunk dependency and inter-chunk conflict. We design a structured information protocol to better cope with inter-chunk dependency and an in-context confidence calibration mechanism to resolve inter-chunk conflicts. Experimental results demonstrate that LLM$\times$MapReduce can outperform representative open-source and commercial long-context LLMs, and is applicable to several different models.

cs.CL↗