1 citations · 3 across the 9 of their papers we have counts for
9 papers
TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding
Sparsh Rastogi, Tanmay Kumar, Baiyu Chen +3
Wearable sensors capture fine-grained motion patterns that support rich behavioral understanding, yet most existing methods reduce these signals to activity labels. Recent LM-based…
AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild
Baiyu Chen, Zechen Li, Wilson Wongso +5
As wearable and mobile devices become increasingly embedded in daily life, they offer a practical way to continuously sense human motion in the wild. But inertial signals are highl…
TrajPrism: A Multi-Task Benchmark for Language-Grounded Urban Trajectory Understanding
Lihuan Li, Wilson Wongso, Baiyu Chen +6
Urban mobility is naturally expressed both as trajectories in space and as natural-language descriptions of travel intent, constraints, and preferences. However, prior work rarely…
TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory Generation
Wilson Wongso, Lihuan Li, Arian Prabowo +4
Generating high-fidelity synthetic GPS trajectories is increasingly important for applications in transportation, urban planning, and what-if scenario simulation, especially as pri…
Resolving Ambiguity in Gaze-Facilitated Visual Assistant Interaction Paradigm
Zeyu Wang, Baiyu Chen, Kun Yan +5
With the rise in popularity of smart glasses, users' attention has been integrated into Vision-Language Models (VLMs) to streamline multi-modal querying in daily scenarios. However…
When Ads Become Profiles: Uncovering the Invisible Risk of Web Advertising at Scale with LLMs
Baiyu Chen, Benjamin Tag, Hao Xue +2
Regulatory limits on explicit targeting have not eliminated algorithmic profiling on the Web, as optimisation systems still adapt ad delivery to users' private attributes. The wide…
ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents
Zechen Li, Baiyu Chen, Hao Xue +1
Motion sensor time-series are central to Human Activity Recognition (HAR), yet conventional approaches are constrained to fixed activity sets and typically require costly parameter…
Multi-Stage Verification-Centric Framework for Mitigating Hallucination in Multi-Modal RAG
Baiyu Chen, Wilson Wongso, Xiaoqian Hu +2
This paper presents the technical solution developed by team CRUISE for the KDD Cup 2025 Meta Comprehensive RAG Benchmark for Multi-modal, Multi-turn (CRAG-MM) challenge. The chall…
COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition
Baiyu Chen, Wilson Wongso, Zechen Li +3
The goal of creating intelligent, human-centered wearable systems for continuous activity understanding faces a fundamental trade-off: Egocentric video-based models capture rich se…