Showing 1–23 of 23 results for author: Chi, G

Dexora: Open-source VLA for High-DoF Bimanual Dexterity

Authors: Zongzheng Zhang, Jingrui Pang, Zhuo Yang, Kun Li, Minwen Liao, Saining Zhang, Guoxuan Chi, Jinbang Guo, Huan-ang Gao, Modi Shi, Dongyun Ge, Yao Mu, Jiayuan Gu, Rui Chen, Hao Dong, Huazhe Xu, Li Yi, Yixin Zhu, Hang Zhao, Pengwei Wang, Shanghang Zhang, Guocai Yao, Jianyu Chen, Hongyang Li, Hao Zhao

Abstract: Vision-Language-Action (VLA) models have recently become a central direction in embodied AI, but current systems are restricted to either dual-gripper control or single-arm dexterous hand manipulation. While low-dimensional gripper control can often be handled with simpler methods, high-dimensional dexterous hand control benefits greatly from full end-to-end VLA learning. In this work, we introduc… ▽ More Vision-Language-Action (VLA) models have recently become a central direction in embodied AI, but current systems are restricted to either dual-gripper control or single-arm dexterous hand manipulation. While low-dimensional gripper control can often be handled with simpler methods, high-dimensional dexterous hand control benefits greatly from full end-to-end VLA learning. In this work, we introduce Dexora, the first open-source VLA system that natively targets dual-arm, dual-hand high-DoF manipulation. We design a hybrid teleoperation pipeline that decouples gross arm kinematics (captured with a custom exoskeleton backpack) from fine finger motion (markerless hand tracking via Apple Vision Pro), and that drives both a physical dual-arm dual-hand platform and an identical MuJoCo digital twin. Using that interface, we assemble a large training corpus: an embodiment-matched synthetic corpus (100K simulated trajectories, 6.5M frames) and a real-world dataset of 10K teleoperated episodes (2.92M frames). To mitigate noisy teleoperation demonstrations, we propose a data-quality-aware training recipe: an offline discriminator provides clip-level weights for diffusion-transformer policy training, down-weighting low-quality demonstrations. Empirically, Dexora outperforms competitive VLA baselines on both basic and dexterous benchmarks (e.g., average dexterous success 66.7% vs. 51.7%), attains 90% success on basic tasks, and shows robust out-of-distribution and cross-embodiment generalization. Ablations confirm the importance of real data and the discriminator for dexterity. △ Less

Submitted 18 May, 2026; originally announced May 2026.

Comments: Accpeted by ICRA 2026

Unified Map Prior Encoder for Mapping and Planning

Authors: Zongzheng Zhang, Sizhe Zou, Guantian Zheng, Zhenxin Zhu, Yu Gao, Guoxuan Chi, Shuo Wang, Yuwen Heng, Zhigang Sun, Yiru Wang, Hao Sun, Chao Ma, Zhen Li, Anqing Jiang, Hao Zhao

Abstract: Online mapping and end-to-end (E2E) planning in autonomous driving remain largely sensor-centric, leaving rich map priors, including HD/SD vector maps, rasterized SD maps, and satellite imagery, underused because of heterogeneity, pose drift, and inconsistent availability at test time. We present UMPE, a Unified Map Prior Encoder that can ingest any subset of four priors and fuse them with BEV fea… ▽ More Online mapping and end-to-end (E2E) planning in autonomous driving remain largely sensor-centric, leaving rich map priors, including HD/SD vector maps, rasterized SD maps, and satellite imagery, underused because of heterogeneity, pose drift, and inconsistent availability at test time. We present UMPE, a Unified Map Prior Encoder that can ingest any subset of four priors and fuse them with BEV features for both mapping and planning. UMPE has two branches. The vector encoder pre-aligns HD/SD polylines with a frame-wise SE(2) correction, encodes points via multi-frequency sinusoidal features, and produces polyline tokens with confidence scores. BEV queries then apply cross-attention with confidence bias, followed by normalized channel-wise gating to avoid length imbalance and softly down-weight uncertain sources. The raster encoder shares a ResNet-18 backbone conditioned by FiLM with scaling and shift at every stage, performs SE(2) micro-alignment, and injects priors through zero-initialized residual fusion, so the network starts from a do-no-harm baseline and learns to add only useful prior evidence. A vector-then-raster fusion order reflects the inductive bias of geometry first, appearance second. On nuScenes mapping, UMPE lifts MapTRv2 from 61.5 to 67.4 mAP (+5.9) and MapQR from 66.4 to 71.7 mAP (+5.3). On Argoverse2, UMPE adds +4.1 mAP over strong baselines. UMPE is compositional: when trained with all priors, it outperforms single-prior models even when only one prior is available at test time, demonstrating powerset robustness. For E2E planning with the VAD backbone on nuScenes, UMPE reduces trajectory error from 0.72 to 0.42 m L2 on average (-0.30 m) and collision rate from 0.22% to 0.12% (-0.10%), surpassing recent prior-injection methods. These results show that a unified, alignment-aware treatment of heterogeneous map priors yields better mapping and better planning. △ Less

Submitted 4 May, 2026; originally announced May 2026.

Comments: Accpeted by ICRA 2026

Cross-Modal Generation: From Commodity WiFi to High-Fidelity mmWave and RFID Sensing

Authors: Zhixiong Yang, Long Jing, Yao Li, Shuli Cheng, Guoxuan Chi, Chenyu Wen

Abstract: AIGC has shown remarkable success in CV and NLP, and has recently demonstrated promising potential in the wireless domain. However, significant data imbalance exists across RF modalities, with abundant WiFi data but scarce mmWave and RFID data due to high acquisition cost. This makes it difficult to train high-quality generative models for these data-scarce modalities. In this work, we propose RF-… ▽ More AIGC has shown remarkable success in CV and NLP, and has recently demonstrated promising potential in the wireless domain. However, significant data imbalance exists across RF modalities, with abundant WiFi data but scarce mmWave and RFID data due to high acquisition cost. This makes it difficult to train high-quality generative models for these data-scarce modalities. In this work, we propose RF-CMG, a diffusion-based cross-modal generative method that leverages data-rich WiFi signals to synthesize high-fidelity RF data for scarce modalities including mmWave and RFID. The key insight of RF-CMG is to decouple cross-modal generation into high-frequency guidance and low-frequency constraint, which respectively learn high-frequency distribution from limited target modality data and preserve the underlying physical structure via low-frequency constraints during generation. On this basis, we introduce a Modality-Guided Embedding (MGE) module to steer the reverse diffusion trajectory toward the target high-frequency distribution, and a Low-Frequency Modality Consistency (LFMC) module to progressively enforce low-frequency constraints to suppress the accumulation of source-modality structural biases during inference, enabling high-quality target-modality generation. Performance comparison with several prevalent generative models demonstrates that RF-CMG achieves superior performance in synthesizing RFID and mmWave signals. We further showcase the effectiveness of the data generated by RF-CMG in gesture recognition tasks, and analyze the impact of the proportion of synthetic data on downstream performance. △ Less

Submitted 17 April, 2026; originally announced April 2026.

AlphaEval: Evaluating Agents in Production

Authors: Pengrui Lu, Bingyu Xu, Wenjun Zhang, Shengjia Hua, Xuanjian Gao, Ranxiang Ge, Lyumanshan Ye, Linxuan Wu, Yiran Li, Junfei Fish Yu, Yibo Zhang, Ruixin Li, Manxiang Li, Xiao Han, Xiaocong Zhou, Guangyao Chi, Zisheng Chen, Kaishen Chen, Kun Wang, Qihua Xu, Fengyue Meng, Yuchen Ni, Jiajun Li, Jinxiu Liu, Danfeng Zhang , et al. (2 additional authors not shown)

Abstract: The rapid deployment of AI agents in commercial settings has outpaced the development of evaluation methodologies that reflect production realities. Existing benchmarks measure agent capabilities through retrospectively curated tasks with well-specified requirements and deterministic metrics -- conditions that diverge fundamentally from production environments where requirements contain implicit c… ▽ More The rapid deployment of AI agents in commercial settings has outpaced the development of evaluation methodologies that reflect production realities. Existing benchmarks measure agent capabilities through retrospectively curated tasks with well-specified requirements and deterministic metrics -- conditions that diverge fundamentally from production environments where requirements contain implicit constraints, inputs are heterogeneous multi-modal documents with information fragmented across sources, tasks demand undeclared domain expertise, outputs are long-horizon professional deliverables, and success is judged by domain experts whose standards evolve over time. We present AlphaEval, a production-grounded benchmark of 94 tasks sourced from seven companies deploying AI agents in their core business, spanning six O*NET (Occupational Information Network) domains. Unlike model-centric benchmarks, AlphaEval evaluates complete agent products -- Claude Code, Codex, etc. -- as commercial systems, capturing performance variations invisible to model-level evaluation. Our evaluation framework covers multiple paradigms (LLM-as-a-Judge, reference-driven metrics, formal verification, rubric-based assessment, automated UI testing, etc.), with individual domains composing multiple paradigms. Beyond the benchmark itself, we contribute a requirement-to-benchmark construction framework -- a systematic methodology that transforms authentic production requirements into executable evaluation tasks in minimal time. This framework standardizes the entire pipeline from requirement to evaluation, providing a reproducible, modular process that any organization can adopt to construct production-grounded benchmarks for their own domains. △ Less

Submitted 13 April, 2026; originally announced April 2026.

SwiftVLM: Efficient Vision-Language Model Inference via Cross-Layer Token Bypass

Authors: Chen Qian, Xinran Yu, Danyang Li, Guoxuan Chi, Zheng Yang, Qiang Ma, Xin Miao

Abstract: Visual token pruning is a promising approach for reducing the computational cost of vision-language models (VLMs), and existing methods often rely on early pruning decisions to improve efficiency. While effective on coarse-grained reasoning tasks, they suffer from significant performance degradation on tasks requiring fine-grained visual details. Through layer-wise analysis, we reveal substantial… ▽ More Visual token pruning is a promising approach for reducing the computational cost of vision-language models (VLMs), and existing methods often rely on early pruning decisions to improve efficiency. While effective on coarse-grained reasoning tasks, they suffer from significant performance degradation on tasks requiring fine-grained visual details. Through layer-wise analysis, we reveal substantial discrepancies in visual token importance across layers, showing that tokens deemed unimportant at shallow layers can later become highly relevant for text-conditioned reasoning. To avoid irreversible critical information loss caused by premature pruning, we introduce a new pruning paradigm, termed bypass, which preserves unselected visual tokens and forwards them to subsequent pruning stages for re-evaluation. Building on this paradigm, we propose SwiftVLM, a simple and training-free method that performs pruning at model-specific layers with strong visual token selection capability, while enabling independent pruning decisions across layers. Experiments across multiple VLMs and benchmarks demonstrate that SwiftVLM consistently outperforms existing pruning strategies, achieving superior accuracy-efficiency trade-offs and more faithful visual token selection behavior. △ Less

Submitted 3 February, 2026; originally announced February 2026.

Generative AI Meets Wireless Sensing: Towards Wireless Foundation Model

Authors: Zheng Yang, Guoxuan Chi, Chenshu Wu, Hanyu Liu, Yuchong Gao, Yunhao Liu, Jie Xu, Tony Xiao Han

Abstract: Generative Artificial Intelligence (GenAI) has made significant advancements in fields such as computer vision (CV) and natural language processing (NLP), demonstrating its capability to synthesize high-fidelity data and improve generalization. Recently, there has been growing interest in integrating GenAI into wireless sensing systems. By leveraging generative techniques such as data augmentation… ▽ More Generative Artificial Intelligence (GenAI) has made significant advancements in fields such as computer vision (CV) and natural language processing (NLP), demonstrating its capability to synthesize high-fidelity data and improve generalization. Recently, there has been growing interest in integrating GenAI into wireless sensing systems. By leveraging generative techniques such as data augmentation, domain adaptation, and denoising, wireless sensing applications, including device localization, human activity recognition, and environmental monitoring, can be significantly improved. This survey investigates the convergence of GenAI and wireless sensing from two complementary perspectives. First, we explore how GenAI can be integrated into wireless sensing pipelines, focusing on two modes of integration: as a plugin to augment task-specific models and as a solver to directly address sensing tasks. Second, we analyze the characteristics of mainstream generative models, such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and diffusion models, and discuss their applicability and unique advantages across various wireless sensing tasks. We further identify key challenges in applying GenAI to wireless sensing and outline a future direction toward a wireless foundation model: a unified, pre-trained design capable of scalable, adaptable, and efficient signal understanding across diverse sensing tasks. △ Less

Submitted 18 September, 2025; originally announced September 2025.

Adaptive Knowledge Distillation for Device-Directed Speech Detection

Authors: Hyung Gun Chi, Florian Pesce, Wonil Chang, Oggi Rudovic, Arturo Argueta, Stefan Braun, Vineet Garg, Ahmed Hussen Abdelaziz

Abstract: Device-directed speech detection (DDSD) is a binary classification task that separates the user's queries to a voice assistant (VA) from background speech or side conversations. This is important for achieving naturalistic user experience. To this end, we propose knowledge distillation (KD) to enhance DDSD accuracy while ensuring efficient deployment. Specifically, we introduce a novel adaptive KD… ▽ More Device-directed speech detection (DDSD) is a binary classification task that separates the user's queries to a voice assistant (VA) from background speech or side conversations. This is important for achieving naturalistic user experience. To this end, we propose knowledge distillation (KD) to enhance DDSD accuracy while ensuring efficient deployment. Specifically, we introduce a novel adaptive KD method that transfers knowledge from general representations of an ASR large pre-trained acoustic encoder (teacher). We apply task-specific adapters, on top of the (frozen) teacher encoder, trained jointly with the student model on DDSD. We demonstrate that the proposed adaptive KD outperforms the student model without distillation in the keyword and keyword-free (follow-up) invocations, with an improvement of +26% and +19% in terms of Equal Error Rate, respectively. We also show that this approach generalizes across the transformer and conformer-based model architectures. △ Less

Submitted 4 August, 2025; originally announced August 2025.

Comments: 5 pages, 2 figures, Interspeech accepted

Delving into Mapping Uncertainty for Mapless Trajectory Prediction

Authors: Zongzheng Zhang, Xuchong Qiu, Boran Zhang, Guantian Zheng, Xunjiang Gu, Guoxuan Chi, Huan-ang Gao, Leichen Wang, Ziming Liu, Xinrun Li, Igor Gilitschenski, Hongyang Li, Hang Zhao, Hao Zhao

Abstract: Recent advances in autonomous driving are moving towards mapless approaches, where High-Definition (HD) maps are generated online directly from sensor data, reducing the need for expensive labeling and maintenance. However, the reliability of these online-generated maps remains uncertain. While incorporating map uncertainty into downstream trajectory prediction tasks has shown potential for perfor… ▽ More Recent advances in autonomous driving are moving towards mapless approaches, where High-Definition (HD) maps are generated online directly from sensor data, reducing the need for expensive labeling and maintenance. However, the reliability of these online-generated maps remains uncertain. While incorporating map uncertainty into downstream trajectory prediction tasks has shown potential for performance improvements, current strategies provide limited insights into the specific scenarios where this uncertainty is beneficial. In this work, we first analyze the driving scenarios in which mapping uncertainty has the greatest positive impact on trajectory prediction and identify a critical, previously overlooked factor: the agent's kinematic state. Building on these insights, we propose a novel Proprioceptive Scenario Gating that adaptively integrates map uncertainty into trajectory prediction based on forecasts of the ego vehicle's future kinematics. This lightweight, self-supervised approach enhances the synergy between online mapping and trajectory prediction, providing interpretability around where uncertainty is advantageous and outperforming previous integration methods. Additionally, we introduce a Covariance-based Map Uncertainty approach that better aligns with map geometry, further improving trajectory prediction. Extensive ablation studies confirm the effectiveness of our approach, achieving up to 23.6% improvement in mapless trajectory prediction performance over the state-of-the-art method using the real-world nuScenes driving dataset. Our code, data, and models are publicly available at https://github.com/Ethan-Zheng136/Map-Uncertainty-for-Trajectory-Prediction. △ Less

Submitted 24 July, 2025; originally announced July 2025.

Comments: Accepted to IROS 2025, Project Page: https://ethan-zheng136.github.io/Dev-Unc/

DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective

Authors: Hyung Gun Chi, Zakaria Aldeneh, Tatiana Likhomanenko, Oggi Rudovic, Takuya Higuchi, Li-Wei Chen, Shinji Watanabe, Ahmed Hussen Abdelaziz

Abstract: We introduce DiceHuBERT, a knowledge distillation framework for compressing HuBERT, a widely used self-supervised learning (SSL)-based speech foundation model. Unlike existing distillation methods that rely on layer-wise and feature-wise mapping between teacher and student models, DiceHuBERT leverages HuBERT's iterative self-distillation mechanism by directly replacing the original model with a st… ▽ More We introduce DiceHuBERT, a knowledge distillation framework for compressing HuBERT, a widely used self-supervised learning (SSL)-based speech foundation model. Unlike existing distillation methods that rely on layer-wise and feature-wise mapping between teacher and student models, DiceHuBERT leverages HuBERT's iterative self-distillation mechanism by directly replacing the original model with a student model. This replacement allows the student to be trained using the same SSL objective used when pre-training HuBERT, eliminating the need for additional modules or architectural constraints. Experimental results on SUPERB show that DiceHuBERT consistently outperforms existing distillation methods, improving phoneme recognition performance by over 21% and ASR performance by more than 14%. Furthermore, DiceHuBERT demonstrates competitive performance across multiple tasks, highlighting its clear advantage. △ Less

Submitted 24 June, 2025; originally announced July 2025.

Comments: 5 pages, 1 figure, interspeech accepted paper

Measuring Global Migration Flows using Online Data

Authors: Guanghua Chi, Guy J. Abel, Drew Johnston, Eugenia Giraudy, Mike Bailey

Abstract: Existing estimates of human migration are limited in their scope, reliability, and timeliness, prompting the United Nations and the Global Compact on Migration to call for improved data collection. Using privacy protected records from three billion Facebook users, we estimate country-to-country migration flows at monthly granularity for 181 countries, accounting for selection into Facebook usage.… ▽ More Existing estimates of human migration are limited in their scope, reliability, and timeliness, prompting the United Nations and the Global Compact on Migration to call for improved data collection. Using privacy protected records from three billion Facebook users, we estimate country-to-country migration flows at monthly granularity for 181 countries, accounting for selection into Facebook usage. Our estimates closely match high-quality measures of migration where available but can be produced nearly worldwide and with less delay than alternative methods. We estimate that 39.1 million people migrated internationally in 2022 (0.63% of the population of the countries in our sample). Migration flows significantly changed during the COVID-19 pandemic, decreasing by 64% before rebounding in 2022 to a pace 24% above the pre-crisis rate. We also find that migration from Ukraine increased tenfold in the wake of the Russian invasion. To support research and policy interventions, we will release these estimates publicly through the Humanitarian Data Exchange. △ Less

Submitted 15 April, 2025; originally announced April 2025.

Chameleon: Fast-slow Neuro-symbolic Lane Topology Extraction

Authors: Zongzheng Zhang, Xinrun Li, Sizhe Zou, Guoxuan Chi, Siqi Li, Xuchong Qiu, Guoliang Wang, Guantian Zheng, Leichen Wang, Hang Zhao, Hao Zhao

Abstract: Lane topology extraction involves detecting lanes and traffic elements and determining their relationships, a key perception task for mapless autonomous driving. This task requires complex reasoning, such as determining whether it is possible to turn left into a specific lane. To address this challenge, we introduce neuro-symbolic methods powered by vision-language foundation models (VLMs). Existi… ▽ More Lane topology extraction involves detecting lanes and traffic elements and determining their relationships, a key perception task for mapless autonomous driving. This task requires complex reasoning, such as determining whether it is possible to turn left into a specific lane. To address this challenge, we introduce neuro-symbolic methods powered by vision-language foundation models (VLMs). Existing approaches have notable limitations: (1) Dense visual prompting with VLMs can achieve strong performance but is costly in terms of both financial resources and carbon footprint, making it impractical for robotics applications. (2) Neuro-symbolic reasoning methods for 3D scene understanding fail to integrate visual inputs when synthesizing programs, making them ineffective in handling complex corner cases. To this end, we propose a fast-slow neuro-symbolic lane topology extraction algorithm, named Chameleon, which alternates between a fast system that directly reasons over detected instances using synthesized programs and a slow system that utilizes a VLM with a chain-of-thought design to handle corner cases. Chameleon leverages the strengths of both approaches, providing an affordable solution while maintaining high performance. We evaluate the method on the OpenLane-V2 dataset, showing consistent improvements across various baseline detectors. Our code, data, and models are publicly available at https://github.com/XR-Lee/neural-symbolic △ Less

Submitted 10 March, 2025; originally announced March 2025.

Comments: ICRA 2025, Project Page: https://github.com/XR-Lee/neural-symbolic

Rate-Aware Learned Speech Compression

Authors: Jun Xu, Zhengxue Cheng, Guangchuan Chi, Yuhan Liu, Yuelin Hu, Li Song

Abstract: The rapid rise of real-time communication and large language models has significantly increased the importance of speech compression. Deep learning-based neural speech codecs have outperformed traditional signal-level speech codecs in terms of rate-distortion (RD) performance. Typically, these neural codecs employ an encoder-quantizer-decoder architecture, where audio is first converted into laten… ▽ More The rapid rise of real-time communication and large language models has significantly increased the importance of speech compression. Deep learning-based neural speech codecs have outperformed traditional signal-level speech codecs in terms of rate-distortion (RD) performance. Typically, these neural codecs employ an encoder-quantizer-decoder architecture, where audio is first converted into latent code feature representations and then into discrete tokens. However, this architecture exhibits insufficient RD performance due to two main drawbacks: (1) the inadequate performance of the quantizer, challenging training processes, and issues such as codebook collapse; (2) the limited representational capacity of the encoder and decoder, making it difficult to meet feature representation requirements across various bitrates. In this paper, we propose a rate-aware learned speech compression scheme that replaces the quantizer with an advanced channel-wise entropy model to improve RD performance, simplify training, and avoid codebook collapse. We employ multi-scale convolution and linear attention mixture blocks to enhance the representational capacity and flexibility of the encoder and decoder. Experimental results demonstrate that the proposed method achieves state-of-the-art RD performance, obtaining 53.51% BD-Rate bitrate saving in average, and achieves 0.26 BD-VisQol and 0.44 BD-PESQ gains. △ Less

Submitted 21 January, 2025; originally announced January 2025.

RF-Diffusion: Radio Signal Generation via Time-Frequency Diffusion

Authors: Guoxuan Chi, Zheng Yang, Chenshu Wu, Jingao Xu, Yuchong Gao, Yunhao Liu, Tony Xiao Han

Abstract: Along with AIGC shines in CV and NLP, its potential in the wireless domain has also emerged in recent years. Yet, existing RF-oriented generative solutions are ill-suited for generating high-quality, time-series RF data due to limited representation capabilities. In this work, inspired by the stellar achievements of the diffusion model in CV and NLP, we adapt it to the RF domain and propose RF-Dif… ▽ More Along with AIGC shines in CV and NLP, its potential in the wireless domain has also emerged in recent years. Yet, existing RF-oriented generative solutions are ill-suited for generating high-quality, time-series RF data due to limited representation capabilities. In this work, inspired by the stellar achievements of the diffusion model in CV and NLP, we adapt it to the RF domain and propose RF-Diffusion. To accommodate the unique characteristics of RF signals, we first introduce a novel Time-Frequency Diffusion theory to enhance the original diffusion model, enabling it to tap into the information within the time, frequency, and complex-valued domains of RF signals. On this basis, we propose a Hierarchical Diffusion Transformer to translate the theory into a practical generative DNN through elaborated design spanning network architecture, functional block, and complex-valued operator, making RF-Diffusion a versatile solution to generate diverse, high-quality, and time-series RF data. Performance comparison with three prevalent generative models demonstrates the RF-Diffusion's superior performance in synthesizing Wi-Fi and FMCW signals. We also showcase the versatility of RF-Diffusion in boosting Wi-Fi sensing systems and performing channel estimation in 5G networks. △ Less

Submitted 14 April, 2024; originally announced April 2024.

Comments: Accepted by MobiCom 2024

ACM Class: I.2.0

Hands-on Wireless Sensing with Wi-Fi: A Tutorial

Authors: Zheng Yang, Yi Zhang, Guoxuan Chi, Guidong Zhang

Abstract: With the rapid development of wireless communication technology, wireless access points (AP) and internet of things (IoT) devices have been widely deployed in our surroundings. Various types of wireless signals (e.g., Wi-Fi, LoRa, LTE) are filling out our living and working spaces. Previous researches reveal the fact that radio waves are modulated by the spatial structure during the propagation pr… ▽ More With the rapid development of wireless communication technology, wireless access points (AP) and internet of things (IoT) devices have been widely deployed in our surroundings. Various types of wireless signals (e.g., Wi-Fi, LoRa, LTE) are filling out our living and working spaces. Previous researches reveal the fact that radio waves are modulated by the spatial structure during the propagation process (e.g., reflection, diffraction, and scattering) and superimposed on the receiver. This observation allows us to reconstruct the surrounding environment based on received wireless signals, called "wireless sensing". Wireless sensing is an emerging technology that enables a wide range of applications, such as gesture recognition for human-computer interaction, vital signs monitoring for health care, and intrusion detection for security management. Compared with other sensing paradigms, such as vision-based and IMU-based sensing, wireless sensing solutions have unique advantages such as high coverage, pervasiveness, low cost, and robustness under adverse light and texture scenarios. Besides, wireless sensing solutions are generally lightweight in terms of both computation overhead and device size. This tutorial takes Wi-Fi sensing as an example. It introduces both the theoretical principles and the code implementation of data collection, signal processing, features extraction, and model design. In addition, this tutorial highlights state-of-the-art deep learning models (e.g., CNN, RNN, and adversarial learning models) and their applications in wireless sensing systems. We hope this tutorial will help people in other research fields to break into wireless sensing research and learn more about its theories, designs, and implementation skills, promoting prosperity in the wireless sensing research field. △ Less

Submitted 19 June, 2022; originally announced June 2022.

Global Tweet Mentions of COVID-19

Authors: Guangqing Chi, Junjun Yin, M. Luke Smith, Yosef Bodovski

Abstract: Background. After a year and half and over 4 million deaths, the COVID-19 pandemic continues to be widespread, and its related topics continue to dominate the global media. Although COVID-19 diagnoses have been well monitored, neither the impacts of the disease on human behavior and social dynamics nor the effectiveness of policy interventions aimed at its containment are fully understood. Monitor… ▽ More Background. After a year and half and over 4 million deaths, the COVID-19 pandemic continues to be widespread, and its related topics continue to dominate the global media. Although COVID-19 diagnoses have been well monitored, neither the impacts of the disease on human behavior and social dynamics nor the effectiveness of policy interventions aimed at its containment are fully understood. Monitoring the spatial and temporal patterns of behavior, social dynamics and policy - and then their interrelations - can provide critical information for preparatory action and effective response. Methods. Here we present an open-source dataset of 1.92 million keyword-selected Twitter posts, updated weekly from January 2020 to present, along with a dynamic dashboard showing totals at national and subnational administrative divisions. Results. The dashboard presents 100% of the geotagged tweets that contain keywords or hashtags related COVID-19. We validated our inclusion criteria using a machine learning-based text classifier and found that 88% of the selected tweets were correctly labeled as related to COVID-19. With this information we tested the correlation between tweets and covid diagnosis from January 1, 2020 through December 31, 2020 and see a decreasing correlation across time. Conclusions. With emerging COVID variants but ongoing vaccine hesitancy and resistance, this dataset could be used by researchers to study numerous aspects of COVID-19 and provide valuable insights for preparing future pandemics. △ Less

Submitted 17 August, 2021; v1 submitted 13 August, 2021; originally announced August 2021.

Micro-Estimates of Wealth for all Low- and Middle-Income Countries

Authors: Guanghua Chi, Han Fang, Sourav Chatterjee, Joshua E. Blumenstock

Abstract: Many critical policy decisions, from strategic investments to the allocation of humanitarian aid, rely on data about the geographic distribution of wealth and poverty. Yet many poverty maps are out of date or exist only at very coarse levels of granularity. Here we develop the first micro-estimates of wealth and poverty that cover the populated surface of all 135 low and middle-income countries (L… ▽ More Many critical policy decisions, from strategic investments to the allocation of humanitarian aid, rely on data about the geographic distribution of wealth and poverty. Yet many poverty maps are out of date or exist only at very coarse levels of granularity. Here we develop the first micro-estimates of wealth and poverty that cover the populated surface of all 135 low and middle-income countries (LMICs) at 2.4km resolution. The estimates are built by applying machine learning algorithms to vast and heterogeneous data from satellites, mobile phone networks, topographic maps, as well as aggregated and de-identified connectivity data from Facebook. We train and calibrate the estimates using nationally-representative household survey data from 56 LMICs, then validate their accuracy using four independent sources of household survey data from 18 countries. We also provide confidence intervals for each micro-estimate to facilitate responsible downstream use. These estimates are provided free for public use in the hope that they enable targeted policy response to the COVID-19 pandemic, provide the foundation for new insights into the causes and consequences of economic development and growth, and promote responsible policymaking in support of the Sustainable Development Goals. △ Less

Submitted 15 April, 2021; originally announced April 2021.

ACM Class: I.2; J.4; K.4

A multi-modal approach towards mining social media data during natural disasters -- a case study of Hurricane Irma

Authors: Somya D. Mohanty, Brown Biggers, Saed Sayedahmed, Nastaran Pourebrahim, Evan B. Goldstein, Rick Bunch, Guangqing Chi, Fereidoon Sadri, Tom P. McCoy, Arthur Cosby

Abstract: Streaming social media provides a real-time glimpse of extreme weather impacts. However, the volume of streaming data makes mining information a challenge for emergency managers, policy makers, and disciplinary scientists. Here we explore the effectiveness of data learned approaches to mine and filter information from streaming social media data from Hurricane Irma's landfall in Florida, USA. We u… ▽ More Streaming social media provides a real-time glimpse of extreme weather impacts. However, the volume of streaming data makes mining information a challenge for emergency managers, policy makers, and disciplinary scientists. Here we explore the effectiveness of data learned approaches to mine and filter information from streaming social media data from Hurricane Irma's landfall in Florida, USA. We use 54,383 Twitter messages (out of 784K geolocated messages) from 16,598 users from Sept. 10 - 12, 2017 to develop 4 independent models to filter data for relevance: 1) a geospatial model based on forcing conditions at the place and time of each tweet, 2) an image classification model for tweets that include images, 3) a user model to predict the reliability of the tweeter, and 4) a text model to determine if the text is related to Hurricane Irma. All four models are independently tested, and can be combined to quickly filter and visualize tweets based on user-defined thresholds for each submodel. We envision that this type of filtering and visualization routine can be useful as a base model for data capture from noisy sources such as Twitter. The data can then be subsequently used by policy makers, environmental managers, emergency managers, and domain scientists interested in finding tweets with specific attributes to use during different stages of the disaster (e.g., preparedness, response, and recovery), or for detailed research. △ Less

Submitted 2 January, 2021; originally announced January 2021.

Comments: 46 pages, 11 Figures

Evolutionary Gait Transfer of Multi-Legged Robots in Complex Terrains

Authors: Min Jiang, Guokun Chi, Geqiang Pan, Shihui Guo, Kay Chen Tan

Abstract: Robot gait optimization is the task of generating an optimal control trajectory under various internal and external constraints. Given the high dimensions of control space, this problem is particularly challenging for multi-legged robots walking in complex and unknown environments. Existing literatures often regard the gait generation as an optimization problem and solve the gait optimization from… ▽ More Robot gait optimization is the task of generating an optimal control trajectory under various internal and external constraints. Given the high dimensions of control space, this problem is particularly challenging for multi-legged robots walking in complex and unknown environments. Existing literatures often regard the gait generation as an optimization problem and solve the gait optimization from scratch for robots walking in a specific environment. However, such approaches do not consider the use of pre-acquired knowledge which can be useful in improving the quality and speed of motion generation in complex environments. To address the issue, this paper proposes a transfer learning-based evolutionary framework for multi-objective gait optimization, named Tr-GO. The idea is to initialize a high-quality population by using the technique of transfer learning, so any kind of population-based optimization algorithms can be seamlessly integrated into this framework. The advantage is that the generated gait can not only dynamically adapt to different environments and tasks, but also simultaneously satisfy multiple design specifications (e.g., speed, stability). The experimental results show the effectiveness of the proposed framework for the gait optimization problem based on three multi-objective evolutionary algorithms: NSGA-II, RM-MEDA and MOPSO. When transferring the pre-acquired knowledge from the plain terrain to various inclined and rugged ones, the proposed Tr-GO framework accelerates the evolution process by a minimum of 3-4 times compared with non-transferred scenarios. △ Less

Submitted 24 December, 2020; originally announced December 2020.

Characterizing People's Daily Activity Patterns in the Urban Environment: A Mobility Network Approach with Geographic Context-Aware Twitter Data

Authors: Junjun Yin, Guangqing Chi

Abstract: People's daily activities in the urban environment are complex and vary by individuals. Existing studies using mobile phone data revealed distinct and recurrent transitional activity patterns, known as mobility motifs, in people's daily lives. However, the limitation in using only a few inferred activity types hinders our ability to examine general patterns in detail. We proposed a mobility networ… ▽ More People's daily activities in the urban environment are complex and vary by individuals. Existing studies using mobile phone data revealed distinct and recurrent transitional activity patterns, known as mobility motifs, in people's daily lives. However, the limitation in using only a few inferred activity types hinders our ability to examine general patterns in detail. We proposed a mobility network approach with geographic context-aware Twitter data to investigate granular daily activity patterns in the urban environment. We first utilized publicly accessible geo-located tweets to track the movements of individuals in two major U.S. cities: Chicago and Greater Boston, where each recorded location is associated with its closest land use parcel to enrich its geographic context. A direct mobility network represents the daily location history of the selected active users, where the nodes are physical places with semantically labeled activity types, and the edges represent the transitions. Analyzing the isomorphic structure of the mobility networks uncovered 16 types of location-based motifs, which describe over 83% of the networks in both cities and are comparable to those from previous studies. With detailed and semantically labeled transitions between every two activities, we further dissected the general location-based motifs into activity-based motifs, where 16 common activity-based motifs describe more than 57% transitional behaviors in the daily activities in the two cities. The integration of geographic context from the synthesis of geo-located Twitter data with land use parcels enables us to reveal unique activity motifs that form the fundamental elements embedded in complex urban activities. △ Less

Submitted 12 December, 2020; originally announced December 2020.

Comments: 39 pages, 9 figures

A first look at COVID-19 information and misinformation sharing on Twitter

Authors: Lisa Singh, Shweta Bansal, Leticia Bode, Ceren Budak, Guangqing Chi, Kornraphop Kawintiranon, Colton Padden, Rebecca Vanarsdall, Emily Vraga, Yanchen Wang

Abstract: Since December 2019, COVID-19 has been spreading rapidly across the world. Not surprisingly, conversation about COVID-19 is also increasing. This article is a first look at the amount of conversation taking place on social media, specifically Twitter, with respect to COVID-19, the themes of discussion, where the discussion is emerging from, myths shared about the virus, and how much of it is conne… ▽ More Since December 2019, COVID-19 has been spreading rapidly across the world. Not surprisingly, conversation about COVID-19 is also increasing. This article is a first look at the amount of conversation taking place on social media, specifically Twitter, with respect to COVID-19, the themes of discussion, where the discussion is emerging from, myths shared about the virus, and how much of it is connected to other high and low quality information on the Internet through shared URL links. Our preliminary findings suggest that a meaningful spatio-temporal relationship exists between information flow and new cases of COVID-19, and while discussions about myths and links to poor quality information exist, their presence is less dominant than other crisis specific themes. This research is a first step toward understanding social media conversation about COVID-19. △ Less

Submitted 30 March, 2020; originally announced March 2020.

Comments: 24 pages, 13 figures

Online Bagging for Anytime Transfer Learning

Authors: Guokun Chi, Min Jiang, Xing Gao, Weizhen Hu, Shihui Guo, Kay Chen Tan

Abstract: Transfer learning techniques have been widely used in the reality that it is difficult to obtain sufficient labeled data in the target domain, but a large amount of auxiliary data can be obtained in the relevant source domain. But most of the existing methods are based on offline data. In practical applications, it is often necessary to face online learning problems in which the data samples are a… ▽ More Transfer learning techniques have been widely used in the reality that it is difficult to obtain sufficient labeled data in the target domain, but a large amount of auxiliary data can be obtained in the relevant source domain. But most of the existing methods are based on offline data. In practical applications, it is often necessary to face online learning problems in which the data samples are achieved sequentially. In this paper, We are committed to applying the ensemble approach to solving the problem of online transfer learning so that it can be used in anytime setting. More specifically, we propose a novel online transfer learning framework, which applies the idea of online bagging methods to anytime transfer learning problems, and constructs strong classifiers through online iterations of the usefulness of multiple weak classifiers. Further, our algorithm also provides two extension schemes to reduce the impact of negative transfer. Experiments on three real data sets show that the effectiveness of our proposed algorithms. △ Less

Submitted 20 October, 2019; originally announced October 2019.

Comments: 7 pages; SSCI2019

Exploring the Performance of Deep Residual Networks in Crazyhouse Chess

Authors: Sun-Yu Gordon Chi

Abstract: Crazyhouse is a chess variant that incorporates all of the classical chess rules, but allows users to drop pieces captured from the opponent as a normal move. Until 2018, all competitive computer engines for this board game made use of an alpha-beta pruning algorithm with a hand-crafted evaluation function for each position. Previous machine learning-based algorithms for just regular chess, such a… ▽ More Crazyhouse is a chess variant that incorporates all of the classical chess rules, but allows users to drop pieces captured from the opponent as a normal move. Until 2018, all competitive computer engines for this board game made use of an alpha-beta pruning algorithm with a hand-crafted evaluation function for each position. Previous machine learning-based algorithms for just regular chess, such as NeuroChess and Giraffe, took hand-crafted evaluation features as input rather than a raw board representation. More recent projects, such as AlphaZero, reached massive success but required massive computational resources in order to reach its final strength. This paper describes the development of SixtyFour, an engine designed to compete in the chess variant of Crazyhouse with limited hardware. This specific variant poses a multitude of significant challenges due to its large branching factor, state-space complexity, and the multiple move types a player can make. We propose the novel creation of a neural network-based evaluation function for Crazyhouse. More importantly, we evaluate the effectiveness of an ensemble model, which allows the training time and datasets to be easily distributed on regular CPU hardware commodity. Early versions of the network have attained a playing level comparable to a strong amateur on online servers. △ Less

Submitted 25 August, 2019; originally announced August 2019.

Comments: 16 pages, 5 figures

Ghost Cities Analysis Based on Positioning Data in China

Authors: Guanghua Chi, Yu Liu, Zhengwei Wu, Haishan Wu

Abstract: Real estate projects are developed excessively in China in this decade. Many new housing districts are built, but they far exceed the actual demand in some cities. These cities with a high housing vacancy rate are called ghost cities. The real situation of vacant housing areas in China has not been studied in previous research. This study, using Baidu positioning data, presents the spatial distrib… ▽ More Real estate projects are developed excessively in China in this decade. Many new housing districts are built, but they far exceed the actual demand in some cities. These cities with a high housing vacancy rate are called ghost cities. The real situation of vacant housing areas in China has not been studied in previous research. This study, using Baidu positioning data, presents the spatial distribution of the vacant housing areas in China and classifies cities with a large vacant housing area as cities or tourism sites. To the best of our knowledge, it is the first time that we detected and analyzed the ghost cities in China at such fine scale. To understand the human dynamic in ghost cities, we select one city and one tourism sites as cases to analyze the features of human dynamics. This study illustrates the capability of big data in sensing our cities objectively and comprehensively. △ Less

Submitted 11 November, 2015; v1 submitted 28 October, 2015; originally announced October 2015.

Comments: added references for Case Study; corrected typos; revised argument in Introduction; added a sentence to explain the second-tier and third tier cities in Result; added two sentences to introduce the background of the study in Conclusion; added two people in the Acknowledgements; added a coauthor for his contribution in designing the algorithms of home-work detection and migration calculation