arXiv subjects

Guannan Liu

Publications and source records attributed to Guannan Liu.

13 recordsLinked to original sources

arXiv2026

Uncertainty-Guided LLM Semantic Augmentation for Heterogeneous Treatment Effect Estimation

Estimating heterogeneous treatment effects is central to targeted interventions, such as personalized promotions and precision medicine. We focus on the conditional average treatment effect (CATE), a standard estimand for characterizing such heterogeneity. Even under standard identification conditions, finite-sample CATE estimation requires learning the nuisance structure for covariate adjustment and treatment-effect heterogeneity, often together with an effective representation of X. Raw numerical and categorical encodings can leave semantic relations and higher-order interactions implicit, making this joint task locally unstable. A motivating study further shows that this instability appears through partially separable assignment- and heterogeneity-side channels. Building on this observation, we propose CURL (Causal Uncertainty-guided Representation Learning), a plug-in adapter that uses estimator uncertainty to allocate pretrained semantic capacity to locally unstable units. CURL queries a frozen LLM through two role-conditioned prompts, constructs assignment- and heterogeneity-oriented representations from the observed covariates, and routes them through separated pathways. On four benchmarks, CURL improves ten host learners in most settings, while ablation, refinement-dynamics, route-reassignment, and probe analyses support the intended design and roles of the two channels.

cs.LG↗

arXiv2026

Dynamic Whole-Body Dancing with Humanoid Robots -- A Model-Based Control Approach

This paper presents an integrated model-based framework for generating and executing dynamic whole-body dance motions on humanoid robots. The framework operates in two stages: offline motion generation and online motion execution, both leveraging future state prediction to enable robust and dynamic dance motions in real-world environments. In the offline motion generation stage, human dance demonstrations are captured via a motion capture (MoCap) system, retargeted to the robot by solving a Quadratic Programming (QP) problem, and further refined using Trajectory Optimization (TO) to ensure dynamic feasibility. In the online motion execution stage, a centroidal dynamics-based Model Predictive Control (MPC) framework tracks the planned motions in real time and proactively adjusts swing foot placement to adapt to real world disturbances. We validate our framework on the full-size humanoid robot Kuavo 4Pro, demonstrating the dynamic dance motions both in simulation and in a four-minute live public performance with a team of four robots. Experimental results show that longer prediction horizons improve both motion expressiveness in planning and stability in execution.

cs.RO↗

arXiv2025

Code Vulnerability Repair with Large Language Model using Context-Aware Prompt Tuning

Large Language Models (LLMs) have shown significant challenges in detecting and repairing vulnerable code, particularly when dealing with vulnerabilities involving multiple aspects, such as variables, code flows, and code structures. In this study, we utilize GitHub Copilot as the LLM and focus on buffer overflow vulnerabilities. Our experiments reveal a notable gap in Copilot's abilities when dealing with buffer overflow vulnerabilities, with a 76% vulnerability detection rate but only a 15% vulnerability repair rate. To address this issue, we propose context-aware prompt tuning techniques designed to enhance LLM performance in repairing buffer overflow. By injecting a sequence of domain knowledge about the vulnerability, including various security and code contexts, we demonstrate that Copilot's successful repair rate increases to 63%, representing more than four times the improvement compared to repairs without domain knowledge.

cs.CR↗

arXiv2025

Toward AI standardization: A triadic human-ai collaboration framework for multi-level autonomous mobility

The goal of the current study is to introduce a triadic human-AI collaboration framework that could be applied in transportation systems such as automated vehicles, micromobility systems, and vehicle teleoperation. Previous standards, such as SAE Levels of Automation, have focused on defining automation levels based on who controls the vehicle. However, it is still not clear how human users and AI should collaborate in real time, especially in dynamic driving contexts where roles can shift frequently. To fill this gap, this study proposed a triadic human-AI collaboration framework with three AI roles: Advisor, Co-Pilot, and Guardian. These roles can dynamically adapt to human needs based on real-time data, such as mental states and environmental conditions. The Advisor AI offers informational support without direct intervention. The Co-Pilot AI provides partial intervention when needed, with the goal of sharing control with humans. The Guardian AI performs emergency overrides if necessary. The use cases for these AI roles in micromobility devices, such as e-scooters, are presented to demonstrate how these roles can influence user preferences and trust. Overall, the study takes a first step toward a universal role-based collaborative framework for AI standardization and explores how AI technologies can be embedded in future transportation systems while considering human interactions.

cs.HC↗

arXiv2024

Modeling Reference-dependent Choices with Graph Neural Networks

While the classic Prospect Theory has highlighted the reference-dependent and comparative nature of consumers' product evaluation processes, few models have successfully integrated this theoretical hypothesis into data-driven preference quantification, particularly in the realm of recommender systems development. To bridge this gap, we propose a new research problem of modeling reference-dependent preferences from a data-driven perspective, and design a novel deep learning-based framework named Attributed Reference-dependent Choice Model for Recommendation (ArcRec) to tackle the inherent challenges associated with this problem. ArcRec features in building a reference network from aggregated historical purchase records for instantiating theoretical reference points, which is then decomposed into product attribute specific sub-networks and represented through Graph Neural Networks. In this way, the reference points of a consumer can be encoded at the attribute-level individually from her past experiences but also reflect the crowd influences. ArcRec also makes novel contributions to quantifying consumers' reference-dependent preferences using a deep neural network-based utility function that integrates both interest-inspired and price-inspired preferences, with their complex interaction effects captured by an attribute-aware price sensitivity mechanism. Most importantly, ArcRec introduces a novel Attribute-level Willingness-To-Pay measure to the reference-dependent utility function, which captures a consumer's heterogeneous salience of product attributes via observing her attribute-level price tolerance to a product. Empirical evaluations on both synthetic and real-world online shopping datasets demonstrate ArcRec's superior performances over fourteen state-of-the-art baselines.

cs.LG↗

arXiv2024

Pathfinder: Exploring Path Diversity for Assessing Internet Censorship Inconsistency

Internet censorship is typically enforced by authorities to achieve information control for a certain group of Internet users. So far existing censorship studies have primarily focused on country-level characterization because (1) in many cases, censorship is enabled by governments with nationwide policies and (2) it is usually hard to control how the probing packets are routed to trigger censorship in different networks inside a country. However, the deployment and implementation of censorship could be highly diverse at the ISP level. In this paper, we investigate Internet censorship from a different perspective by scrutinizing the diverse censorship deployment inside a country. Specifically, by leveraging an end-to-end measurement framework, we deploy multiple geo-distributed back-end control servers to explore various paths from one single vantage point. The generated traffic with the same domain but different control servers' IPs could be forced to traverse different transit networks, thereby being examined by different censorship devices if present. Through our large-scale experiments and in-depth investigation, we reveal that the diversity of Internet censorship caused by different routing paths inside a country is prevalent, implying that (1) the implementations of centralized censorship are commonly incomplete or flawed and (2) decentralized censorship is also common. Moreover, we identify that different hosting platforms also result in inconsistent censorship activities due to different peering relationships with the ISPs in a country. Finally, we present extensive case studies in detail to illustrate the configurations that lead to censorship inconsistency and explore the causes.

cs.CR↗

arXiv2023

A Framework for Ductility in Metallic Glasses

The understanding and quantification of ductility in crystalline metals, which has led to their widespread and effective usage as a structural material, is lacking in metallic glasses (MGs). Here, we introduce such a framework for ductility. This very practical framework is based on a MGs ability to support stable shear band growth, quantified in a stress gradient, gradSDB, which we measure and calculate for a range of MGs. Whether a MG behaves ductile or brittle in an application is determined by the comparison between gradsDB the applied stress field gradient, gradsapp. If gradsDB > gradsapp, the MG will behave brittle, if gradsDB < gradsapp, the MG will behave ductile, and gradsapp - gradsDB indicates how ductile. This framework can explain observed plastic properties of MGs and their apparent contradicting brittle and ductile characteristics. Looking forward, proposed framework provides the constitutive relation to quantitatively model their plastic behavior in any application, a requirement to use MGs as structural materials.

cond-mat.mtrl-sci↗

arXiv2021

Multi-Aspect Temporal Network Embedding: A Mixture of Hawkes Process View

Recent years have witnessed the tremendous research interests in network embedding. Extant works have taken the neighborhood formation as the critical information to reveal the inherent dynamics of network structures, and suggested encoding temporal edge formation sequences to capture the historical influences of neighbors. In this paper, however, we argue that the edge formation can be attributed to a variety of driving factors including the temporal influence, which is better referred to as multiple aspects. As a matter of fact, different node aspects can drive the formation of distinctive neighbors, giving birth to the multi-aspect embedding that relates to but goes beyond a temporal scope. Along this vein, we propose a Mixture of Hawkes-based Temporal Network Embeddings (MHNE) model to capture the aspect-driven neighborhood formation of networks. In MHNE, we encode the multi-aspect embeddings into the mixture of Hawkes processes to gain the advantages in modeling the excitation effects and the latent aspects. Specifically, a graph attention mechanism is used to assign different weights to account for the excitation effects of history events, while a Gumbel-Softmax is plugged in to derive the distribution over the aspects. Extensive experiments on 8 different temporal networks have demonstrated the great performance of the multi-aspect embeddings obtained by MHNE in comparison with the state-of-the-art methods.

cs.LG↗

arXiv2020

Recommendation with Attribute-aware Product Networks: A Representation Learning Model

With the prosperity of business intelligence, recommender systems have evolved into a new stage that we not only care about what to recommend, but why it is recommended. Explainability of recommendations thus emerges as a focal point of research and becomes extremely desired in e-commerce. Existent studies along this line often exploit item attributes and correlations from different perspectives, but they yet lack an effective way to combine both types of information for deep learning of personalized interests. In light of this, we propose a novel graph structure, \emph{attribute network}, based on both items' co-purchase network and important attributes. A novel neural model called \emph{eRAN} is then proposed to generate recommendations from attribute networks with explainability and cold-start capability. Specifically, eRAN first maps items connected in attribute networks to low-dimensional embedding vectors through a deep autoencoder, and then an attention mechanism is applied to model the attractions of attributes to users, from which personalized item representation can be derived. Moreover, a pairwise ranking loss is constructed into eRAN to improve recommendations, with the assumption that item pairs co-purchased by a user should be more similar than those non-paired with negative sampling in personalized view. Experiments on real-world datasets demonstrate the effectiveness of our method compared with some state-of-the-art competitors. In particular, eRAN shows its unique abilities in recommending cold-start items with higher accuracy, as well as in understanding user preferences underlying complicated co-purchasing behaviors.

cs.IR↗

arXiv2019

Beyond Similarity: Relation Embedding with Dual Attentions for Item-based Recommendation

Given the effectiveness and ease of use, Item-based Collaborative Filtering (ICF) methods have been broadly used in industry in recent years. The key of ICF lies in the similarity measurement between items, which however is a coarse-grained numerical value that can hardly capture users' fine-grained preferences toward different latent aspects of items from a representation learning perspective. In this paper, we propose a model called REDA (latent Relation Embedding with Dual Attentions) to address this challenge. REDA is essentially a deep learning based recommendation method that employs an item relation embedding scheme through a neural network structure for inter-item relations representation. A relational user embedding is then proposed by aggregating the relation embeddings between all purchased items of a user, which not only better characterizes user preferences but also alleviates the data sparsity problem. Moreover, to capture valid meta-knowledge that reflects users' desired latent aspects and meanwhile suppress their explosive growth towards overfitting, we further propose a dual attentions mechanism, including a memory attention and a weight attention. A relation-wise optimization method is finally developed for model inference by constructing a personalized ranking loss for item relations. Extensive experiments are implemented on real-world datasets and the proposed model is shown to greatly outperform state-of-the-art methods, especially when the data is sparse.

cs.IR↗

arXiv2019

A self-driven phase transition drives Myxococcus xanthus fruiting body formation

Combining high-resolution single cell tracking experiments with numerical simulations, we show that starvation-induced fruiting body (FB) formation in Myxococcus xanthus is a phase separation driven by cells that tune their motility over time. The phase separation can be understood in terms of cell density and a dimensionless Peclet number that captures cell motility through speed and reversal frequency. Our work suggests that M. xanthus take advantage of a self-driven non-equilibrium phase transition that can be controlled at the single cell level.

physics.bio-ph↗

arXiv2018

Social Media Would Not Lie: Prediction of the 2016 Taiwan Election via Online Heterogeneous Data

The prevalence of online media has attracted researchers from various domains to explore human behavior and make interesting predictions. In this research, we leverage heterogeneous social media data collected from various online platforms to predict Taiwan's 2016 presidential election. In contrast to most existing research, we take a "signal" view of heterogeneous information and adopt the Kalman filter to fuse multiple signals into daily vote predictions for the candidates. We also consider events that influenced the election in a quantitative manner based on the so-called event study model that originated in the field of financial research. We obtained the following interesting findings. First, public opinions in online media dominate traditional polls in Taiwan election prediction in terms of both predictive power and timeliness. But offline polls can still function on alleviating the sample bias of online opinions. Second, although online signals converge as election day approaches, the simple Facebook "Like" is consistently the strongest indicator of the election result. Third, most influential events have a strong connection to cross-strait relations, and the Chou Tzu-yu flag incident followed by the apology video one day before the election increased the vote share of Tsai Ing-Wen by 3.66%. This research justifies the predictive power of online media in politics and the advantages of information fusion. The combined use of the Kalman filter and the event study method contributes to the data-driven political analytics paradigm for both prediction and attribution purposes.

cs.SI↗

arXiv2010

Being Rational or Aggressive? A Revisit to Dunbar's Number in Online Social Networks

Recent years have witnessed the explosion of online social networks (OSNs). They provide powerful IT-innovations for online social activities such as organizing contacts, publishing contents, and sharing interests between friends who may never meet before. As more and more people become the active users of online social networks, one may ponder questions such as: (1) Do OSNs indeed improve our sociability? (2) To what extent can we expand our offline social spectrum in OSNs? (3) Can we identify some interesting user behaviors in OSNs? Our work in this paper just aims to answer these interesting questions. To this end, we pay a revisit to the well-known Dunbar's number in online social networks. Our main research contributions are as follows. First, to our best knowledge, our work is the first one that systematically validates the existence of the online Dunbar's number in the range of [200,300]. To reach this, we combine using local-structure analysis and user-interaction analysis for extensive real-world OSNs. Second, we divide OSNs users into two categories: rational and aggressive, and find that rational users intend to develop close and reciprocated relationships, whereas aggressive users have no consistent behaviors. Third, we build a simple model to capture the constraints of time and cognition that affect the evolution of online social networks. Finally, we show the potential use of our findings in viral marketing and privacy management in online social networks.

cs.SI↗