Yuan Zhuang

Yilun Zhu, Yuan Zhuang, Nikhita Vedula et al.

Many applications of LLM-based text regression require predicting a full conditional distribution rather than a single point value. We study distributional regression under empirical-quantile supervision, where each input is paired with multiple observed quantile outcomes, and the target distribution is represented by a dense grid of quantiles. We address two key limitations of current approaches: the lack of local grounding for distribution estimates, and the reliance on shared representations that create an indirect bottleneck between inputs and quantile outputs. In this paper, we introduce Quantile Token Regression, which, to our knowledge, is the first work to insert dedicated quantile tokens into the input sequence, enabling direct input-output pathways for each quantile through self-attention. We further augment these quantile tokens with retrieval, incorporating semantically similar neighbor instances and their empirical distributions to ground predictions with local evidence from similar instances. We also provide the first theoretical analysis of loss functions for quantile regression, clarifying which distributional objectives each optimizes. Experiments on the Inside Airbnb and StackSample benchmark datasets with LLMs ranging from 1.7B to 14B parameters show that quantile tokens with neighbors consistently outperform baselines (~4 points lower MAPE and 2x narrower prediction intervals), with especially large gains on smaller and more challenging datasets where quantile tokens produce substantially sharper and more accurate distributions.

Zejian Eric Wu, Zhongyi Jiang, Yuan Zhuang et al.

Multi-agent systems are increasingly deployed to support various tasks where agents interact to achieve individual and collective objectives. Although these systems can enhance task performance and decision-making, fairness preservation through bias reduction remains challenging. This study examines how agent-level biases shift and impact system-wide fairness. We use prompts to expose individual agents to group-favoring bias, then assess downstream impacts at the system level. To quantify the impact, we propose Favor Bias Strength (FBS), a zero-centered metric that decomposes bias alteration between favored-group uplift and disfavored-group suppression. Using multiple agent designs, benchmarks, and up-to-date large language models, we show that agents endowed with bias can substantially affect system-wide fairness. Interestingly, when agents are exposed to bias uniformly, the system-wide bias elevates, even exceeding the additive sum of the individual agents' biases. The empirical evidence underscores the criticality of fairness in multi-agent systems, which warrants further analyses and empirical tests.

Aidan San, Yuan Zhuang, Jan Bakus et al.

Recently, neural models have been leveraged to significantly improve the performance of information extraction from semi-structured websites. However, a barrier for continued progress is the small number of datasets large enough to train these models. In this work, we introduce the PLAtE (Pages of Lists Attribute Extraction) benchmark dataset as a challenging new web extraction task. PLAtE focuses on shopping data, specifically extractions from product review pages with multiple items encompassing the tasks of: (1) finding product-list segmentation boundaries and (2) extracting attributes for each product. PLAtE is composed of 52, 898 items collected from 6, 694 pages and 156, 014 attributes, making it the first largescale list page web extraction dataset. We use a multi-stage approach to collect and annotate the dataset and adapt three state-of-the-art web extraction models to the two tasks comparing their strengths and weaknesses both quantitatively and qualitatively.

Yuan Zhuang, Yuexin Bian, Sihong He et al.

Scaling critic capacity is a promising direction for enhancing off-policy reinforcement learning (RL). However, larger critics are prone to overfitting and unstable in replay-buffer-based bootstrap training. This paper leverages Low-Rank Adaptation (LoRA) as a structural-sparsity regularizer for off-policy critics. Our approach freezes randomly initialized base matrices and solely optimizes low-rank adapters, thereby constraining critic updates to a low-dimensional subspace. Built on top of SimbaV2, we further develop a LoRA formulation, compatible with SimbaV2, that preserves its hyperspherical normalization geometry under frozen-backbone training. We evaluate our method with SAC and FastTD3 on DeepMind Control locomotion and IsaacLab robotics benchmarks. LoRA consistently achieves lower critic loss during training and stronger policy performance. Extensive experiments demonstrate that adaptive low-rank updates provide a simple, scalable, and effective structural regularization for critic learning in off-policy RL.

Louie Hong Yao, Vishesh Anand, Yuan Zhuang et al.

Rhetorical questions are asked not to seek information but to persuade or signal stance. How large language models internally represent them remains unclear. We analyze rhetorical questions in LLM representations using linear probes on two social-media datasets with different discourse contexts, and find that rhetorical signals emerge early and are most stably captured by last-token representations. Rhetorical questions are linearly separable from information-seeking questions within datasets, and remain detectable under cross-dataset transfer, reaching AUROC around 0.7-0.8. However, we demonstrate that transferability does not simply imply a shared representation. Probes trained on different datasets produce different rankings when applied to the same target corpus, with overlap among the top-ranked instances often below 0.2. Qualitative analysis shows that these divergences correspond to distinct rhetorical phenomena: some probes capture discourse-level rhetorical stance embedded in extended argumentation, while others emphasize localized, syntax-driven interrogative acts. Together, these findings suggest that rhetorical questions in LLM representations are encoded by multiple linear directions emphasizing different cues, rather than a single shared direction.

Mengyao Guo, Xiaolin Zhang, Yuan Zhuang et al.

This paper explores using generative AI and aesthetics to promote cultural creativity in rural China amidst COVID-19's impact. Through literature reviews, case studies, surveys, and text analysis, it examines art and technology applications in rural contexts and identifies key challenges. The study finds artworks often fail to resonate locally, while reliance on external artists limits sustainability. Hence, nurturing grassroots "artist villagers" through AI is proposed. Our approach involves training machine learning on subjective aesthetics to generate culturally relevant content. Interactive AI media can also boost tourism while preserving heritage. This pioneering research puts forth original perspectives on the intersection of AI and aesthetics to invigorate rural culture. It advocates holistic integration of technology and emphasizes AI's potential as a creative enabler versus replacement. Ultimately, it lays the groundwork for further exploration of leveraging AI innovations to empower rural communities. This timely study contributes to growing interest in emerging technologies to address critical issues facing rural China.

Tianchonghui Fang, Yuan Zhuang, Fei Miao

Vision-Language-Action (VLA) and imitation-learning policies trained via community toolchains on low-cost hardware frequently fail when deployed outside the training environment. Existing evaluations, including the original ACT and SmolVLA benchmarks, demonstrate high success rates under controlled, fixed backgrounds, yet community practitioners report near-zero transfer to new environments. We present SEVO (Semantic-Enhanced Virtual Observation), a data-centric approach that improves cross-environment manipulation robustness without modifying the policy architecture. SEVO transforms the raw RGB camera stream through three mechanisms: (1) body-fixed cameras whose combined fields of view cover the full manipulation workspace, (2) active red-spectrum illumination that physically normalizes object appearance, and (3) real-time YOLO segmentation overlay that provides a background-invariant semantic cue. Critically, we show that a diversified data collection protocol (systematically varying lighting, backgrounds, and distractors during teleoperation) is the single most important factor for generalization. We target transparent water bottles, objects that visually blend with their surroundings, and select a simple pick-and-place task to enable hundreds of controlled real-robot trials across two mobile platforms. The full pipeline achieves 95% grasp success with ACT and 83% with SmolVLA in the training environment, transferring to novel environments at 85% and 75%. Without SEVO, the same policies achieve only 75%/70% in training and collapse to 30-35% in novel environments. Our results demonstrate that principled observation design and environmental diversity during data collection, not model scaling, enable low-cost robots to operate reliably in everyday household environments.

Guokai Sun, Yuan Zhuang, Shuo Zhang et al.

Smart contracts, closely intertwined with cryptocurrency transactions, have sparked widespread concerns about considerable financial losses of security issues. To counteract this, a variety of tools have been developed to identify vulnerability in smart contract. However, they fail to overcome two challenges at the same time when faced with smart contract bytecode: (i) strong interference caused by enormous non-relevant instructions; (ii) missing semantics of bytecode due to incomplete data and control flow dependencies. In this paper, we propose a multi-teacher based bytecode vulnerability detection method, namely Multi-Teacher Vulnerability Hunter (MTVHunter), which delivers effective denoising and missing semantic to bytecode under multi-teacher guidance. Specifically, we first propose an instruction denoising teacher to eliminate noise interference by abstract vulnerability pattern and further reflect in contract embeddings. Secondly, we design a novel semantic complementary teacher with neuron distillation, which effectively extracts necessary semantic from source code to replenish the bytecode. Particularly, the proposed neuron distillation accelerate this semantic filling by turning the knowledge transition into a regression task. We conduct experiments on 229,178 real-world smart contracts that concerns four types of common vulnerabilities. Extensive experiments show MTVHunter achieves significantly performance gains over state-of-the-art approaches.

Yuan Zhuang, Yi Shen, Yuexin Bian et al.

Recent studies have shown that combining parameter-efficient fine-tuning (PEFT) with mixture-of-experts (MoE) is an effective strategy for adapting large language models (LLMs) to the downstream tasks. However, most existing approaches rely on conventional TopK routing, which requires careful hyperparameter tuning and assigns a fixed number of experts to each token. In this work, we propose LD-MoLE, a Learnable Dynamic routing mechanism for Mixture of LoRA Experts that enables adaptive, token-dependent, and layer-wise expert allocation. Our method replaces the non-differentiable TopK selection with a differentiable routing function and a closed-form solution. Moreover, our design allows the model to adaptively determine the number of experts to activate for each token at different layers. In addition, we introduce an analytical sparsity control objective to regularize the number of activated experts. Extensive experiments on the Qwen3-1.7B and Llama-3.2-3B models show that LD-MoLE achieves the highest average scores compared to state-of-the-art baselines, across a diverse set of benchmarks. Our method not only achieves superior performance, but also demonstrates the ability to learn token-dependent and layer-wise expert allocation.

Jianzhu Huai, Yukai Lin, Yuan Zhuang et al.

Camera-IMU (Inertial Measurement Unit) sensor fusion has been extensively studied in recent decades. Numerous observability analysis and fusion schemes for motion estimation with self-calibration have been presented. However, it has been uncertain whether both camera and IMU intrinsic parameters are observable under general motion. To answer this question, by using the Lie derivatives, we first prove that for a rolling shutter (RS) camera-IMU system, all intrinsic and extrinsic parameters, camera time offset, and readout time of the RS camera, are observable with an unknown landmark. To our knowledge, we are the first to present such a proof. Next, to validate this analysis and to solve the drift issue of a structureless filter during standstills, we develop a Keyframe-based Sliding Window Filter (KSWF) for odometry and self-calibration, which works with a monocular RS camera or stereo RS cameras. Though the keyframe concept is widely used in vision-based sensor fusion, to our knowledge, KSWF is the first of its kind to support self-calibration. Our simulation and real data tests have validated that it is possible to fully calibrate the camera-IMU system using observations of opportunistic landmarks under diverse motion. Real data tests confirmed previous allusions that keeping landmarks in the state vector can remedy the drift in standstill, and showed that the keyframe-based scheme is an alternative solution.

Jianzhu Huai, Yuan Zhuang, Qicheng Yuan et al.

The rolling shutter (RS) mechanism is widely used by consumer-grade cameras, which are essential parts in smartphones and autonomous vehicles. The RS effect leads to image distortion upon relative motion between a camera and the scene. This effect needs to be considered in video stabilization, structure from motion, and vision-aided odometry, for which recent studies have improved earlier global shutter (GS) methods by accounting for the RS effect. However, it is still unclear how the RS affects spatiotemporal calibration of the camera in a sensor assembly, which is crucial to good performance in aforementioned applications. This work takes the camera-IMU system as an example and looks into the RS effect on its spatiotemporal calibration. To this end, we develop a calibration method for a RS-camera-IMU system with continuous-time B-splines by using a calibration target. Unlike in calibrating GS cameras, every observation of a landmark on the target has a unique camera pose fitted by continuous-time B-splines. With simulated data generated from four sets of public calibration data, we show that RS can noticeably affect the extrinsic parameters, causing errors about 1$^\circ$ in orientation and 2 $cm$ in translation with a RS setting as in common smartphone cameras. With real data collected by two industrial camera-IMU systems, we find that considering the RS effect gives more accurate and consistent spatiotemporal calibration. Moreover, our method also accurately calibrates the inter-line delay of the RS. The code for simulation and calibration is publicly available.

Zhenguang Liu, Peng Qian, Xiaoyang Wang et al.

Smart contract vulnerability detection draws extensive attention in recent years due to the substantial losses caused by hacker attacks. Existing efforts for contract security analysis heavily rely on rigid rules defined by experts, which are labor-intensive and non-scalable. More importantly, expert-defined rules tend to be error-prone and suffer the inherent risk of being cheated by crafty attackers. Recent researches focus on the symbolic execution and formal analysis of smart contracts for vulnerability detection, yet to achieve a precise and scalable solution. Although several methods have been proposed to detect vulnerabilities in smart contracts, there is still a lack of effort that considers combining expert-defined security patterns with deep neural networks. In this paper, we explore using graph neural networks and expert knowledge for smart contract vulnerability detection. Specifically, we cast the rich control- and data- flow semantics of the source code into a contract graph. To highlight the critical nodes in the graph, we further design a node elimination phase to normalize the graph. Then, we propose a novel temporal message propagation network to extract the graph feature from the normalized graph, and combine the graph feature with designed expert patterns to yield a final detection system. Extensive experiments are conducted on all the smart contracts that have source code in Ethereum and VNT Chain platforms. Empirical results show significant accuracy improvements over the state-of-the-art methods on three types of vulnerabilities, where the detection accuracy of our method reaches 89.15%, 89.02%, and 83.21% for reentrancy, timestamp dependence, and infinite loop vulnerabilities, respectively.

Jianzhu Huai, Yukai Lin, Yuan Zhuang et al.

State estimation problems without absolute position measurements routinely arise in navigation of unmanned aerial vehicles, autonomous ground vehicles, etc., whose proper operation relies on accurate state estimates and reliable covariances. Unaware of absolute positions, these problems have immanent unobservable directions. Traditional causal estimators, however, usually gain spurious information on the unobservable directions, leading to over-confident covariance inconsistent with actual estimator errors. The consistency problem of fixed-lag smoothers (FLSs) has only been attacked by the first estimate Jacobian (FEJ) technique because of the complexity to analyze their observability property. But the FEJ has several drawbacks hampering its wide adoption. To ensure the consistency of a FLS, this paper introduces the right invariant error formulation into the FLS framework. To our knowledge, we are the first to analyze the observability of a FLS with the right invariant error. Our main contributions are twofold. As the first novelty, to bypass the complexity of analysis with the classic observability matrix, we show that observability analysis of FLSs can be done equivalently on the linearized system. Second, we prove that the inconsistency issue in the traditional FLS can be elegantly solved by the right invariant error formulation without artificially correcting Jacobians. By applying the proposed FLS to the monocular visual inertial simultaneous localization and mapping (SLAM) problem, we confirm that the method consistently estimates covariance similarly to a batch smoother in simulation and that our method achieved comparable accuracy as traditional FLSs on real data.

Jianzhu Huai, Yukai Lin, Charles Toth et al.

Motion estimation by fusing data from at least a camera and an Inertial Measurement Unit (IMU) enables many applications in robotics. However, among the multitude of Visual Inertial Odometry (VIO) methods, few efficiently estimate device motion with consistent covariance, and calibrate sensor parameters online for handling data from consumer sensors. This paper addresses the gap with a Keyframe-based Structureless Filter (KSF). For efficiency, landmarks are not included in the filter's state vector. For robustness, KSF associates feature observations and manages state variables using the concept of keyframes. For flexibility, KSF supports anytime calibration of IMU systematic errors, as well as extrinsic, intrinsic, and temporal parameters of each camera. Estimator consistency and observability of sensor parameters were analyzed by simulation. Sensitivity to design options, e.g., feature matching method and camera count was studied with the EuRoC benchmark. Sensor parameter estimation was evaluated on raw TUM VI sequences and smartphone data. Moreover, pose estimation accuracy was evaluated on EuRoC and TUM VI sequences versus recent VIO methods. These tests confirm that KSF reliably calibrates sensor parameters when the data contain adequate motion, and consistently estimate motion with accuracy rivaling recent VIO methods. Our implementation runs at 42 Hz with stereo camera images on a consumer laptop.

Min Shi, David A. Wilson, Xingquan Zhu et al.

Automated machine learning (AutoML) has seen a resurgence in interest with the boom of deep learning over the past decade. In particular, Neural Architecture Search (NAS) has seen significant attention throughout the AutoML research community, and has pushed forward the state-of-the-art in a number of neural models to address grid-like data such as texts and images. However, very litter work has been done about Graph Neural Networks (GNN) learning on unstructured network data. Given the huge number of choices and combinations of components such as aggregator and activation function, determining the suitable GNN structure for a specific problem normally necessitates tremendous expert knowledge and laborious trails. In addition, the slight variation of hyper parameters such as learning rate and dropout rate could dramatically hurt the learning capacity of GNN. In this paper, we propose a novel AutoML framework through the evolution of individual models in a large GNN architecture space involving both neural structures and learning parameters. Instead of optimizing only the model structures with fixed parameter settings as existing work, an alternating evolution process is performed between GNN structures and learning parameters to dynamically find the best fit of each other. To the best of our knowledge, this is the first work to introduce and evaluate evolutionary architecture search for GNN models. Experiments and validations demonstrate that evolutionary NAS is capable of matching existing state-of-the-art reinforcement learning approaches for both the semi-supervised transductive and inductive node representation learning and classification.

You Li, Ruizhi Chen, Xiaoji Niu et al.

The inertial navigation system (INS) has been widely used to provide self-contained and continuous motion estimation in intelligent transportation systems. Recently, the emergence of chip-level inertial sensors has expanded the relevant applications from positioning, navigation, and mobile mapping to location-based services, unmanned systems, and transportation big data. Meanwhile, benefit from the emergence of big data and the improvement of algorithms and computing power, artificial intelligence (AI) has become a consensus tool that has been successfully applied in various fields. This article reviews the research on using AI technology to enhance inertial sensing from various aspects, including sensor design and selection, calibration and error modeling, navigation and motion-sensing algorithms, multi-sensor information fusion, system evaluation, and practical application. Based on the over 30 representative articles selected from the nearly 300 related publications, this article summarizes the state of the art, advantages, and challenges on each aspect. Finally, it summarizes nine advantages and nine challenges of AI-enhanced inertial sensing and then points out future research directions.

You Li, Xin Hu, Yuan Zhuang et al.

Location is key to spatialize internet-of-things (IoT) data. However, it is challenging to use low-cost IoT devices for robust unsupervised localization (i.e., localization without training data that have known location labels). Thus, this paper proposes a deep reinforcement learning (DRL) based unsupervised wireless-localization method. The main contributions are as follows. (1) This paper proposes an approach to model a continuous wireless-localization process as a Markov decision process (MDP) and process it within a DRL framework. (2) To alleviate the challenge of obtaining rewards when using unlabeled data (e.g., daily-life crowdsourced data), this paper presents a reward-setting mechanism, which extracts robust landmark data from unlabeled wireless received signal strengths (RSS). (3) To ease requirements for model re-training when using DRL for localization, this paper uses RSS measurements together with agent location to construct DRL inputs. The proposed method was tested by using field testing data from multiple Bluetooth 5 smart ear tags in a pasture. Meanwhile, the experimental verification process reflected the advantages and challenges for using DRL in wireless localization.