arXiv subjects

Jing Huang

Publications and source records attributed to Jing Huang.

At least 109 records · Page 6Linked to original sources

arXiv2025

Facial Expression-based Parkinson's Disease Severity Diagnosis via Feature Fusion and Adaptive Class Balancing

Parkinson's disease (PD) severity diagnosis is crucial for early detecting potential patients and adopting tailored interventions. Diagnosing PD based on facial expression is grounded in PD patients' "masked face" symptom and gains growing interest recently for its convenience and affordability. However, current facial expression-based approaches often rely on single type of expression which can lead to misdiagnosis, and ignore the class imbalance across different PD stages which degrades the prediction performance. Moreover, most existing methods focus on binary classification (i.e., PD / non-PD) rather than diagnosing the severity of PD. To address these issues, we propose a new facial expression-based method for PD severity diagnosis which integrates multiple facial expression features through attention-based feature fusion. Moreover, we mitigate the class imbalance problem via an adaptive class balancing strategy which dynamically adjusts the contribution of training samples based on their class distribution and classification difficulty. Experimental results demonstrate the promising performance of the proposed method for PD severity diagnosis, as well as the efficacy of attention-based feature fusion and adaptive class balancing.

cs.CV↗

arXiv2025

Customer-R1: Personalized Simulation of Human Behaviors via RL-based LLM Agent in Online Shopping

Simulating step-wise human behavior with Large Language Models (LLMs) has become an emerging research direction, enabling applications in various practical domains. While prior methods, including prompting, supervised fine-tuning (SFT), and reinforcement learning (RL), have shown promise in modeling step-wise behavior, they primarily learn a population-level policy without conditioning on a user's persona, yielding generic rather than personalized simulations. In this work, we pose a critical question: how can LLM agents better simulate personalized user behavior? We introduce Customer-R1, an RL-based method for personalized, step-wise user behavior simulation in online shopping environments. Our policy is conditioned on an explicit persona, and we optimize next-step rationale and action generation via action correctness reward signals. Experiments on the OPeRA dataset emonstrate that Customer-R1 not only significantly outperforms prompting and SFT-based baselines in next-action prediction tasks, but also better matches users' action distribution, indicating higher fidelity in personalized behavior simulation.

cs.CL↗

arXiv2025

RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters

Crowd evacuation simulation is critical for enhancing public safety, and demanded for realistic virtual environments. Current mainstream evacuation models overlook the complex human behaviors that occur during evacuation, such as pedestrian collisions, interpersonal interactions, and variations in behavior influenced by terrain types or individual body shapes. This results in the failure to accurately simulate the escape of people in the real world. In this paper, aligned with the sensory-decision-motor (SDM) flow of the human brain, we propose a real-time 3D crowd evacuation simulation framework that integrates a 3D-adaptive SFM (Social Force Model) Decision Mechanism and a Personalized Gait Control Motor. This framework allows multiple agents to move in parallel and is suitable for various scenarios, with dynamic crowd awareness. Additionally, we introduce Part-level Force Visualization to assist in evacuation analysis. Experimental results demonstrate that our framework supports dynamic trajectory planning and personalized behavior for each agent throughout the evacuation process, and is compatible with uneven terrain. Visually, our method generates evacuation results that are more realistic and plausible, providing enhanced insights for crowd simulation. The code is available at http://cic.tju.edu.cn/faculty/likun/projects/RESCUE.

cs.CV↗

arXiv2025

LLM Agent Meets Agentic AI: Can LLM Agents Simulate Customers to Evaluate Agentic-AI-based Shopping Assistants?

Agentic AI is emerging, capable of executing tasks through natural language, such as Copilot for coding or Amazon Rufus for shopping. Evaluating these systems is challenging, as their rapid evolution outpaces traditional human evaluation. Researchers have proposed LLM Agents to simulate participants as digital twins, but it remains unclear to what extent a digital twin can represent a specific customer in multi-turn interaction with an agentic AI system. In this paper, we recruited 40 human participants to shop with Amazon Rufus, collected their personas, interaction traces, and UX feedback, and then created digital twins to repeat the task. Pairwise comparison of human and digital-twin traces shows that while agents often explored more diverse choices, their action patterns aligned with humans and yielded similar design feedback. This study is the first to quantify how closely LLM agents can mirror human multi-turn interaction with an agentic AI system, highlighting their potential for scalable evaluation.

cs.HC↗

arXiv2025

Strong chordality in tournaments and multipartite tournaments with possible loops

Strongly chordal digraphs are included in the class of chordal digraphs and generalize strongly chordal graphs and chordal bipartite graphs. They are the digraphs that admit a linear ordering of its vertex set for which their adjacency matrix does not contain the $Γ$ matrix as a submatrix. In general, it is not clear if these digraphs can be recognized in polynomial time. We focus on multipartite tournaments with possible loops. We give a polynomial-time recognition algorithm and a forbidden induced subgraph characterization of the strong chordality for each of the following cases: tournaments with possible loops, reflexive multipartite tournaments, irreflexive bipartite tournaments, irreflexive tournaments minus one arc, and balanced digraphs. In addition, we prove that in a strongly chordal digraph the minimum size of a total dominating set equals the maximum number of disjoint in-neighborhoods, and this number can be calculated in linear time given a $Γ$-free ordering of the input graph.

math.CO↗

arXiv2025

NGRPO: Negative-enhanced Group Relative Policy Optimization

RLVR has enhanced the reasoning capabilities of Large Language Models (LLMs) across various tasks. However, GRPO, a representative RLVR algorithm, suffers from a critical limitation: when all responses within a group are either entirely correct or entirely incorrect, the model fails to learn from these homogeneous responses. This is particularly problematic for homogeneously incorrect groups, where GRPO's advantage function yields a value of zero, leading to null gradients and the loss of valuable learning signals. To overcome this issue, we propose NGRPO (Negative-enhanced Group Relative Policy Optimization), an algorithm designed to convert homogeneous errors into robust learning signals. First, NGRPO introduces Advantage Calibration. This mechanism hypothesizes the existence of a virtual maximum-reward sample during advantage calculation, thereby altering the mean and variance of rewards within a group and ensuring that the advantages for homogeneously incorrect samples are no longer zero. Second, NGRPO employs Asymmetric Clipping, which relaxes the update magnitude for positive samples while imposing stricter constraints on that of negative samples. This serves to stabilize the exploration pressure introduced by the advantage calibration. Our experiments on Qwen2.5-Math-7B demonstrate that NGRPO significantly outperforms baselines such as PPO, GRPO, DAPO, and PSR-NSR on mathematical benchmarks including MATH500, AMC23, and AIME2025. These results validate NGRPO's ability to learn from homogeneous errors, leading to stable and substantial improvements in mathematical reasoning. Our code is available at https://github.com/nangongrui-ngr/NGRPO.

cs.LG↗

arXiv2025

UXAgent: A System for Simulating Usability Testing of Web Design with LLM Agents

Usability testing is a fundamental research method that user experience (UX) researchers use to evaluate and iterate their new designs. But what about evaluating and iterating the usability testing study design itself? Recent advances in Large Language Model-simulated Agent (LLM Agent) research inspired us to design UXAgent to support UX researchers in evaluating and iterating their study design before they conduct the real human-subject study. Our system features a Persona Generator module, an LLM Agent module, and a Universal Browser Connector module to automatically generate thousands of simulated users and to interactively test the target website. The system also provides a Result Viewer Interface so that the UX researchers can easily review and analyze the generated qualitative (e.g., agents' post-study surveys) and quantitative data (e.g., agents' interaction logs), or even interview agents directly. Through a heuristic evaluation with 16 UX researchers, participants praised the innovation of our system but also expressed concerns about the future of LLM Agent usage in UX studies.

cs.CL↗

arXiv2025

Sharp lower bounds and extremal graphs for the generalized $k$-independence number

A vertex set $S$ is a generalized $k$-independent set if the induced subgraph $G[S]$ contains no tree on $k$ vertices. The generalized $k$-independence number $α_k(G)$ is the maximum size of such a set. For a tree $T$ with $n$ vertices, Bock et al. [J. Graph Theory 103 (2023) 661-673] and Li et al. [Taiwanese J. Math. 27 (2023) 647-683] independently showed that $α_3(G)\geq \frac{2}{3}n$ and identified the extremal trees that attain this lower bound. Subsequently, Li and Zhou [Appl. Math. Comput. 484 (2025) 129018] established that $α_4(T) \geq \frac{3}{4}n$ and they further characterized all trees achieving this bound. This result was recently extended by Huang, who proved that $α_4(G)\geq \frac{3}{4}(n-ω(G))$ holds for every $n$-vertex graph, where $ω(G)$ denotes the dimension of the cycle space of $G.$ The extremal graphs attaining this lower bound were also fully characterized. Based on these findings, Huang proposed a conjecture concerning a lower bound for $α_k(G)\ (k\geq2)$ together with the corresponding extremal graphs, which naturally generalizes all the aforementioned results. In this paper, we confirm this conjecture here. We further quantify strict improvements over this bound when the equality conditions fail, and we provide a linear-time algorithm that constructs a generalized $k$-independent set of size at least $\left\lceil\frac{k-1}{k}\left(n-ω(G)\right)\right\rceil$.

math.CO↗

arXiv2025

A sharp lower bound on the generalized 4-independence number

For a graph $G$, a vertex subset $S$ is called a maximum generalized $k$-independent set if the induced subgraph $G[S]$ does not contain a $k$-tree as its subgraph, and the subset has maximum cardinality. The generalized $k$-independence number of $G$, denoted as $α_k(G)$, is the number of vertices in a maximum generalized $k$-independent set of $G$. For a graph $G$ with $n$ vertices, $m$ edges, $c$ connected components, and $c_1$ induced cycles of length 1 modulo 3, Bock et al. [J. Graph Theory 103 (2023) 661-673] showed that $α_3(G)\geq n-\frac{1}{3}(m+c+c_1)$ and identified the extremal graphs in which every two cycles are vertex-disjoint. Li and Zhou [Appl. Math. Comput. 484 (2025) 129018] proved that if $G$ is a tree with $n$ vertices, then $α_4(G) \geq \frac{3}{4}n$. They also presented all the corresponding extremal trees. In this paper, for a general graph $G$ with $n$ vertices, it is proved that $α_4(G)\geq \frac{3}{4}(n-ω(G))$ by using a different approach, where $ω(G)$ denotes the dimension of the cycle space of $G$. The graphs whose generalized $4$-independence number attains the lower bound are characterized completely. This represents a logical continuation of the work by Bock et al. and serves as a natural extension of the result by Li and Zhou.

math.CO↗

arXiv2025

Inpainting-Guided Policy Optimization for Diffusion Large Language Models

Masked diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive LLMs, offering competitive performance while supporting unique generation capabilities such as inpainting. We explore how inpainting can inform RL algorithm design for dLLMs. Aligning LLMs with reinforcement learning faces an exploration challenge: sparse reward signals and sample waste when models fail to discover correct solutions. While this inefficiency affects LLMs broadly, dLLMs offer a distinctive opportunity--their inpainting ability can guide exploration. We introduce IGPO (Inpainting Guided Policy Optimization), an RL framework that strategically inserts partial ground-truth reasoning traces during online sampling. Unlike providing full solutions, inpainting steers exploration toward promising trajectory spaces while preserving self-generated reasoning, bridging supervised fine-tuning and reinforcement learning. We apply IGPO to group-based optimization methods such as GRPO, where exploration failures cause zero advantages and gradients. IGPO restores meaningful gradients while improving sample efficiency. We also propose supervised fine-tuning on synthetically rewritten concise traces that better align with dLLM generation patterns. With additional techniques including entropy-based filtering, our training recipe yields substantial gains across three mathematical benchmarks--GSM8K, Math500, and AMC--achieving new state-of-the-art results for full-attention masked dLLMs.

cs.LG↗

arXiv2025

OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds

Multimodal large language models are evolving toward multimodal agents capable of proactively executing tasks. Most agent research focuses on GUI or embodied scenarios, which correspond to agents interacting with 2D virtual worlds or 3D real worlds, respectively. However, many complex tasks typically require agents to interleavely interact with these two types of environment. We initially mix GUI and embodied data to train, but find the performance degeneration brought by the data conflict. Further analysis reveals that GUI and embodied data exhibit synergy and conflict at the shallow and deep layers, respectively, which resembles the cerebrum-cerebellum mechanism in the human brain. To this end, we propose a high-performance generalist agent OmniActor, designed from both structural and data perspectives. First, we propose Layer-heterogeneity MoE to eliminate the conflict between GUI and embodied data by separating deep-layer parameters, while leverage their synergy by sharing shallow-layer parameters. By successfully leveraging the synergy and eliminating the conflict, OmniActor outperforms agents only trained by GUI or embodied data in GUI or embodied tasks. Furthermore, we unify the action spaces of GUI and embodied tasks, and collect large-scale GUI and embodied data from various sources for training. This significantly improves OmniActor under different scenarios, especially in GUI tasks. The code will be publicly available.

cs.CV↗

arXiv2025

Learning covariate importance for matching in policy-relevant observational research

Matching methods are widely used to reduce confounding effects in observational studies, but conventional approaches often treat all covariates as equally important, which can result in poor performance when covariates differ in their relevance to the study. We propose the Priority-Aware one-to-one Matching Algorithm (PAMA), a novel semi-supervised framework that learns a covariate importance measure from a subset data of units that are paired by experts and uses it to match additional units. It optimizes a weighted quadratic score that reflects the relevance between each covariate and the study, and iteratively updates the covariate importance measure in the score function using unlabeled data. PAMA is model-free, but we have established that the covariate importance measure -- the learned weights -- is consistent when the oracle matching rule aligns with the design. In addition, we introduce extensions that address imbalanced data, accommodate temporal covariates, and improve robustness to mispaired observations. In simulations, PAMA outperforms standard methods, particularly in high-dimensional settings and under model misspecification. Applied to a real-world study of in-person schooling and COVID-19 transmission, PAMA recovers nearly twice as many expert-designated matches as competing methods using baseline covariates. A self-taught learning extension improves performance in simulations, though its benefit is context-dependent. To our knowledge, PAMA is the first framework to apply semi-supervised learning to observational matching with covariates of unequal relevance. It offers a scalable and interpretable tool for incorporating expert insight into policy-relevant observational research.

stat.ML↗

arXiv2025

UItron: Foundational GUI Agent with Advanced Perception and Planning

GUI agent aims to enable automated operations on Mobile/PC devices, which is an important task toward achieving artificial general intelligence. The rapid advancement of VLMs accelerates the development of GUI agents, owing to their powerful capabilities in visual understanding and task planning. However, building a GUI agent remains a challenging task due to the scarcity of operation trajectories, the availability of interactive infrastructure, and the limitation of initial capabilities in foundation models. In this work, we introduce UItron, an open-source foundational model for automatic GUI agents, featuring advanced GUI perception, grounding, and planning capabilities. UItron highlights the necessity of systemic data engineering and interactive infrastructure as foundational components for advancing GUI agent development. It not only systematically studies a series of data engineering strategies to enhance training effects, but also establishes an interactive environment connecting both Mobile and PC devices. In training, UItron adopts supervised finetuning over perception and planning tasks in various GUI scenarios, and then develop a curriculum reinforcement learning framework to enable complex reasoning and exploration for online environments. As a result, UItron achieves superior performance in benchmarks of GUI perception, grounding, and planning. In particular, UItron highlights the interaction proficiency with top-tier Chinese mobile APPs, as we identified a general lack of Chinese capabilities even in state-of-the-art solutions. To this end, we manually collect over one million steps of operation trajectories across the top 100 most popular apps, and build the offline and online agent evaluation environments. Experimental results demonstrate that UItron achieves significant progress in Chinese app scenarios, propelling GUI agents one step closer to real-world application.

cs.CV↗

arXiv2025

Generative Model-Based Feature Attention Module for Video Action Analysis

Video action analysis is a foundational technology within the realm of intelligent video comprehension, particularly concerning its application in Internet of Things(IoT). However, existing methodologies overlook feature semantics in feature extraction and focus on optimizing action proposals, thus these solutions are unsuitable for widespread adoption in high-performance IoT applications due to the limitations in precision, such as autonomous driving, which necessitate robust and scalable intelligent video analytics analysis. To address this issue, we propose a novel generative attention-based model to learn the relation of feature semantics. Specifically, by leveraging the differences of actions' foreground and background, our model simultaneously learns the frame- and segment-dependencies of temporal action feature semantics, which takes advantage of feature semantics in the feature extraction effectively. To evaluate the effectiveness of our model, we conduct extensive experiments on two benchmark video task, action recognition and action detection. In the context of action detection tasks, we substantiate the superiority of our approach through comprehensive validation on widely recognized datasets. Moreover, we extend the validation of the effectiveness of our proposed method to a broader task, video action recognition. Our code is available at https://github.com/Generative-Feature-Model/GAF.

cs.CV↗

arXiv2025

DyCrowd: Towards Dynamic Crowd Reconstruction from a Large-scene Video

3D reconstruction of dynamic crowds in large scenes has become increasingly important for applications such as city surveillance and crowd analysis. However, current works attempt to reconstruct 3D crowds from a static image, causing a lack of temporal consistency and inability to alleviate the typical impact caused by occlusions. In this paper, we propose DyCrowd, the first framework for spatio-temporally consistent 3D reconstruction of hundreds of individuals' poses, positions and shapes from a large-scene video. We design a coarse-to-fine group-guided motion optimization strategy for occlusion-robust crowd reconstruction in large scenes. To address temporal instability and severe occlusions, we further incorporate a VAE (Variational Autoencoder)-based human motion prior along with a segment-level group-guided optimization. The core of our strategy leverages collective crowd behavior to address long-term dynamic occlusions. By jointly optimizing the motion sequences of individuals with similar motion segments and combining this with the proposed Asynchronous Motion Consistency (AMC) loss, we enable high-quality unoccluded motion segments to guide the motion recovery of occluded ones, ensuring robust and plausible motion recovery even in the presence of temporal desynchronization and rhythmic inconsistencies. Additionally, in order to fill the gap of no existing well-annotated large-scene video dataset, we contribute a virtual benchmark dataset, VirtualCrowd, for evaluating dynamic crowd reconstruction from large-scene videos. Experimental results demonstrate that the proposed method achieves state-of-the-art performance in the large-scene dynamic crowd reconstruction task. The code and dataset will be available for research purposes.

cs.CV↗

arXiv2025

DocTron-Formula: Generalized Formula Recognition in Complex and Structured Scenarios

Optical Character Recognition (OCR) for mathematical formula is essential for the intelligent analysis of scientific literature. However, both task-specific and general vision-language models often struggle to handle the structural diversity, complexity, and real-world variability inherent in mathematical content. In this work, we present DocTron-Formula, a unified framework built upon general vision-language models, thereby eliminating the need for specialized architectures. Furthermore, we introduce CSFormula, a large-scale and challenging dataset that encompasses multidisciplinary and structurally complex formulas at the line, paragraph, and page levels. Through straightforward supervised fine-tuning, our approach achieves state-of-the-art performance across a variety of styles, scientific domains, and complex layouts. Experimental results demonstrate that our method not only surpasses specialized models in terms of accuracy and robustness, but also establishes a new paradigm for the automated understanding of complex scientific documents.

cs.CV↗

arXiv2025

Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation

Nearly all human work is collaborative; thus, the evaluation of real-world NLP applications often requires multiple dimensions that align with diverse human perspectives. As real human evaluator resources are often scarce and costly, the emerging "LLM-as-a-judge" paradigm sheds light on a promising approach to leverage LLM agents to believably simulate human evaluators. Yet, to date, existing LLM-as-a-judge approaches face two limitations: persona descriptions of agents are often arbitrarily designed, and the frameworks are not generalizable to other tasks. To address these challenges, we propose MAJ-EVAL, a Multi-Agent-as-Judge evaluation framework that can automatically construct multiple evaluator personas with distinct dimensions from relevant text documents (e.g., research papers), instantiate LLM agents with the personas, and engage in-group debates with multi-agents to Generate multi-dimensional feedback. Our evaluation experiments in both the educational and medical domains demonstrate that MAJ-EVAL can generate evaluation results that better align with human experts' ratings compared with conventional automated evaluation metrics and existing LLM-as-a-judge methods.

cs.CL↗

arXiv2025

INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling

Hallucinations in large vision-language models (LVLMs) pose significant challenges for real-world applications, as LVLMs may generate responses that appear plausible yet remain inconsistent with the associated visual content. This issue rarely occurs in human cognition. We argue that this discrepancy arises from humans' ability to effectively leverage multimodal interaction information in data samples. Specifically, humans typically first gather multimodal information, analyze the interactions across modalities for understanding, and then express their understanding through language. Motivated by this observation, we conduct extensive experiments on popular LVLMs and obtained insights that surprisingly reveal human-like, though less pronounced, cognitive behavior of LVLMs on multimodal samples. Building on these findings, we further propose \textbf{INTER}: \textbf{Inter}action Guidance Sampling, a novel training-free algorithm that mitigate hallucinations without requiring additional data. Specifically, INTER explicitly guides LVLMs to effectively reapply their understanding of multimodal interaction information when generating responses, thereby reducing potential hallucinations. On six benchmarks including VQA and image captioning tasks, INTER achieves an average improvement of up to 3.4\% on five LVLMs compared to the state-of-the-art decoding strategy. The code will be released when the paper is accepted.

cs.CV↗