arXiv subjects

Yiheng Huang

Publications and source records attributed to Yiheng Huang.

At least 19 recordsLinked to original sources

arXiv2026

VulWeaver: Weaving Broken Semantics for Grounded Vulnerability Detection

Detecting vulnerabilities in source code remains critical yet challenging, as conventional static analysis tools construct inaccurate program representations, while existing LLM-based approaches often miss essential vulnerability context and lack grounded reasoning. In this paper, we introduce VulWeaver, a novel LLM-based approach that weaves broken program semantics into accurate representations and extracts holistic vulnerability context for grounded vulnerability detection. VulWeaver first constructs an enhanced unified dependency graph (UDG) by integrating deterministic rules with LLM-based semantic inference to address static analysis inaccuracies. It then extracts holistic vulnerability context by combining explicit contexts from program slicing with implicit contexts, including usage, definition, and declaration information. Finally, VulWeaver employs meta-prompting with vulnerability type specific expert guidelines to steer LLMs through systematic reasoning, aggregated via majority voting for robustness. Extensive experiments on PrimeVul4J dataset show that VulWeaver achieves a precision of 0.82, recall of 0.71, and F1-score of 0.76, outperforming state-of-the-art learning-based, LLM-based, and agent-based baselines by 25%, 17%, and 21% in F1-score, respectively. Notably, VulWeaver attains a VP-S score of 0.58, 164% higher than the best baseline, confirming its strong discriminative power

cs.SE↗

arXiv2026

ProfMalPlus: Agent-Coordinated Detection of Malicious NPM Packages via Static-Dynamic Analysis Synergy

Open source software is vulnerable to supply-chain attacks through transitive dependencies, especially malicious code injected into NPM packages. Existing detectors often inadequately model obfuscated behavior, overlook JavaScript's object-centric features, poorly coordinate static and dynamic analysis, and lose semantic information during behavior abstraction. We propose ProfMalPlus, a malicious NPM package detector combining object-sensitive behavior graphs with coordinated LLM reasoning over annotated code slices. It identifies installation commands and entry files, then constructs graphs capturing sensitive APIs, third-party calls, and unresolved calls. From these graphs, ProfMalPlus extracts security-relevant slices and adds inline static analysis evidence. Local judge agents independently assess each slice. Self-consistency consolidates repeated judgements to reduce LLM variance, while a global judge synthesizes their reports into an entry-level verdict. For undetermined cases, a router selects either third-party enrichment, which adds registry derived module and method semantics, or dynamic augmentation, which executes the package in a sandbox to resolve runtime dependent behavior. The enriched evidence is fed back for reassessment. Finally, a localization agent reports malicious code snippets with explanations. ProfMalPlus achieves a 98.1% F1-score, outperforming state-of-the-art detectors by 3.5% to 52.6%. It also identified 597 previously unknown malicious packages, all confirmed and removed from NPM.

cs.SE↗

arXiv2026

From Component Manipulation to System Compromise: Understanding and Detecting Malicious MCP Servers

The model context protocol (MCP) standardizes how LLMs connect to external tools and data sources, enabling faster integration but introducing new attack vectors. Despite the growing adoption of MCP, existing MCP security studies classify attacks by their observable effects, obscuring how attacks behave across different MCP server components and overlooking multi-component attack chains. Meanwhile, existing defenses are less effective when facing multi-component attacks or previously unknown malicious behaviors. This work presents a component-centric perspective for understanding and detecting malicious MCP servers. First, we build the first component-centric PoC dataset of 114 malicious MCP servers where attacks are achieved as manipulation over MCP components and their compositions. We evaluate these attacks' effectiveness across two MCP hosts and five LLMs, and uncover that (1) component position shapes attack success rate; and (2) multi-component compositions often outperform single-component attacks by distributing malicious logic. Second, we propose and implement Connor, a two-stage behavioral deviation detector for malicious MCP servers. It first performs pre-execution analysis to detect malicious shell commands and extract each tool's function intent, and then conducts step-wise in-execution analysis to trace each tool's behavioral trajectories and detect deviations from its function intent. Evaluation on our curated dataset indicates that Connor achieves an F1-score of 94.6%, outperforming the state of the art by 8.9% to 59.6%. In real-world detection, Connor identifies two malicious servers.

cs.CR↗

arXiv2026

GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the final performance. We then propose Reinforcement Learning with Curriculum Sampling (RLCS) to unlock the full potential of the model, leading to comprehensive capability enhancement across a diverse range of tasks, including STEM problem solving, video understanding, content recognition, coding, grounding, GUI-based agents, and long document interpretation. In a comprehensive evaluation across 42 public benchmarks, GLM-4.5V achieves state-of-the-art performance on nearly all tasks among open-source models of similar size, and demonstrates competitive or even superior results compared to closed-source models such as Gemini-2.5-Flash on challenging tasks including Coding and GUI Agents. Meanwhile, the smaller GLM-4.1V-9B-Thinking remains highly competitive-achieving superior results to the much larger Qwen2.5-VL-72B on 29 benchmarks. We open-source both GLM-4.1V-9B-Thinking and GLM-4.5V. We further introduce the GLM-4.6V series, open-source multimodal models with native tool use and a 128K context window. A brief overview is available at https://z.ai/blog/glm-4.6v. Code, models and more information are released at https://github.com/zai-org/GLM-V.

cs.CV↗

arXiv2025

DASP: Self-supervised Nighttime Monocular Depth Estimation with Domain Adaptation of Spatiotemporal Priors

Self-supervised monocular depth estimation has achieved notable success under daytime conditions. However, its performance deteriorates markedly at night due to low visibility and varying illumination, e.g., insufficient light causes textureless areas, and moving objects bring blurry regions. To this end, we propose a self-supervised framework named DASP that leverages spatiotemporal priors for nighttime depth estimation. Specifically, DASP consists of an adversarial branch for extracting spatiotemporal priors and a self-supervised branch for learning. In the adversarial branch, we first design an adversarial network where the discriminator is composed of four devised spatiotemporal priors learning blocks (SPLB) to exploit the daytime priors. In particular, the SPLB contains a spatial-based temporal learning module (STLM) that uses orthogonal differencing to extract motion-related variations along the time axis and an axial spatial learning module (ASLM) that adopts local asymmetric convolutions with global axial attention to capture the multiscale structural information. By combining STLM and ASLM, our model can acquire sufficient spatiotemporal features to restore textureless areas and estimate the blurry regions caused by dynamic objects. In the self-supervised branch, we propose a 3D consistency projection loss to bilaterally project the target frame and source frame into a shared 3D space, and calculate the 3D discrepancy between the two projected frames as a loss to optimize the 3D structural consistency and daytime priors. Extensive experiments on the Oxford RobotCar and nuScenes datasets demonstrate that our approach achieves state-of-the-art performance for nighttime depth estimation. Ablation studies further validate the effectiveness of each component.

cs.CV↗

arXiv2025

StrokeNet: Unveiling How to Learn Fine-Grained Interactions in Online Handwritten Stroke Classification

Stroke classification remains challenging due to variations in writing style, ambiguous content, and dynamic writing positions. The core challenge in stroke classification is modeling the semantic relationships between strokes. Our observations indicate that stroke interactions are typically localized, making it difficult for existing deep learning methods to capture such fine-grained relationships. Although viewing strokes from a point-level perspective can address this issue, it introduces redundancy. However, by selecting reference points and using their sequential order to represent strokes in a fine-grained manner, this problem can be effectively solved. This insight inspired StrokeNet, a novel network architecture encoding strokes as reference pair representations (points + feature vectors), where reference points enable spatial queries and features mediate interaction modeling. Specifically, we dynamically select reference points for each stroke and sequence them, employing an Inline Sequence Attention (ISA) module to construct contextual features. To capture spatial feature interactions, we devised a Cross-Ellipse Query (CEQ) mechanism that clusters reference points and extracts features across varying spatial scales. Finally, a joint optimization framework simultaneously predicts stroke categories via reference points regression and adjacent stroke semantic transition modeling through an Auxiliary Branch (Aux-Branch). Experimental results show that our method achieves state-of-the-art performance on multiple public online handwritten datasets. Notably, on the CASIA-onDo dataset, the accuracy improves from 93.81$\%$ to 95.54$\%$, demonstrating the effectiveness and robustness of our approach.

cs.CV↗

arXiv2025

RoleMotion: A Large-Scale Dataset towards Robust Scene-Specific Role-Playing Motion Synthesis with Fine-grained Descriptions

In this paper, we introduce RoleMotion, a large-scale human motion dataset that encompasses a wealth of role-playing and functional motion data tailored to fit various specific scenes. Existing text datasets are mainly constructed decentrally as amalgamation of assorted subsets that their data are nonfunctional and isolated to work together to cover social activities in various scenes. Also, the quality of motion data is inconsistent, and textual annotation lacks fine-grained details in these datasets. In contrast, RoleMotion is meticulously designed and collected with a particular focus on scenes and roles. The dataset features 25 classic scenes, 110 functional roles, over 500 behaviors, and 10296 high-quality human motion sequences of body and hands, annotated with 27831 fine-grained text descriptions. We build an evaluator stronger than existing counterparts, prove its reliability, and evaluate various text-to-motion methods on our dataset. Finally, we explore the interplay of motion generation of body and hands. Experimental results demonstrate the high-quality and functionality of our dataset on text-driven whole-body generation.

cs.CV↗

arXiv2025

SIG-Chat: Spatial Intent-Guided Conversational Gesture Generation Involving How, When and Where

The accompanying actions and gestures in dialogue are often closely linked to interactions with the environment, such as looking toward the interlocutor or using gestures to point to the described target at appropriate moments. Speech and semantics guide the production of gestures by determining their timing (WHEN) and style (HOW), while the spatial locations of interactive objects dictate their directional execution (WHERE). Existing approaches either rely solely on descriptive language to generate motions or utilize audio to produce non-interactive gestures, thereby lacking the characterization of interactive timing and spatial intent. This significantly limits the applicability of conversational gesture generation, whether in robotics or in the fields of game and animation production. To address this gap, we present a full-stack solution. We first established a unique data collection method to simultaneously capture high-precision human motion and spatial intent. We then developed a generation model driven by audio, language, and spatial data, alongside dedicated metrics for evaluating interaction timing and spatial accuracy. Finally, we deployed the solution on a humanoid robot, enabling rich, context-aware physical interactions.

cs.GR↗

arXiv2025

A Survey and Benchmarking of Spatial-Temporal Traffic Data Imputation Models

Traffic data imputation is a critical preprocessing step in intelligent transportation systems, underpinning the reliability of downstream transportation services. Despite substantial progress in imputation models, model selection and development for practical applications remains challenging due to three key gaps: 1) the absence of a model taxonomy for traffic data imputation to trace the technological development and highlight their distinct features. 2) the lack of unified benchmarking pipeline for fair and reproducible model evaluation across standardized traffic datasets. 3) insufficient in-depth analysis that jointly compare models across multiple dimensions, including effectiveness, computational efficiency and robustness. To this end, this paper proposes practice-oriented taxonomies for traffic data missing patterns and imputation models, systematically cataloging real-world traffic data loss scenarios and analyzing the characteristics of existing models. We further introduce a unified benchmarking pipeline to comprehensively evaluate 11 representative models across various missing patterns and rates, assessing overall performance, performance under challenging scenarios, computational efficiency, and providing visualizations. This work aims to provide a holistic perspective on traffic data imputation and to serve as a practical guideline for model selection and application in intelligent transportation systems.

cs.LG↗

arXiv2025

Lifting the Veil on Composition, Risks, and Mitigations of the Large Language Model Supply Chain

Large language models (LLMs) have sparked significant impact with regard to both intelligence and productivity. Numerous enterprises have integrated LLMs into their applications to solve their own domain-specific tasks. However, integrating LLMs into specific scenarios is a systematic process that involves substantial components, which are collectively referred to as the LLM supply chain. A comprehensive understanding of LLM supply chain composition, as well as the relationships among its components, is crucial for enabling effective mitigation measures for different related risks. While existing literature has explored various risks associated with LLMs, there remains a notable gap in systematically characterizing the LLM supply chain from the dual perspectives of contributors and consumers. In this work, we develop a structured taxonomy encompassing risk types, risky actions, and corresponding mitigations across different stakeholders and components of the supply chain. We believe that a thorough review of the LLM supply chain composition, along with its inherent risks and mitigation measures, would be valuable for industry practitioners to avoid potential damages and losses, and enlightening for academic researchers to rethink existing approaches and explore new avenues of research.

cs.SE↗

arXiv2025

Killing Two Birds with One Stone: Malicious Package Detection in NPM and PyPI using a Single Model of Malicious Behavior Sequence

Open-source software (OSS) supply chain enlarges the attack surface, which makes package registries attractive targets for attacks. Recently, package registries NPM and PyPI have been flooded with malicious packages. The effectiveness of existing malicious NPM and PyPI package detection approaches is hindered by two challenges. The first challenge is how to leverage the knowledge of malicious packages from different ecosystems in a unified way such that multi-lingual malicious package detection can be feasible. The second challenge is how to model malicious behavior in a sequential way such that maliciousness can be precisely captured. To address the two challenges, we propose and implement Cerebro to detect malicious packages in NPM and PyPI. We curate a feature set based on a high-level abstraction of malicious behavior to enable multi-lingual knowledge fusing. We organize extracted features into a behavior sequence to model sequential malicious behavior. We fine-tune the BERT model to understand the semantics of malicious behavior. Extensive evaluation has demonstrated the effectiveness of Cerebro over the state-of-the-art as well as the practically acceptable efficiency. Cerebro has successfully detected 306 and 196 new malicious packages in PyPI and NPM, and received 385 thank letters from the official PyPI and NPM teams.

cs.CR↗

arXiv2024

StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework

Thanks to the powerful generative capacity of diffusion models, recent years have witnessed rapid progress in human motion generation. Existing diffusion-based methods employ disparate network architectures and training strategies. The effect of the design of each component is still unclear. In addition, the iterative denoising process consumes considerable computational overhead, which is prohibitive for real-time scenarios such as virtual characters and humanoid robots. For this reason, we first conduct a comprehensive investigation into network architectures, training strategies, and inference processs. Based on the profound analysis, we tailor each component for efficient high-quality human motion generation. Despite the promising performance, the tailored model still suffers from foot skating which is an ubiquitous issue in diffusion-based solutions. To eliminate footskate, we identify foot-ground contact and correct foot motions along the denoising process. By organically combining these well-designed components together, we present StableMoFusion, a robust and efficient framework for human motion generation. Extensive experimental results show that our StableMoFusion performs favorably against current state-of-the-art methods. Project page: https://h-y1heng.github.io/StableMoFusion-page/

cs.CV↗

arXiv2024

Diff-RNTraj: A Structure-aware Diffusion Model for Road Network-constrained Trajectory Generation

Trajectory data is essential for various applications as it records the movement of vehicles. However, publicly available trajectory datasets remain limited in scale due to privacy concerns, which hinders the development of trajectory data mining and trajectory-based applications. To address this issue, some methods for generating synthetic trajectories have been proposed to expand the scale of the dataset. However, all existing methods generate trajectories in the geographical coordinate system, which poses two limitations for their utilization in practical applications: 1) the inability to ensure that the generated trajectories are constrained on the road. 2) the lack of road-related information. In this paper, we propose a new problem to meet the practical application need, \emph{i.e.}, road network-constrained trajectory (RNTraj) generation, which can directly generate trajectories on the road network with road-related information. RNTraj is a hybrid type of data, in which each point is represented by a discrete road segment and a continuous moving rate. To generate RNTraj, we design a diffusion model called Diff-RNTraj. This model can effectively handle the hybrid RNTraj using a continuous diffusion framework by incorporating a pre-training strategy to embed hybrid RNTraj into continuous representations. During the sampling stage, a RNTraj decoder is designed to map the continuous representation generated by the diffusion model back to the hybrid RNTraj format. Furthermore, Diff-RNTraj introduces a novel loss function to enhance the spatial validity of the generated trajectories. Extensive experiments conducted on two real-world trajectory datasets demonstrate the effectiveness of the proposed model.

cs.LG↗

arXiv2024

DistillGrasp: Integrating Features Correlation with Knowledge Distillation for Depth Completion of Transparent Objects

Due to the visual properties of reflection and refraction, RGB-D cameras cannot accurately capture the depth of transparent objects, leading to incomplete depth maps. To fill in the missing points, recent studies tend to explore new visual features and design complex networks to reconstruct the depth, however, these approaches tremendously increase computation, and the correlation of different visual features remains a problem. To this end, we propose an efficient depth completion network named DistillGrasp which distillates knowledge from the teacher branch to the student branch. Specifically, in the teacher branch, we design a position correlation block (PCB) that leverages RGB images as the query and key to search for the corresponding values, guiding the model to establish correct correspondence between two features and transfer it to the transparent areas. For the student branch, we propose a consistent feature correlation module (CFCM) that retains the reliable regions of RGB images and depth maps respectively according to the consistency and adopts a CNN to capture the pairwise relationship for depth completion. To avoid the student branch only learning regional features from the teacher branch, we devise a distillation loss that not only considers the distance loss but also the object structure and edge information. Extensive experiments conducted on the ClearGrasp dataset manifest that our teacher network outperforms state-of-the-art methods in terms of accuracy and generalization, and the student network achieves competitive results with a higher speed of 48 FPS. In addition, the significant improvement in a real-world robotic grasping system illustrates the effectiveness and robustness of our proposed system.

cs.CV↗

arXiv2021

Non-Autoregressive Transformer ASR with CTC-Enhanced Decoder Input

Non-autoregressive (NAR) transformer models have achieved significantly inference speedup but at the cost of inferior accuracy compared to autoregressive (AR) models in automatic speech recognition (ASR). Most of the NAR transformers take a fixed-length sequence filled with MASK tokens or a redundant sequence copied from encoder states as decoder input, they cannot provide efficient target-side information thus leading to accuracy degradation. To address this problem, we propose a CTC-enhanced NAR transformer, which generates target sequence by refining predictions of the CTC module. Experimental results show that our method outperforms all previous NAR counterparts and achieves 50x faster decoding speed than a strong AR baseline with only 0.0 ~ 0.3 absolute CER degradation on Aishell-1 and Aishell-2 datasets.

cs.SD↗

arXiv2020

Masked Pre-trained Encoder base on Joint CTC-Transformer

This study (The work was accomplished during the internship in Tencent AI lab) addresses semi-supervised acoustic modeling, i.e. attaining high-level representations from unsupervised audio data and fine-tuning the parameters of pre-trained model with supervised data. The proposed approach adopts a two-stage training framework, consisting of masked pre-trained encoder (MPE) and Joint CTC-Transformer (JCT). In the MPE framework, part of input frames are masked and reconstructed after the encoder with massive unsupervised data. In JCT framework, compared with original Transformer, acoustic features are applied as input instead of plain text. CTC loss performs as the prediction target on top of the encoder, and decoder blocks remain unchanged. This paper presents a comparison between two-stage training method and the fully supervised JCT. In addition, this paper investigates the our approach's robustness against different volumns of training data. Experiments on the two-stage training method deliver much better performance than fully supervised model. The word error rate (WER) with two-stage training which only exploits 30\% of WSJ labeled data achieves 17\% reduction than which trained by 50\% of WSJ in a fully supervised way. Moreover, increasing unlabeled data for MPE from WSJ (81h) to Librispeech (960h) attains about 22\% WER reduction.

eess.AS↗

arXiv2020

Speech-XLNet: Unsupervised Acoustic Model Pretraining For Self-Attention Networks

Self-attention network (SAN) can benefit significantly from the bi-directional representation learning through unsupervised pretraining paradigms such as BERT and XLNet. In this paper, we present an XLNet-like pretraining scheme "Speech-XLNet" for unsupervised acoustic model pretraining to learn speech representations with SAN. The pretrained SAN is finetuned under the hybrid SAN/HMM framework. We conjecture that by shuffling the speech frame orders, the permutation in Speech-XLNet serves as a strong regularizer to encourage the SAN to make inferences by focusing on global structures through its attention weights. In addition, Speech-XLNet also allows the model to explore the bi-directional contexts for effective speech representation learning. Experiments on TIMIT and WSJ demonstrate that Speech-XLNet greatly improves the SAN/HMM performance in terms of both convergence speed and recognition accuracy compared to the one trained from randomly initialized weights. Our best systems achieve a relative improvement of 11.9% and 8.3% on the TIMIT and WSJ tasks respectively. In particular, the best system achieves a phone error rate (PER) of 13.3% on the TIMIT test set, which to our best knowledge, is the lowest PER obtained from a single system.

cs.CL↗

arXiv2020

A Random Gossip BMUF Process for Neural Language Modeling

Neural network language model (NNLM) is an essential component of industrial ASR systems. One important challenge of training an NNLM is to leverage between scaling the learning process and handling big data. Conventional approaches such as block momentum provides a blockwise model update filtering (BMUF) process and achieves almost linear speedups with no performance degradation for speech recognition. However, it needs to calculate the model average from all computing nodes (e.g., GPUs) and when the number of computing nodes is large, the learning suffers from the severe communication latency. As a consequence, BMUF is not suitable under restricted network conditions. In this paper, we present a decentralized BMUF process, in which the model is split into different components, each of which is updated by communicating to some randomly chosen neighbor nodes with the same component, followed by a BMUF-like process. We apply this method to several LSTM language modeling tasks. Experimental results show that our approach achieves consistently better performance than conventional BMUF. In particular, we obtain a lower perplexity than the single-GPU baseline on the wiki-text-103 benchmark using 4 GPUs. In addition, no performance degradation is observed when scaling to 8 and 16 GPUs.

cs.CL↗