arXiv subjects

He Zhang

Publications and source records attributed to He Zhang.

At least 91 records · Page 5Linked to original sources

arXiv2025

OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions

Existing feedforward subject-driven video customization methods mainly study single-subject scenarios due to the difficulty of constructing multi-subject training data pairs. Another challenging problem that how to use the signals such as depth, mask, camera, and text prompts to control and edit the subject in the customized video is still less explored. In this paper, we first propose a data construction pipeline, VideoCus-Factory, to produce training data pairs for multi-subject customization from raw videos without labels and control signals such as depth-to-video and mask-to-video pairs. Based on our constructed data, we develop an Image-Video Transfer Mixed (IVTM) training with image editing data to enable instructive editing for the subject in the customized video. Then we propose a diffusion Transformer framework, OmniVCus, with two embedding mechanisms, Lottery Embedding (LE) and Temporally Aligned Embedding (TAE). LE enables inference with more subjects by using the training subjects to activate more frame embeddings. TAE encourages the generation process to extract guidance from temporally aligned control signals by assigning the same frame embeddings to the control and noise tokens. Experiments demonstrate that our method significantly surpasses state-of-the-art methods in both quantitative and qualitative evaluations. Video demos are at our project page: https://caiyuanhao1998.github.io/project/OmniVCus/. Our code, models, data are released at https://github.com/caiyuanhao1998/Open-OmniVCus

cs.CV↗

arXiv2025

BacAlarm: Mining and Simulating Composite API Traffic to Prevent Broken Access Control Violations

Broken Access Control (BAC) violations, which consistently rank among the top five security risks in the OWASP API Security Top 10, refer to unauthorized access attempts arising from BAC vulnerabilities, whose successful exploitation can impose significant risks on exposed application programming interfaces (APIs). In recent years, learning-based methods have demonstrated promising prospects in detecting various types of malicious activities. However, in real-network operation and maintenance scenarios, leveraging learning-based methods for BAC detection faces two critical challenges. Firstly, under the RESTful API design principles, most systems omit recording composite traffic for performance, and together with ethical and legal bans on directly testing real-world systems, this leads to a critical shortage of training data for detecting BAC violations. Secondly, common malicious behaviors such as SQL injection typically generate individual access traffic that is inherently anomalous. In contrast, BAC is usually composed of multiple correlated access requests that appear normal when examined in isolation. To tackle these problems, we introduce \BAC, an approach for establishing a BAC violation detection model by generating and utilizing API traffic data. The \BAC consists of an API Traffic Generator and a BAC Detector. Experimental results show that \BAC outperforms current state-of-the-art invariant-based and learning-based methods with the $\text{F}_1$ and MCC improving by 21.2\% and 24.1\%.

cs.CR↗

arXiv2025

Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing

Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend is to adopt high-dimensional features from representation encoders as generative latents. However, we empirically identify two fundamental obstacles in this paradigm: (1) the discriminative feature space lacks compact regularization, making diffusion models prone to off-manifold latents that lead to inaccurate object structures; and (2) the encoder's inherently weak pixel-level reconstruction hinders the generator from learning accurate fine-grained geometry and texture. In this paper, we propose a systematic framework to adapt understanding-oriented encoder features for generative tasks. We introduce a semantic-pixel reconstruction objective to regularize the latent space, enabling the compression of both semantic information and fine-grained details into a highly compact representation (96 channels with 16x16 spatial downsampling). This design ensures that the latent space remains semantically rich and achieves state-of-the-art image reconstruction, while remaining compact enough for accurate generation. Leveraging this representation, we design a unified Text-to-Image (T2I) and image editing model. Benchmarking against various feature spaces, we demonstrate that our approach achieves state-of-the-art reconstruction, faster convergence, and substantial performance gains in both T2I and editing tasks, validating that representation encoders can be effectively adapted into robust generative components.

cs.CV↗

arXiv2025

On planar Schrodinger-Poisson systems with repulsive interactions in the mass supercritical regime

In this paper, we investigate solutions with prescribed $L^{2}$-norm (i.e., prescribed mass) for the planar Schrödinger-Poisson (SP) equation% \begin{equation*} -Δu+λu+α\left( \log |\cdot |\ast |u|^{2}\right) u=|u|^{p-2}u,\ \text{in}\ Ω_{R} , \end{equation*}% where $λ\in \mathbb{R}$ is unknown, $α<0,p>4$ and $Ω_{R} \subseteq \mathbb{R}^{2}$ is a domain. First, we prove that the energy functional $J$ corresponding to the SP equation in $\mathbb{R}^{2}$ is unbounded both above and below on the Pohozaev manifold $\mathcal{P}$; this explains the reason why the minimax level of $J$ is difficult to determine, as referenced in [Cingolani and Jeanjean, SIAM J. Math. Anal., 2019]. Second, we establish the existence of a ground state and a high-energy solution, both with positive energy in a large bounded domain $Ω_{R} $, which is a substantial advancement in addressing an open problem proposed in [Cingolani and Jeanjean, SIAM J. Math. Anal., 2019]. Finally, we analyze the asymptotic behavior of solutions as the domain $Ω_{R} $ is extended to the entire space $\mathbb{R}^{2}$.

math.AP↗

arXiv2025

TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision Search

Diffusion Transformers (DiTs) have emerged as a highly scalable and effective backbone for image generation, outperforming U-Net architectures in both scalability and performance. However, their real-world deployment remains challenging due to high computational and memory demands. Mixed-Precision Quantization (MPQ), designed to push the limits of quantization, has demonstrated remarkable success in advancing U-Net quantization to sub-4bit settings while significantly reducing computational and memory overhead. Nevertheless, its application to DiT architectures remains limited and underexplored. In this work, we propose TreeQ, a unified framework addressing key challenges in DiT quantization. First, to tackle inefficient search and proxy misalignment, we introduce Tree Structured Search (TSS). This DiT-specific approach leverages the architecture's linear properties to traverse the solution space in O(n) time while improving objective accuracy through comparison-based pruning. Second, to unify optimization objectives, we propose Environmental Noise Guidance (ENG), which aligns Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) configurations using a single hyperparameter. Third, to mitigate information bottlenecks in ultra-low-bit regimes, we design the General Monarch Branch (GMB). This structured sparse branch prevents irreversible information loss, enabling finer detail generation. Through extensive experiments, our TreeQ framework demonstrates state-of-the-art performance on DiT-XL/2 under W3A3 and W4A4 PTQ/PEFT settings. Notably, our work is the first to achieve near-lossless 4-bit PTQ performance on DiT models. The code and models will be available at https://github.com/racoonykc/TreeQ

cs.CV↗

arXiv2025

pETNNs: Partial Evolutionary Tensor Neural Networks for Solving Time-dependent Partial Differential Equations

We present the partial evolutionary tensor neural networks (pETNNs), a novel framework for solving time-dependent partial differential equations with high accuracy and capable of handling high-dimensional problems. Our architecture incorporates tensor neural networks and evolutionary parametric approximation. A posterior error bounded is proposed to support the extrapolation capabilities. In the numerical implementations, we adopt a partial update strategy to achieve a significant reduction in computational cost while maintaining precision and robustness. Notably, as a low-rank approximation method of complex dynamical systems, pETNNs enhance the accuracy of evolutionary deep neural networks and empower computational abilities to address high-dimensional problems. Numerical experiments demonstrate the superior performance of the pETNNs in solving time-dependent complex equations, including the incompressible Navier-Stokes equations, high-dimensional heat equations, high-dimensional transport equations, and dispersive equations of higher-order derivatives.

math.NA↗

arXiv2025

The Solar Close Observations and Proximity Experiments (SCOPE) mission

The Solar Close Observations and Proximity Experiments (SCOPE) mission will send a spacecraft into the solar atmosphere at a low altitude of just 5 R_sun from the solar center. It aims to elucidate the mechanisms behind solar eruptions and coronal heating, and to directly measure the coronal magnetic field. The mission will perform in situ measurements of the current sheet between coronal mass ejections and their associated solar flares, and energetic particles produced by either reconnection or fast-mode shocks driven by coronal mass ejections. This will help to resolve the nature of reconnections in current sheets, and energetic particle acceleration regions. To investigate coronal heating, the mission will observe nano-flares on scales smaller than 70 km in the solar corona and regions smaller than 40 km in the photosphere, where magnetohydrodynamic waves originate. To study solar wind acceleration mechanisms, the mission will also track the process of ion charge-state freezing in the solar wind. A key achievement will be the observation of the coronal magnetic field at unprecedented proximity to the solar photosphere. The polar regions will also be observed at close range, and the inner edge of the solar system dust disk may be identified for the first time. This work presents the detailed background, science, and mission concept of SCOPE and discusses how we aim to address the questions mentioned above.

astro-ph.SR↗

arXiv2025

HBridge: H-Shape Bridging of Heterogeneous Experts for Unified Multimodal Understanding and Generation

Recent unified models integrate understanding experts (e.g., LLMs) with generative experts (e.g., diffusion models), achieving strong multimodal performance. However, recent advanced methods such as BAGEL and LMFusion follow the Mixture-of-Transformers (MoT) paradigm, adopting a symmetric design that mirrors one expert to another for convenient initialization and fusion, which remains suboptimal due to inherent modality discrepancies. In this work, we propose HBridge, an asymmetric H-shaped architecture that enables heterogeneous experts to optimally leverage pretrained priors from their respective modality domains. Unlike prior dense fusion strategies that straightforwardly connect all layers between experts via shared attention, HBridge selectively bridges intermediate layers, reducing over 40% attention sharing, which improves efficiency and enhances generation quality. Shallow and deep layers, which capture modality-specific representations, are decoupled, while mid-layer bridging promotes semantic alignment. To further strengthen cross-modal coherence, we introduce semantic reconstruction tokens that explicitly guide the generative expert to reconstruct visual semantic tokens of the target image. Extensive experiments across multiple benchmarks demonstrate the effectiveness and superior performance of HBridge, establishing a new paradigm for unified multimodal generation.

cs.CV↗

arXiv2025

Fault2Flow: An AlphaEvolve-Optimized Human-in-the-Loop Multi-Agent System for Fault-to-Workflow Automation

Power grid fault diagnosis is a critical process hindered by its reliance on manual, error-prone methods. Technicians must manually extract reasoning logic from dense regulations and attempt to combine it with tacit expert knowledge, which is inefficient, error-prone, and lacks maintainability as ragulations are updated and experience evolves. While Large Language Models (LLMs) have shown promise in parsing unstructured text, no existing framework integrates these two disparate knowledge sources into a single, verified, and executable workflow. To bridge this gap, we propose Fault2Flow, an LLM-based multi-agent system. Fault2Flow systematically: (1) extracts and structures regulatory logic into PASTA-formatted fault trees; (2) integrates expert knowledge via a human-in-the-loop interface for verification; (3) optimizes the reasoning logic using a novel AlphaEvolve module; and (4) synthesizes the final, verified logic into an n8n-executable workflow. Experimental validation on transformer fault diagnosis datasets confirms 100\% topological consistency and high semantic fidelity. Fault2Flow establishes a reproducible path from fault analysis to operational automation, substantially reducing expert workload.

cs.AI↗

arXiv2025

Leveraging Self-Paced Learning for Software Vulnerability Detection

Software vulnerabilities are major risks to software systems. Recently, researchers have proposed many deep learning approaches to detect software vulnerabilities. However, their accuracy is limited in practice. One of the main causes is low-quality training data (i.e., source code). To this end, we propose a new approach: SPLVD (Self-Paced Learning for Software Vulnerability Detection). SPLVD dynamically selects source code for model training based on the stage of training, which simulates the human learning process progressing from easy to hard. SPLVD has a data selector that is specifically designed for the vulnerability detection task, which enables it to prioritize the learning of easy source code. Before each training epoch, SPLVD uses the data selector to recalculate the difficulty of the source code, select new training source code, and update the data selector. When evaluating SPLVD, we first use three benchmark datasets with over 239K source code in which 25K are vulnerable for standard evaluations. Experimental results demonstrate that SPLVD achieves the highest F1 of 89.2%, 68.7%, and 43.5%, respectively, outperforming the state-of-the-art approaches. Then we collect projects from OpenHarmony, a new ecosystem that has not been learned by general LLMs, to evaluate SPLVD further. SPLVD achieves the highest precision of 90.9%, demonstrating its practical effectiveness.

cs.SE↗

arXiv2025

Human-in-the-loop Online Rejection Sampling for Robotic Manipulation

Reinforcement learning (RL) is widely used to produce robust robotic manipulation policies, but fine-tuning vision-language-action (VLA) models with RL can be unstable due to inaccurate value estimates and sparse supervision at intermediate steps. In contrast, imitation learning (IL) is easy to train but often underperforms due to its offline nature. In this paper, we propose Hi-ORS, a simple yet effective post-training method that utilizes rejection sampling to achieve both training stability and high robustness. Hi-ORS stabilizes value estimation by filtering out negatively rewarded samples during online fine-tuning, and adopts a reward-weighted supervised training objective to provide dense intermediate-step supervision. For systematic study, we develop an asynchronous inference-training framework that supports flexible online human-in-the-loop corrections, which serve as explicit guidance for learning error-recovery behaviors. Across three real-world tasks and two embodiments, Hi-ORS fine-tunes a pi-base policy to master contact-rich manipulation in just 1.5 hours of real-world training, outperforming RL and IL baselines by a substantial margin in both effectiveness and efficiency. Notably, the fine-tuned policy exhibits strong test-time scalability by reliably executing complex error-recovery behaviors to achieve better performance.

cs.RO↗

arXiv2025

Building AI Literacy at Home: How Families Navigate Children's Self-Directed Learning with AI

As generative AI becomes embedded in children's learning spaces, families face new challenges in guiding its use. Middle childhood (ages 7-13) is a critical stage where children seek autonomy even as parental influence remains strong. Using self-directed learning (SDL) as a lens, we examine how parents perceive and support children's developing AI literacy through focus groups with 13 parent-child pairs. Parents described evolving phases of engagement driven by screen time, self-motivation, and growing knowledge. While many framed AI primarily as a study tool, few considered its non-educational roles or risks, such as privacy and infrastructural embedding. Parents also noted gaps in their own AI understanding, often turning to joint exploration and engagement as a form of co-learning. Our findings reveal how families co-construct children's AI literacy, exposing tensions between practical expectations and critical literacies, and provide design implications that foster SDL while balancing autonomy and oversight.

cs.HC↗

arXiv2025

"Learning Together": AI-Mediated Support for Parental Involvement in Everyday Learning

Family learning takes place in everyday routines where children and caregivers read, practice, and develop new skills together. Although AI is increasingly present in learning environments, most systems remain child-centered and overlook the collaborative, distributed nature of family education. This paper investigates how AI can mediate family collaboration by addressing tensions of coordination, uneven workloads, and parental mediation. From a formative study with families using AI in daily learning, we identified challenges in responsibility sharing and recognition of contributions. Building on these insights, we designed FamLearn, an LLM-powered prototype that distributes tasks, visualizes contributions, and provides individualized support. A one-week field study with 11 families shows how this prototype can ease caregiving burdens, foster recognition, and enrich shared learning experiences. Our findings suggest that LLMs can move beyond the role of tutor to act as family mediators - balancing responsibilities, scaffolding intergenerational participation, and strengthening the relational fabric of family learning.

cs.HC↗

arXiv2025

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction

Existing feedforward image-to-3D methods mainly rely on 2D multi-view diffusion models that cannot guarantee 3D consistency. These methods easily collapse when changing the prompt view direction and mainly handle object-centric cases. In this paper, we propose a novel single-stage 3D diffusion model, DiffusionGS, for object generation and scene reconstruction from a single view. DiffusionGS directly outputs 3D Gaussian point clouds at each timestep to enforce view consistency and allow the model to generate robustly given prompt views of any directions, beyond object-centric inputs. Plus, to improve the capability and generality of DiffusionGS, we scale up 3D training data by developing a scene-object mixed training strategy. Experiments show that DiffusionGS yields improvements of 2.20 dB/23.25 and 1.34 dB/19.16 in PSNR/FID for objects and scenes than the state-of-the-art methods, without depth estimator. Plus, our method enjoys over 5$\times$ faster speed ($\sim$6s on an A100 GPU). Our Project page at https://caiyuanhao1998.github.io/project/DiffusionGS/ shows the video and interactive results. The code and models are publicly available at https://github.com/caiyuanhao1998/Open-DiffusionGS

cs.CV↗

arXiv2025

CHOICE: Coordinated Human-Object Interaction in Cluttered Environments for Pick-and-Place Actions

Animating human-scene interactions such as pick-and-place tasks in cluttered, complex layouts is a challenging task, with objects of a wide variation of geometries and articulation under scenarios with various obstacles. The main difficulty lies in the sparsity of the motion data compared to the wide variation of the objects and environments as well as the poor availability of transition motions between different tasks, increasing the complexity of the generalization to arbitrary conditions. To cope with this issue, we develop a system that tackles the interaction synthesis problem as a hierarchical goal-driven task. Firstly, we develop a bimanual scheduler that plans a set of keyframes for simultaneously controlling the two hands to efficiently achieve the pick-and-place task from an abstract goal signal such as the target object selected by the user. Next, we develop a neural implicit planner that generates guidance hand trajectories under diverse object shape/types and obstacle layouts. Finally, we propose a linear dynamic model for our DeepPhase controller that incorporates a Kalman filter to enable smooth transitions in the frequency domain, resulting in a more realistic and effective multi-objective control of the character.Our system can produce a wide range of natural pick-and-place movements with respect to the geometry of objects, the articulation of containers and the layout of the objects in the scene.

cs.GR↗

arXiv2025

Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion

This paper addresses the critical need for democratizing large language models (LLM) in the Arab world, a region that has seen slower progress in developing models comparable to state-of-the-art offerings like GPT-4 or ChatGPT 3.5, due to a predominant focus on mainstream languages (e.g., English and Chinese). One practical objective for an Arabic LLM is to utilize an Arabic-specific vocabulary for the tokenizer that could speed up decoding. However, using a different vocabulary often leads to a degradation of learned knowledge since many words are initially out-of-vocabulary (OOV) when training starts. Inspired by the vocabulary learning during Second Language (Arabic) Acquisition for humans, the released AraLLaMA employs progressive vocabulary expansion, which is implemented by a modified BPE algorithm that progressively extends the Arabic subwords in its dynamic vocabulary during training, thereby balancing the OOV ratio at every stage. The ablation study demonstrated the effectiveness of Progressive Vocabulary Expansion. Moreover, AraLLaMA achieves decent performance comparable to the best Arabic LLMs across a variety of Arabic benchmarks. Models, training data, benchmarks, and codes will be all open-sourced.

cs.CL↗

arXiv2025

Short-wave infrared broadband up-conversion imaging by using a noncritical phase matched bulk KTiOPO$_4$ crystal

Compared to cryogenically cooled conventional detectors, up-conversion detection enables efficient room-temperature short-wave infrared (SWIR) imaging. Although quasi-phase-matching (QPM) in periodically poled crystals offers advantages, the small crystal aperture (typically 1 mm$\times$3 mm) limits resolution. Non-poled crystals enable larger apertures but suffer walk-off aberrations. This work overcomes these limitations by using a noncritical phase matched (NCPM) KTiOPO$_4$ crystal (6 mm$\times$7 mm aperture, 0.5 mm length). Results show resolutions 6$\times$ and 2$\times$ higher than periodically poled crystals in orthogonal directions, with broad conversion band (1.3-2.2 $μ$m) covering biological and atmospheric windows. The absence of walk-off ensures better image fidelity in up-conversion process. This study presents the first comprehensive characterization of NCPM-based broadband up-conversion imaging, demonstrating performance at the theoretical resolution limit while circumventing drawbacks inherent in alternative up-conversion schemes and conventional detectors.

physics.optics↗

arXiv2025

Brevity is the Soul of Wit: Condensing Code Changes to Improve Commit Message Generation

Commit messages are valuable resources for describing why code changes are committed to repositories in version control systems (e.g., Git). They effectively help developers understand code changes and better perform software maintenance tasks. Unfortunately, developers often neglect to write high-quality commit messages in practice. Therefore, a growing body of work is proposed to generate commit messages automatically. These works all demonstrated that how to organize and represent code changes is vital in generating good commit messages, including the use of fine-grained graphs or embeddings to better represent code changes. In this study, we choose an alternative way to condense code changes before generation, i.e., proposing brief yet concise text templates consisting of the following three parts: (1) summarized code changes, (2) elicited comments, and (3) emphasized code identifiers. Specifically, we first condense code changes by using our proposed templates with the help of a heuristic-based tool named ChangeScribe, and then fine-tune CodeLlama-7B on the pairs of our proposed templates and corresponding commit messages. Our proposed templates better utilize pre-trained language models, while being naturally brief and readable to complement generated commit messages for developers. Our evaluation based on a widely used dataset showed that our approach can outperform six baselines in terms of BLEU-Norm, METEOR, and ROUGE-L, with average improvements of 51.7%, 78.7%, and 62.5%, respectively. The ablation study and human evaluation also provide further insights into the effectiveness of our approach.

cs.SE↗