arXiv subjects

Jiahao Zhu

Publications and source records attributed to Jiahao Zhu.

At least 19 recordsLinked to original sources

arXiv2026

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

We introduce Semantic Task Completion Video Generation, an outcome-oriented video generation task. Under this formulation, success requires both achievement of the intended outcome and semantic grounding. Semantic grounding characterizes the correspondence between the reference image and the generated outcome in terms of high-level semantics relevant to the task. Evaluation focuses on the generated outcome and requires neither the presentation of a complete sequence of intermediate task steps nor conventional appearance consistency with the reference image. To support systematic evaluation, we construct SemComp-Data, an evaluation dataset covering six domains. Each instance comprises a reference image, a detailed instruction, a brief instruction, and an outcome-centric video clip. A scalable four-stage curation pipeline converts raw videos into standardized SemComp-Data instances. We further introduce SemComp-Bench, an evaluation protocol that uses a vision-language model (VLM) to answer structured binary questions. SemComp-Bench reports the OA Score and the GR Score for Outcome Achievement and Generation Reliability, respectively. Experiments on representative video generation models show that achieving intended outcomes while maintaining task-relevant semantic grounding in reference images remains challenging.

cs.CV↗

arXiv2026

Efficient LiDAR Reflectance Compression via Scanning Serialization

Reflectance attributes in LiDAR point clouds provide essential information for downstream tasks but remain underexplored in neural compression methods. To address this, we introduce SerLiC, a serialization-based neural compression framework to fully exploit the intrinsic characteristics of LiDAR reflectance. SerLiC first transforms 3D LiDAR point clouds into 1D sequences via scan-order serialization, offering a device-centric perspective for reflectance analysis. Each point is then tokenized into a contextual representation comprising its sensor scanning index, radial distance, and prior reflectance, for effective dependencies exploration. For efficient sequential modeling, Mamba is incorporated with a dual parallelization scheme, enabling simultaneous autoregressive dependency capture and fast processing. Extensive experiments demonstrate that SerLiC attains over 2x volume reduction against the original reflectance data, outperforming the state-of-the-art method by up to 22% reduction of compressed bits while using only 2% of its parameters. Moreover, a lightweight version of SerLiC achieves > 10 fps (frames per second) with just 111K parameters, which is attractive for real-world applications.

cs.CV↗

arXiv2026

Memory-Conditioned Tool Calling for Camera-First Visual Agents

Recognition tells an agent what is in an image; personal memory affects what is worth looking up next. In a camera-first setting the user can send only an image, so the agent must form the lookups. We study whether personal visual memory improves agent-side tool choice and tool arguments, and thereby more user-aligned multi-tool lookups. The design uses a three-layer personal visual memory (profile, short-term focus, observations) that is loaded on each turn to condition an LLM tool-calling loop under camera-first intake, and includes conflict-aware write-back intended to refresh the user model for later captures. On 800 images paired with synthetic memory blocks constructed for controlled ablation, removing the full three-layer memory block reduces tool-query relevance by 0.47 points absolute (4.21 -> 3.74 on a 5-point scale; 11.2% relative) and end-to-end utility by 0.082 absolute (0.842 -> 0.760; 9.7% relative). These results measure memory conditioning of tool policy under image-only intake with fixed synthetic blocks, not multi-session write-back from live user histories.

cs.CV↗

arXiv2026

PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud Compression

LiDAR point cloud compression is vital for autonomous systems to handle massive data from high-resolution sensors. While learned entropy modeling built upon octree structures yields high compression gains, it faces two critical bottlenecks: 1) prohibitive latency, particularly during decoding, caused by causal, multi-stage context modeling; and 2) a rigid performance-latency trade-off, preventing a single model from adapting to varying constraints. These limitations stem from the tight coupling between the context aggregation backbone and probability prediction. To address this, we propose PACE, a new framework that reformulates ancestral context aggregation as a non-causal backbone and confines causality to a lightweight, stage-scalable predictor, eliminating repetitive backbone executions and reducing computational overhead. The predictor supports an arbitrary number of prediction stages, enabling seamless adaptation across diverse performance-latency trade-offs without reloading parameters. Experiments demonstrate that PACE sets a new state-of-the-art in compression efficiency, achieving notable BD-BR savings and reducing decoding latency by over 90\% in autoregressive mode, making it attractive for practical applications.

cs.CV↗

arXiv2026

LibraGen: Playing a Balance Game in Subject-Driven Video Generation

With the advancement of video generation foundation models (VGFMs), customized generation, particularly subject-to-video (S2V), has attracted growing attention. However, a key challenge lies in balancing the intrinsic priors of a VGFM, such as motion coherence, visual aesthetics, and prompt alignment, with its newly derived S2V capability. Existing methods often neglect this balance by enhancing one aspect at the expense of others. To address this, we propose LibraGen, a novel framework that views extending foundation models for S2V generation as a balance game between intrinsic VGFM strengths and S2V capability. Specifically, guided by the core philosophy of "Raising the Fulcrum, Tuning to Balance," we identify data quality as the fulcrum and advocate a quality-over-quantity approach. We construct a hybrid pipeline that combines automated and manual data filtering to improve overall data quality. To further harmonize the VGFM's native capabilities with its S2V extension, we introduce a Tune-to-Balance post-training paradigm. During supervised fine-tuning, both cross-pair and in-pair data are incorporated, and model merging is employed to achieve an effective trade-off. Subsequently, two tailored direct preference optimization (DPO) pipelines, namely Consis-DPO and Real-Fake DPO, are designed and merged to consolidate this balance. During inference, we introduce a time-dependent dynamic classifier-free guidance scheme to enable flexible and fine-grained control. Experimental results demonstrate that LibraGen outperforms both open-source and commercial S2V models using only thousand-scale training data.

cs.CV↗

arXiv2026

Plug-and-Hide: Provable and Adjustable Diffusion Generative Steganography

Diffusion model-based generative image steganography (DM-GIS) is an emerging paradigm that leverages the generative power of diffusion models to conceal secret messages without requiring pre-existing cover images. In this paper, we identify a fundamental trade-off between stego image quality, steganographic security, and extraction reliability within the DM-GIS framework. Drawing on this insight, we propose \textbf{PA-B2G}, a \textbf{P}rovable and \textbf{A}djustable \textbf{B}it-to-\textbf{G}aussian mapping. Theoretically, PA-B2G guarantees the reversible encoding of arbitrary-length bit sequences into pure Gaussian noise; practically, it enables fine-grained control over the balance between image fidelity, security, and extraction accuracy. By integrating PA-B2G with probability-flow ordinary differential equations (PF-ODEs), we establish a theoretically invertible mapping between secret bitstreams and stego images. PA-B2G is model-agnostic and can be seamlessly integrated into mainstream diffusion models without additional training or fine-tuning, making it also suitable for diffusion model watermarking. Extensive experiments validate our theoretical analysis of the inherent DM-GIS trade-offs and demonstrate that our method flexibly supports arbitrary payloads while achieving competitive image quality and security. Furthermore, our method exhibits strong resilience to lossy processing in watermarking applications, highlighting its practical utility.

cs.CR↗

arXiv2025

Chinese Morph Resolution in E-commerce Live Streaming Scenarios

E-commerce live streaming in China, particularly on platforms like Douyin, has become a major sales channel, but hosts often use morphs to evade scrutiny and engage in false advertising. This study introduces the Live Auditory Morph Resolution (LiveAMR) task to detect such violations. Unlike previous morph research focused on text-based evasion in social media and underground industries, LiveAMR targets pronunciation-based evasion in health and medical live streams. We constructed the first LiveAMR dataset with 86,790 samples and developed a method to transform the task into a text-to-text generation problem. By leveraging large language models (LLMs) to generate additional training data, we improved performance and demonstrated that morph resolution significantly enhances live streaming regulation.

cs.CL↗

arXiv2025

Adaptive 3D Mesh Steganography Based on Feature-Preserving Distortion

Current 3D mesh steganography algorithms relying on geometric modification are prone to detection by steganalyzers. In traditional steganography, adaptive steganography has proven to be an efficient means of enhancing steganography security. Taking inspiration from this, we propose a highly adaptive embedding algorithm, guided by the principle of minimizing a carefully crafted distortion through efficient steganography codes. Specifically, we tailor a payload-limited embedding optimization problem for 3D settings and devise a feature-preserving distortion (FPD) to measure the impact of message embedding. The distortion takes on an additive form and is defined as a weighted difference of the effective steganalytic subfeatures utilized by the current 3D steganalyzers. With practicality in mind, we refine the distortion to enhance robustness and computational efficiency. By minimizing the FPD, our algorithm can preserve mesh features to a considerable extent, including steganalytic and geometric features, while achieving a high embedding capacity. During the practical embedding phase, we employ the Q-layered syndrome trellis code (STC). However, calculating the bit modification probability (BMP) for each layer of the Q-layered STC, given the variation of Q, can be cumbersome. To address this issue, we design a universal and automatic approach for the BMP calculation. The experimental results demonstrate that our algorithm achieves state-of-the-art performance in countering 3D steganalysis. Code is available at https://github.com/zjhJOJO/3D-steganography-based-on-FPD.git.

cs.MM↗

arXiv2025

Developing and Validating a High-Throughput Robotic System for the Accelerated Development of Porous Membranes

The development of porous polymeric membranes remains a labor-intensive process, often requiring extensive trial and error to identify optimal fabrication parameters. In this study, we present a fully automated platform for membrane fabrication and characterization via nonsolvent-induced phase separation (NIPS). The system integrates automated solution preparation, blade casting, controlled immersion, and compression testing, allowing precise control over fabrication parameters such as polymer concentration and ambient humidity. The modular design allows parallel processing and reproducible handling of samples, reducing experimental time and increasing consistency. Compression testing is introduced as a sensitive mechanical characterization method for estimating membrane stiffness and as a proxy to infer porosity and intra-sample uniformity through automated analysis of stress-strain curves. As a proof of concept to demonstrate the effectiveness of the system, NIPS was carried out with polysulfone, the green solvent PolarClean, and water as the polymer, solvent, and nonsolvent, respectively. Experiments conducted with the automated system reproduced expected effects of polymer concentration and ambient humidity on membrane properties, namely increased stiffness and uniformity with increasing polymer concentration and humidity variations in pore morphology and mechanical response. The developed automated platform supports high-throughput experimentation and is well-suited for integration into self-driving laboratory workflows, offering a scalable and reproducible foundation for data-driven optimization of porous polymeric membranes through NIPS.

cs.RO↗

arXiv2025

SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation

Recent advancements in text-to-3D generation improve the visual quality of Score Distillation Sampling (SDS) and its variants by directly connecting Consistency Distillation (CD) to score distillation. However, due to the imbalance between self-consistency and cross-consistency, these CD-based methods inherently suffer from improper conditional guidance, leading to sub-optimal generation results. To address this issue, we present SegmentDreamer, a novel framework designed to fully unleash the potential of consistency models for high-fidelity text-to-3D generation. Specifically, we reformulate SDS through the proposed Segmented Consistency Trajectory Distillation (SCTD), effectively mitigating the imbalance issues by explicitly defining the relationship between self- and cross-consistency. Moreover, SCTD partitions the Probability Flow Ordinary Differential Equation (PF-ODE) trajectory into multiple sub-trajectories and ensures consistency within each segment, which can theoretically provide a significantly tighter upper bound on distillation error. Additionally, we propose a distillation pipeline for a more swift and stable generation. Extensive experiments demonstrate that our SegmentDreamer outperforms state-of-the-art methods in visual quality, enabling high-fidelity 3D asset creation through 3D Gaussian Splatting (3DGS).

cs.CV↗

arXiv2025

GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting

3D Gaussian Splatting (3DGS) has recently created impressive 3D assets for various applications. However, considering security, capacity, invisibility, and training efficiency, the copyright of 3DGS assets is not well protected as existing watermarking methods are unsuited for its rendering pipeline. In this paper, we propose GuardSplat, an innovative and efficient framework for watermarking 3DGS assets. Specifically, 1) We propose a CLIP-guided pipeline for optimizing the message decoder with minimal costs. The key objective is to achieve high-accuracy extraction by leveraging CLIP's aligning capability and rich representations, demonstrating exceptional capacity and efficiency. 2) We tailor a Spherical-Harmonic-aware (SH-aware) Message Embedding module for 3DGS, seamlessly embedding messages into the SH features of each 3D Gaussian while preserving the original 3D structure. This enables watermarking 3DGS assets with minimal fidelity trade-offs and prevents malicious users from removing the watermarks from the model files, meeting the demands for invisibility and security. 3) We present an Anti-distortion Message Extraction module to improve robustness against various distortions. Experiments demonstrate that GuardSplat outperforms state-of-the-art and achieves fast optimization speed. Project page is at https://narcissusex.github.io/GuardSplat, and Code is at https://github.com/NarcissusEx/GuardSplat.

cs.CV↗

arXiv2025

GS-KGC: A Generative Subgraph-based Framework for Knowledge Graph Completion with Large Language Models

Knowledge graph completion (KGC) focuses on identifying missing triples in a knowledge graph (KG) , which is crucial for many downstream applications. Given the rapid development of large language models (LLMs), some LLM-based methods are proposed for KGC task. However, most of them focus on prompt engineering while overlooking the fact that finer-grained subgraph information can aid LLMs in generating more accurate answers. In this paper, we propose a novel completion framework called \textbf{G}enerative \textbf{S}ubgraph-based KGC (GS-KGC), which utilizes subgraph information as contextual reasoning and employs a QA approach to achieve the KGC task. This framework primarily includes a subgraph partitioning algorithm designed to generate negatives and neighbors. Specifically, negatives can encourage LLMs to generate a broader range of answers, while neighbors provide additional contextual insights for LLM reasoning. Furthermore, we found that GS-KGC can discover potential triples within the KGs and new facts beyond the KGs. Experiments conducted on four common KGC datasets highlight the advantages of the proposed GS-KGC, e.g., it shows a 5.6\% increase in Hits@3 compared to the LLM-based model CP-KGC on the FB15k-237N, and a 9.3\% increase over the LLM-based model TECHS on the ICEWS14.

cs.CL↗

arXiv2024

Dynamic ETF Portfolio Optimization Using enhanced Transformer-Based Models for Covariance and Semi-Covariance Prediction(Work in Progress)

This study explores the use of Transformer-based models to predict both covariance and semi-covariance matrices for ETF portfolio optimization. Traditional portfolio optimization techniques often rely on static covariance estimates or impose strict model assumptions, which may fail to capture the dynamic and non-linear nature of market fluctuations. Our approach leverages the power of Transformer models to generate adaptive, real-time predictions of asset covariances, with a focus on the semi-covariance matrix to account for downside risk. The semi-covariance matrix emphasizes negative correlations between assets, offering a more nuanced approach to risk management compared to traditional methods that treat all volatility equally. Through a series of experiments, we demonstrate that Transformer-based predictions of both covariance and semi-covariance significantly enhance portfolio performance. Our results show that portfolios optimized using the semi-covariance matrix outperform those optimized with the standard covariance matrix, particularly in volatile market conditions. Moreover, the use of the Sortino ratio, a risk-adjusted performance metric that focuses on downside risk, further validates the effectiveness of our approach in managing risk while maximizing returns. These findings have important implications for asset managers and investors, offering a dynamic, data-driven framework for portfolio construction that adapts more effectively to shifting market conditions. By integrating Transformer-based models with the semi-covariance matrix for improved risk management, this research contributes to the growing field of machine learning in finance and provides valuable insights for optimizing ETF portfolios.

q-fin.PM↗

arXiv2024

Enhancing Text-based Knowledge Graph Completion with Zero-Shot Large Language Models: A Focus on Semantic Enhancement

The design and development of text-based knowledge graph completion (KGC) methods leveraging textual entity descriptions are at the forefront of research. These methods involve advanced optimization techniques such as soft prompts and contrastive learning to enhance KGC models. The effectiveness of text-based methods largely hinges on the quality and richness of the training data. Large language models (LLMs) can utilize straightforward prompts to alter text data, thereby enabling data augmentation for KGC. Nevertheless, LLMs typically demand substantial computational resources. To address these issues, we introduce a framework termed constrained prompts for KGC (CP-KGC). This CP-KGC framework designs prompts that adapt to different datasets to enhance semantic richness. Additionally, CP-KGC employs a context constraint strategy to effectively identify polysemous entities within KGC datasets. Through extensive experimentation, we have verified the effectiveness of this framework. Even after quantization, the LLM (Qwen-7B-Chat-int4) still enhances the performance of text-based KGC methods \footnote{Code and datasets are available at \href{https://github.com/sjlmg/CP-KGC}{https://github.com/sjlmg/CP-KGC}}. This study extends the performance limits of existing models and promotes further integration of KGC with LLMs.

cs.CL↗

arXiv2024

VividDreamer: Towards High-Fidelity and Efficient Text-to-3D Generation

Text-to-3D generation aims to create 3D assets from text-to-image diffusion models. However, existing methods face an inherent bottleneck in generation quality because the widely-used objectives such as Score Distillation Sampling (SDS) inappropriately omit U-Net jacobians for swift generation, leading to significant bias compared to the "true" gradient obtained by full denoising sampling. This bias brings inconsistent updating direction, resulting in implausible 3D generation e.g., color deviation, Janus problem, and semantically inconsistent details). In this work, we propose Pose-dependent Consistency Distillation Sampling (PCDS), a novel yet efficient objective for diffusion-based 3D generation tasks. Specifically, PCDS builds the pose-dependent consistency function within diffusion trajectories, allowing to approximate true gradients through minimal sampling steps (1-3). Compared to SDS, PCDS can acquire a more accurate updating direction with the same sampling time (1 sampling step), while enabling few-step (2-3) sampling to trade compute for higher generation quality. For efficient generation, we propose a coarse-to-fine optimization strategy, which first utilizes 1-step PCDS to create the basic structure of 3D objects, and then gradually increases PCDS steps to generate fine-grained details. Extensive experiments demonstrate that our approach outperforms the state-of-the-art in generation quality and training efficiency, conspicuously alleviating the implausible 3D generation issues caused by the deviated updating direction. Moreover, it can be simply applied to many 3D generative applications to yield impressive 3D assets, please see our project page: https://narcissusex.github.io/VividDreamer.

cs.CV↗

arXiv2024

Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning

Code Pre-trained Models (CodePTMs) based vulnerability detection have achieved promising results over recent years. However, these models struggle to generalize as they typically learn superficial mapping from source code to labels instead of understanding the root causes of code vulnerabilities, resulting in poor performance in real-world scenarios beyond the training instances. To tackle this challenge, we introduce VulLLM, a novel framework that integrates multi-task learning with Large Language Models (LLMs) to effectively mine deep-seated vulnerability features. Specifically, we construct two auxiliary tasks beyond the vulnerability detection task. First, we utilize the vulnerability patches to construct a vulnerability localization task. Second, based on the vulnerability features extracted from patches, we leverage GPT-4 to construct a vulnerability interpretation task. VulLLM innovatively augments vulnerability classification by leveraging generative LLMs to understand complex vulnerability patterns, thus compelling the model to capture the root causes of vulnerabilities rather than overfitting to spurious features of a single task. The experiments conducted on six large datasets demonstrate that VulLLM surpasses seven state-of-the-art models in terms of effectiveness, generalization, and robustness.

cs.CR↗

arXiv2024

DP-MDM: Detail-Preserving MR Reconstruction via Multiple Diffusion Models

Detail features of magnetic resonance images play a cru-cial role in accurate medical diagnosis and treatment, as they capture subtle changes that pose challenges for doc-tors when performing precise judgments. However, the widely utilized naive diffusion model has limitations, as it fails to accurately capture more intricate details. To en-hance the quality of MRI reconstruction, we propose a comprehensive detail-preserving reconstruction method using multiple diffusion models to extract structure and detail features in k-space domain instead of image do-main. Moreover, virtual binary modal masks are utilized to refine the range of values in k-space data through highly adaptive center windows, which allows the model to focus its attention more efficiently. Last but not least, an inverted pyramid structure is employed, where the top-down image information gradually decreases, ena-bling a cascade representation. The framework effective-ly represents multi-scale sampled data, taking into ac-count the sparsity of the inverted pyramid architecture, and utilizes cascade training data distribution to repre-sent multi-scale data. Through a step-by-step refinement approach, the method refines the approximation of de-tails. Finally, the proposed method was evaluated by con-ducting experiments on clinical and public datasets. The results demonstrate that the proposed method outper-forms other methods.

cs.CV↗

arXiv2023

Simulation of a Solar Jet Formed from an Untwisting Flux Rope Interacting with a Null Point

Coronal jets are eruptions identified by a collimated, sometimes twisted spire. They are small-scale energetic events compared with flares. Using multi-wavelength observations from the Solar Dynamics Observatory/Atmospheric Imaging Assembly (SDO/AIA) and a magnetogram from Hinode/Spectro-Polarimeter (Hinode/SP), we study the formation and evolution of a jet occurring on 2019 March 22 in the active region NOAA 12736. A zero-$β$ magnetohydrodynamic (MHD) simulation is conducted to probe the initiation mechanisms and appearance of helical motion during this jet event. As the simulation reveals, there are two pairs of field lines at the jet base, indicating two distinct magnetic structures. One structure outlines a flux rope lying low above the photosphere in the north of a bald patch region and the other structure shows a null point high in the corona in the south. The untwisting motions of the observed flux rope was recovered by adding an anomalous (artificial) resistivity in the simulation. A reconnection occurs at the bald patch in the flux rope structure, which is moving upwards and simultaneously encounters the field lines of the null point structure. The interaction of the two structures results in the jet while the twist of the flux rope is transferred to the jet by the reconnected field lines. The rotational motion of the flux rope is proposed to be an underlying trigger of this process and responsible for helical motions in the jet spire.

astro-ph.SR↗