arXiv subjects

Jiahao Zhang

Publications and source records attributed to Jiahao Zhang.

At least 91 records · Page 5Linked to original sources

arXiv2025

Cross-Modal Retrieval with Cauchy-Schwarz Divergence

Effective cross-modal retrieval requires robust alignment of heterogeneous data types. Most existing methods focus on bi-modal retrieval tasks and rely on distributional alignment techniques such as Kullback-Leibler divergence, Maximum Mean Discrepancy, and correlation alignment. However, these methods often suffer from critical limitations, including numerical instability, sensitivity to hyperparameters, and their inability to capture the full structure of the underlying distributions. In this paper, we introduce the Cauchy-Schwarz (CS) divergence, a hyperparameter-free measure that improves both training stability and retrieval performance. We further propose a novel Generalized CS (GCS) divergence inspired by Hölder's inequality. This extension enables direct alignment of three or more modalities within a unified mathematical framework through a bidirectional circular comparison scheme, eliminating the need for exhaustive pairwise comparisons. Extensive experiments on six benchmark datasets demonstrate the effectiveness of our method in both bi-modal and tri-modal retrieval tasks. The code of our CS/GCS divergence is publicly available at https://github.com/JiahaoZhang666/CSD.

cs.IR↗

arXiv2025

Estimating Global HIV Prevalence in Key Populations: A Cross-Population Hierarchical Modeling Approach

Key populations at high risk of HIV infection are critical for understanding and monitoring HIV epidemics, but global estimation is hampered by sparse, uneven data. We analyze data from 199 countries for female sex workers (FSW), men who have sex with men (MSM), and people who inject drugs (PWID) over 2011-2021, and introduce a cross-population hierarchical model that borrows strength across countries, years, and populations. The model combines region- and population-specific means with country random effects, temporal dependence, and cross-population correlations in a Gaussian Markov random-field formulation on the log-prevalence scale. In 5-fold cross-validation, the approach outperforms a regional-median baseline and reduced variants (65 percent reduction in cross-validated MSE) with well-calibrated posterior predictive coverage (93 percent). We map the 2021 prevalence and quantify the change between 2011 and 2021 using posterior prevalence ratios to identify countries with substantial increases or decreases. The framework yields globally comparable and uncertainty-quantified country-by-year prevalence estimates, enhancing evidence for resource allocation and targeted interventions for marginalized populations where routine data are limited.

stat.AP↗

arXiv2025

Score-based Generative Diffusion Models for Social Recommendations

With the prevalence of social networks on online platforms, social recommendation has become a vital technique for enhancing personalized recommendations. The effectiveness of social recommendations largely relies on the social homophily assumption, which presumes that individuals with social connections often share similar preferences. However, this foundational premise has been recently challenged due to the inherent complexity and noise present in real-world social networks. In this paper, we tackle the low social homophily challenge from an innovative generative perspective, directly generating optimal user social representations that maximize consistency with collaborative signals. Specifically, we propose the Score-based Generative Model for Social Recommendation (SGSR), which effectively adapts the Stochastic Differential Equation (SDE)-based diffusion models for social recommendations. To better fit the recommendation context, SGSR employs a joint curriculum training strategy to mitigate challenges related to missing supervision signals and leverages self-supervised learning techniques to align knowledge across social and collaborative domains. Extensive experiments on real-world datasets demonstrate the effectiveness of our approach in filtering redundant social information and improving recommendation performance.

cs.SI↗

arXiv2025

TombRaider: Entering the Vault of History to Jailbreak Large Language Models

Warning: This paper contains content that may involve potentially harmful behaviours, discussed strictly for research purposes. Jailbreak attacks can hinder the safety of Large Language Model (LLM) applications, especially chatbots. Studying jailbreak techniques is an important AI red teaming task for improving the safety of these applications. In this paper, we introduce TombRaider, a novel jailbreak technique that exploits the ability to store, retrieve, and use historical knowledge of LLMs. TombRaider employs two agents, the inspector agent to extract relevant historical information and the attacker agent to generate adversarial prompts, enabling effective bypassing of safety filters. We intensively evaluated TombRaider on six popular models. Experimental results showed that TombRaider could outperform state-of-the-art jailbreak techniques, achieving nearly 100% attack success rates (ASRs) on bare models and maintaining over 55.4% ASR against defence mechanisms. Our findings highlight critical vulnerabilities in existing LLM safeguards, underscoring the need for more robust safety defences.

cs.CR↗

arXiv2025

Exposing Privacy Risks in Graph Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) is a powerful technique for enhancing Large Language Models (LLMs) with external, up-to-date knowledge. Graph RAG has emerged as an advanced paradigm that leverages graph-based knowledge structures to provide more coherent and contextually rich answers. However, the move from plain document retrieval to structured graph traversal introduces new, under-explored privacy risks. This paper investigates the data extraction vulnerabilities of the Graph RAG systems. We design and execute tailored data extraction attacks to probe their susceptibility to leaking both raw text and structured data, such as entities and their relationships. Our findings reveal a critical trade-off: while Graph RAG systems may reduce raw text leakage, they are significantly more vulnerable to the extraction of structured entity and relationship information. We also explore potential defense mechanisms to mitigate these novel attack surfaces. This work provides a foundational analysis of the unique privacy challenges in Graph RAG and offers insights for building more secure systems.

cs.CR↗

arXiv2025

LSM-OPD: Boosting Scan in LSM-Trees by Enabling Direct Computing on Compressed Data

Scan-based operations, such as backstage compaction and value filtering, have emerged as the main bottleneck for LSM-Trees in supporting contemporary data-intensive applications. For slower external storage devices, such as HDD and SATA SSD, the scan performance is primarily limited by the I/O bandwidth (i.e., I/O bound) due to the substantial read/write amplifications in LSM-Trees. Recent adoption of high-performance storage devices, such as NVMe SSD, has transformed the main limitation to be compute-bound, emerging the impact of computational resource consumption caused by inefficient compactions and filtering. However, when the value size increases, the bottleneck for scan performance in fast devices gradually shifts towards the I/O bandwidth as well, and the overall throughput across all types of devices undergo a dramatic reduction. This paper addresses the core issues by proposing LSM-OPD, a Log-S tructured M erge-O rder- Preserving Dictionary encoding scheme that enables direct computing on compressed data within LSM-Trees. It first enables key-value-separated data flushing to disk in a densely encoded columnar layout, ideally with few bytes for a large string value (e.g., 1024 bytes), thereby significantly alleviating the frequent I/O requests caused by intensive scans. Then, it is capable of offloading the costly scan-based operations on large values, including compaction and value filtering, to lightweight dictionaries due to the order-preserving property. And SIMD-based vectorization can now be employed to maximize the evaluating performance on modern multi-core processors, further breaking the compute-bound limitations in LSM-trees. Extensive experiments demonstrate the superior efficiency of LSM-OPD in processing various workloads that involve intensive scan-based operations on diverse modern storage devices.

cs.DB↗

arXiv2025

Too Easily Fooled? Prompt Injection Breaks LLMs on Frustratingly Simple Multiple-Choice Questions

Large Language Models (LLMs) have recently demonstrated strong emergent abilities in complex reasoning and zero-shot generalization, showing unprecedented potential for LLM-as-a-judge applications in education, peer review, and data quality evaluation. However, their robustness under prompt injection attacks, where malicious instructions are embedded into the content to manipulate outputs, remains a significant concern. In this work, we explore a frustratingly simple yet effective attack setting to test whether LLMs can be easily misled. Specifically, we evaluate LLMs on basic arithmetic questions (e.g., "What is 3 + 2?") presented as either multiple-choice or true-false judgment problems within PDF files, where hidden prompts are injected into the file. Our results reveal that LLMs are indeed vulnerable to such hidden prompt injection attacks, even in these trivial scenarios, highlighting serious robustness risks for LLM-as-a-judge applications.

cs.CR↗

arXiv2025

Retrieval-Augmented Prompt for OOD Detection

Out-of-Distribution (OOD) detection is crucial for the reliable deployment of machine learning models in-the-wild, enabling accurate identification of test samples that differ from the training data distribution. Existing methods rely on auxiliary outlier samples or in-distribution (ID) data to generate outlier information for training, but due to limited outliers and their mismatch with real test OOD samples, they often fail to provide sufficient semantic supervision, leading to suboptimal performance. To address this, we propose a novel OOD detection method called Retrieval-Augmented Prompt (RAP). RAP augments a pre-trained vision-language model's prompts by retrieving external knowledge, offering enhanced semantic supervision for OOD detection. During training, RAP retrieves descriptive words for outliers based on joint similarity with external textual knowledge and uses them to augment the model's OOD prompts. During testing, RAP dynamically updates OOD prompts in real-time based on the encountered OOD samples, enabling the model to rapidly adapt to the test environment. Our extensive experiments demonstrate that RAP achieves state-of-the-art performance on large-scale OOD detection benchmarks. For example, in 1-shot OOD detection on the ImageNet-1k dataset, RAP reduces the average FPR95 by 7.05% and improves the AUROC by 1.71% compared to previous methods. Additionally, comprehensive ablation studies validate the effectiveness of each module and the underlying motivations of our approach.

cs.CV↗

arXiv2025

Towards High-Order Mean Flow Generative Models: Feasibility, Expressivity, and Provably Efficient Criteria

Generative modelling has seen significant advances through simulation-free paradigms such as Flow Matching, and in particular, the MeanFlow framework, which replaces instantaneous velocity fields with average velocities to enable efficient single-step sampling. In this work, we introduce a theoretical study on Second-Order MeanFlow, a novel extension that incorporates average acceleration fields into the MeanFlow objective. We first establish the feasibility of our approach by proving that the average acceleration satisfies a generalized consistency condition analogous to first-order MeanFlow, thereby supporting stable, one-step sampling and tractable loss functions. We then characterize its expressivity via circuit complexity analysis, showing that under mild assumptions, the Second-Order MeanFlow sampling process can be implemented by uniform threshold circuits within the $\mathsf{TC}^0$ class. Finally, we derive provably efficient criteria for scalable implementation by leveraging fast approximate attention computations: we prove that attention operations within the Second-Order MeanFlow architecture can be approximated to within $1/\mathrm{poly}(n)$ error in time $n^{2+o(1)}$. Together, these results lay the theoretical foundation for high-order flow matching models that combine rich dynamics with practical sampling efficiency.

cs.LG↗

arXiv2025

When a Paper Has 1000 Authors: Rethinking Citation Metrics in the Era of LLMs

Author-level citation metrics provide a practical, interpretable, and scalable signal of scholarly influence in a complex research ecosystem. It has been widely used as a proxy in hiring decisions. However, the past five years have seen the rapid emergence of large-scale publications in the field of large language models and foundation models, with papers featuring hundreds to thousands of co-authors and receiving tens of thousands of citations within months. For example, Gemini has 1361 authors and has been cited around 4600 times in 19 months. In such cases, traditional metrics, such as total citation count and the $h$-index, fail to meaningfully distinguish individual contributions. Therefore, we propose the following research question: How can one identify standout researchers among thousands of co-authors in large-scale LLM papers? This question is particularly important in scenarios such as academic hiring and funding decisions. In this paper, we introduce a novel citation metric designed to address this challenge by balancing contributions across large-scale and small-scale publications. We propose the SBCI index, analyze its theoretical properties, and evaluate its behavior on synthetic publication datasets. Our results demonstrate that the proposed metric provides a more robust and discriminative assessment of individual scholarly impact in the era of large-scale collaborations.

cs.DL↗

arXiv2025

T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation

Text-to-video (T2V) models have shown remarkable performance in generating visually reasonable scenes, while their capability to leverage world knowledge for ensuring semantic consistency and factual accuracy remains largely understudied. In response to this challenge, we propose T2VWorldBench, the first systematic evaluation framework for evaluating the world knowledge generation abilities of text-to-video models, covering 6 major categories, 60 subcategories, and 1,200 prompts across a wide range of domains, including physics, nature, activity, culture, causality, and object. To address both human preference and scalable evaluation, our benchmark incorporates both human evaluation and automated evaluation using vision-language models (VLMs). We evaluated the 10 most advanced text-to-video models currently available, ranging from open source to commercial models, and found that most models are unable to understand world knowledge and generate truly correct videos. These findings point out a critical gap in the capability of current text-to-video models to leverage world knowledge, providing valuable research opportunities and entry points for constructing models with robust capabilities for commonsense reasoning and factual generation.

cs.CV↗

arXiv2025

Thinking Isn't an Illusion: Overcoming the Limitations of Reasoning Models via Tool Augmentations

Large Reasoning Models (LRMs) have become a central focus in today's large language model (LLM) research, where models are designed to output a step-by-step thinking process before arriving at a final answer to handle complex reasoning tasks. Despite their promise, recent empirical studies (e.g., [Shojaee et al., 2025] from Apple) suggest that this thinking process may not actually enhance reasoning ability, where LLMs without explicit reasoning actually outperform LRMs on tasks with low or high complexity. In this work, we revisit these findings and investigate whether the limitations of LRMs persist when tool augmentations are introduced. We incorporate two types of tools, Python interpreters and scratchpads, and evaluate three representative LLMs and their LRM counterparts on Apple's benchmark reasoning puzzles. Our results show that, with proper tool use, LRMs consistently outperform their non-reasoning counterparts across all levels of task complexity. These findings challenge the recent narrative that reasoning is an illusion and highlight the potential of tool-augmented LRMs for solving complex problems.

cs.AI↗

arXiv2025

DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models

Large language models (LLMs) have recently showcased remarkable capabilities, spanning a wide range of tasks and applications, including those in the medical domain. Models like GPT-4 excel in medical question answering but may face challenges in the lack of interpretability when handling complex tasks in real clinical settings. We thus introduce the diagnostic reasoning dataset for clinical notes (DiReCT), aiming at evaluating the reasoning ability and interpretability of LLMs compared to human doctors. It contains 511 clinical notes, each meticulously annotated by physicians, detailing the diagnostic reasoning process from observations in a clinical note to the final diagnosis. Additionally, a diagnostic knowledge graph is provided to offer essential knowledge for reasoning, which may not be covered in the training data of existing LLMs. Evaluations of leading LLMs on DiReCT bring out a significant gap between their reasoning ability and that of human doctors, highlighting the critical need for models that can reason effectively in real-world clinical scenarios.

cs.CL↗

arXiv2025

The impact of the following vehicles behaviors on the car following behaviors of the ego-vehicle

Among all types of crashes, rear-end crashes dominate, which are closely related to the car-following (CF) behaviors. Traditional CF behavior models focused on the influence of the vehicle in front, but usually ignored the peer pressure from the surrounding road users, including the following vehicle (FV). Based on an open dataset, the highD dataset, we investigated whether the FV's states can affect the CF behavior of the ego-vehicle in CF events. Two types of CF events were extracted from highD database, including the tailgated events, where the time headway between the FV and the ego-vehicle (i.e., time gap) was smaller than 1 second, and the gapped events, where the time gap was larger than 3 seconds. The dynamic time warping was used to extract CF pairs with similar speed profiles of the leading vehicle (LV). Statistical analyses were conducted to compare the CF-performance metrics in tailgated and gapped events. Then, the inverse reinforcement learning was used to recover the reward function of the ego-vehicle drivers in different CF events. The results showed that the ego-driver would adjust their CF behavior in response to the pressure from a tailgating FV, by maintaining a closer distance to the LV, but at the same time, driving more cautiously. Further, drivers were still able to adjust their CF strategies based on the speed of traffic flow and the distance to the LV, even when being tailgated. These findings provide insights regarding more accurate modelling of traffic flow by considering the peer pressure from surrounding road users.

eess.SY↗

arXiv2025

Accept More, Reject Less: Reducing up to 19% Unnecessary Desk-Rejections over 11 Years of ICLR Data

The explosive growth of AI research has driven paper submissions at flagship AI conferences to unprecedented levels, necessitating many venues in 2025 (e.g., CVPR, ICCV, KDD, AAAI, IJCAI, WSDM) to enforce strict per-author submission limits and to desk-reject any excess papers by simple ID order. While this policy helps reduce reviewer workload, it may unintentionally discard valuable papers and penalize authors' efforts. In this paper, we ask an essential research question on whether it is possible to follow submission limits while minimizing needless rejections. We first formalize the current desk-rejection policies as an optimization problem, and then develop a practical algorithm based on linear programming relaxation and a rounding scheme. Under extensive evaluation on 11 years of real-world ICLR (International Conference on Learning Representations) data, our method preserves up to $19.23\%$ more papers without violating any author limits. Moreover, our algorithm is highly efficient in practice, with all results on ICLR data computed within at most 53.64 seconds. Our work provides a simple and practical desk-rejection strategy that significantly reduces unnecessary rejections, demonstrating strong potential to improve current CS conference submission policies.

cs.DS↗

arXiv2025

DualEquiNet: A Dual-Space Hierarchical Equivariant Network for Large Biomolecules

Geometric graph neural networks (GNNs) that respect E(3) symmetries have achieved strong performance on small molecule modeling, but they face scalability and expressiveness challenges when applied to large biomolecules such as RNA and proteins. These systems require models that can simultaneously capture fine-grained atomic interactions, long-range dependencies across spatially distant components, and biologically relevant hierarchical structure, such as atoms forming residues, which in turn form higher-order domains. Existing geometric GNNs, which typically operate exclusively in either Euclidean or Spherical Harmonics space, are limited in their ability to capture both the fine-scale atomic details and the long-range, symmetry-aware dependencies required for modeling the multi-scale structure of large biomolecules. We introduce DualEquiNet, a Dual-Space Hierarchical Equivariant Network that constructs complementary representations in both Euclidean and Spherical Harmonics spaces to capture local geometry and global symmetry-aware features. DualEquiNet employs bidirectional cross-space message passing and a novel Cross-Space Interaction Pooling mechanism to hierarchically aggregate atomic features into biologically meaningful units, such as residues, enabling efficient and expressive multi-scale modeling for large biomolecular systems. DualEquiNet achieves state-of-the-art performance on multiple existing benchmarks for RNA property prediction and protein modeling, and outperforms prior methods on two newly introduced 3D structural benchmarks demonstrating its broad effectiveness across a range of large biomolecule modeling tasks.

q-bio.BM↗

arXiv2025

AHSG: Adversarial Attack on High-level Semantics in Graph Neural Networks

Adversarial attacks on Graph Neural Networks aim to perturb the performance of the learner by carefully modifying the graph topology and node attributes. Existing methods achieve attack stealthiness by constraining the modification budget and differences in graph properties. However, these methods typically disrupt task-relevant primary semantics directly, which results in low defensibility and detectability of the attack. In this paper, we propose an Adversarial Attack on High-level Semantics for Graph Neural Networks (AHSG), which is a graph structure attack model that ensures the retention of primary semantics. By combining latent representations with shared primary semantics, our model retains detectable attributes and relational patterns of the original graph while leveraging more subtle changes to carry out the attack. Then we use the Projected Gradient Descent algorithm to map the latent representations with attack effects to the adversarial graph. Through experiments on robust graph deep learning models equipped with defense strategies, we demonstrate that AHSG outperforms other state-of-the-art methods in attack effectiveness. Additionally, using Contextual Stochastic Block Models to detect the attacked graph further validates that our method preserves the primary semantics of the graph.

cs.LG↗

arXiv2025

Towards Generalizable Drowsiness Monitoring with Physiological Sensors: A Preliminary Study

Accurately detecting drowsiness is vital to driving safety. Among all measures, physiological-signal-based drowsiness monitoring can be more privacy-preserving than a camera-based approach. However, conflicts exist regarding how physiological metrics are associated with different drowsiness labels across datasets. Thus, we analyzed key features from electrocardiograms (ECG), electrodermal activity (EDA), and respiratory (RESP) signals across four datasets, where different drowsiness inducers (such as fatigue and low arousal) and assessment methods (subjective vs. objective) were used. Binary logistic regression models were built to identify the physiological metrics that are associated with drowsiness. Findings indicate that distinct different drowsiness inducers can lead to different physiological responses, and objective assessments were more sensitive than subjective ones in detecting drowsiness. Further, the increased heart rate stability, reduced respiratory amplitude, and decreased tonic EDA are robustly associated with increased drowsiness. The results enhance understanding of drowsiness detection and can inform future generalizable monitoring designs.

eess.SP↗