arXiv subjects

Wenwen Wang

Publications and source records attributed to Wenwen Wang.

14 recordsLinked to original sources

arXiv2026

Cascading Relevance-driven Recommendation Network for CTR Prediction in Trigger-Introduced Recommendation

E-commerce has emerged as crucial platforms for people's daily consumption and shopping interests. There is a new recommendation scenario, Trigger-Introduced Recommendation (TIR), where users click interested product, which is defined as the trigger item, containing their instant interest, and in the undertaking page following the relevant target items. Distinguished from traditional search and recommendation scenarios, trigger contains relatively strong instant interest, which is more vague and implicit compared to search terms. Relying on large amounts of labeled data, existing methods lack the exploration of trigger relevance, which affects users' immersive experience. To alleviate this problem, we propose the Cascading Relevance-driven Recommendation Network (CRRN) to emphasize the interaction and relevance between trigger and target, comprising three essential components: 1) the Trigger-Target Interaction layer extracts interaction features of trigger and target based on personalized gating. 2) Cascading Interest Fusion module explicitly estimates users' trigger intention and fuses instant and personalized interests adaptively with cascading attention blocks. 3) Category-assisted Pairwise Loss enhances trigger relevance with the guidance of category association between trigger and target. Extensive experiment results show that CRRN outperforms recent state-of-the-art methods on both industrial and public datasets. Online A/B tests further validate the effectiveness of our method. Our code is available at https://github.com/a-little-cabbage/CRRN.

cs.IR↗

arXiv2026

TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training

Recent advances in unified multimodal models (UMMs) have led to a proliferation of architectures capable of understanding, generating, and editing across visual and textual modalities. However, developing a unified framework for UMMs remains challenging due to the diversity of model architectures and the heterogeneity of training paradigms and implementation details. In this paper, we present TorchUMM, the first unified codebase for comprehensive evaluation, analysis, and post-training across diverse UMM backbones, tasks, and datasets. TorchUMM supports a broad spectrum of models covering a wide range of scales and design paradigms. Our benchmark encompasses three core task dimensions: multimodal understanding, generation, and editing, and integrates both established and novel datasets to evaluate perception, reasoning, compositionality, and instruction-following abilities. By providing a unified interface and standardized evaluation protocols, TorchUMM enables fair and reproducible comparisons across heterogeneous models and fosters deeper insights into their strengths and limitations, facilitating the development of more capable unified multimodal systems. Code is available at: https://github.com/AIFrontierLab/TorchUMM.

cs.AI↗

arXiv2026

LatentUMM: Dual Latent Alignment for Unified Multimodal Models

Unified multimodal models (UMMs) achieve strong performance in both understanding and generation by learning a shared latent space, yet they often exhibit functional inconsistency between these two capabilities. We observe that this issue does not stem from a lack of shared representations, but from the absence of explicit alignment between the transformations that map into and out of the latent space. As a result, generation and re-encoding can follow inconsistent trajectories, leading to semantic drift under modality transitions. In this work, we propose LatentUMM, a framework that constructs an enhanced shared latent space to explicitly align these transformations and improve cross-modal consistency. LatentUMM consists of two stages. First, dual latent alignment enforces consistency at both the modality and capacity levels: cross-modal alignment uses a stronger embedding model to impose structured cross-modal semantics, while dual capacity alignment enforces bidirectional consistency under generation and re-encoding. Second, latent dynamics stabilization improves robustness via stochastic latent rollouts and preference optimization, favoring trajectories that better preserve semantic consistency. Experiments show that LatentUMM consistently improves multimodal consistency across diverse architectures. Code is available at: https://github.com/AIFrontierLab/TorchUMM/tree/main/src/umm/post_training/LatentUMM.

cs.CV↗

arXiv2026

UniPath: Adaptive Coordination of Understanding and Generation for Unified Multimodal Reasoning

Unified multimodal models (UMMs) aim to integrate understanding and generation within a single architecture. However, it remains underexplored how to effectively coordinate these two capabilities for more effective and efficient reasoning. Existing coordination approaches either perform coupling during training, without explicit inference-time coordination, or impose a fixed coordination pattern for all inputs. In this work, we show that multimodal tasks exhibit substantial coordination-path diversity: different inputs favor different coordination paths. This suggests that exploiting such diversity is key to improving performance. We propose UniPath, a framework for adaptively modeling and exploiting coordination-path diversity. Instead of enforcing a single coordination pattern, we represent task solving as the selection and execution of a path, ranging from direct answering to textual inference, visual-thought construction, and hypothesis-based exploration. We construct role-aligned trajectories to train a path-conditioned executor and introduce a lightweight planner mechanism to enable input-dependent path selection. Experiments show that leveraging coordination-path diversity improves performance over fixed coordination strategies while providing interpretable intermediate behaviors. The code is available at:https://github.com/AIFrontierLab/TorchUMM/tree/main/src/umm/post_training/unipath.

cs.MM↗

arXiv2026

Computational Pathology in the Era of Emerging Foundation and Agentic AI -- International Expert Perspectives on Clinical Integration and Translational Readiness

Recent breakthroughs in artificial intelligence through foundation models and agents have accelerated the evolution of computational pathology. Demonstrated performance gains reported across academia in benchmarking datasets in predictive tasks such as diagnosis, prognosis, and treatment response have ignited substantial enthusiasm for clinical application. Despite this development momentum, real world adoption has lagged, as implementation faces economic, technical, and administrative challenges. Beyond existing discussions of technical architectures and comparative performance, this review considers how these emerging AI systems can be responsibly integrated into medical practice by connecting deployable clinical relevance with downstream analytical capabilities and their technical maturity, operational readiness, and economic and regulatory context. Drawing on perspectives from an international group, we provide a practical assessment of current capabilities and barriers to adoption in patient care settings.

cs.CE↗

arXiv2026

Can Vision Replace Text in Working Memory? Evidence from Spatial n-Back in Vision-Language Models

Working memory is a central component of intelligent behavior, providing a dynamic workspace for maintaining and updating task-relevant information. Recent work has used n-back tasks to probe working-memory-like behavior in large language models, but it is unclear whether the same probe elicits comparable computations when information is carried in a visual rather than textual code in vision-language models. We evaluate Qwen2.5 and Qwen2.5-VL on a controlled spatial n-back task presented as matched text-rendered or image-rendered grids. Across conditions, models show reliably higher accuracy and d' with text than with vision. To interpret these differences at the process level, we use trial-wise log-probability evidence and find that nominal 2/3-back often fails to reflect the instructed lag and instead aligns with a recency-locked comparison. We further show that grid size alters recent-repeat structure in the stimulus stream, thereby changing interference and error patterns. These results motivate computation-sensitive interpretations of multimodal working memory.

cs.CL↗

arXiv2025

Evading Data Provenance in Deep Neural Networks

Modern over-parameterized deep models are highly data-dependent, with large scale general-purpose and domain-specific datasets serving as the bedrock for rapid advancements. However, many datasets are proprietary or contain sensitive information, making unrestricted model training problematic. In the open world where data thefts cannot be fully prevented, Dataset Ownership Verification (DOV) has emerged as a promising method to protect copyright by detecting unauthorized model training and tracing illicit activities. Due to its diversity and superior stealth, evading DOV is considered extremely challenging. However, this paper identifies that previous studies have relied on oversimplistic evasion attacks for evaluation, leading to a false sense of security. We introduce a unified evasion framework, in which a teacher model first learns from the copyright dataset and then transfers task-relevant yet identifier-independent domain knowledge to a surrogate student using an out-of-distribution (OOD) dataset as the intermediary. Leveraging Vision-Language Models and Large Language Models, we curate the most informative and reliable subsets from the OOD gallery set as the final transfer set, and propose selectively transferring task-oriented knowledge to achieve a better trade-off between generalization and evasion effectiveness. Experiments across diverse datasets covering eleven DOV methods demonstrate our approach simultaneously eliminates all copyright identifiers and significantly outperforms nine state-of-the-art evasion attacks in both generalization and effectiveness, with moderate computational overhead. As a proof of concept, we reveal key vulnerabilities in current DOV methods, highlighting the need for long-term development to enhance practicality.

cs.CV↗

arXiv2025

The link between galaxy structure properties and star formation in local galaxies

To investigate the role of morphology in galaxy evolution, we analyze the relationships between galaxy structure, star formation, and HI gas content. Using multi-band images from the DESI Legacy Imaging Surveys, we perform detailed structural decompositions on a representative local galaxy sample from xGASS. Structural components and color properties are examined as functions of deviations from the star formation main sequence ($\rm ΔSFR_{MS}$) and HI gas deficiency ($\rm Δf_{HI}$). We find that bulge fractions decrease with higher $\rm ΔSFR_{MS}$ and lower stellar mass, indicating that star-forming galaxies are predominantly disc-dominated, while quiescent galaxies are bulge-dominated. The slope of the color ($g-r$) versus $\rm ΔSFR_{MS}$ relationship decreases from low to high stellar masses and from outer to inner regions, with greater color variation in massive galaxies. Color gradients are predominantly negative, becoming shallower in lower-mass galaxies and in the outer disk regions. We also identify inflection points in the color gradient and bulge fraction relations with $\rm ΔSFR_{MS}$, with main-sequence galaxies having the lowest bulge fractions and steepest color gradients. At fixed stellar mass, we observe only a slight correlation between bulge fraction and HI deficiency. However, outer disk colors show a stronger dependence on HI content than inner regions, and color gradients flatten as $\rm Δf_{HI}$ increases. These results suggest that HI gas is more closely linked to star-forming, disc-dominated systems, supporting the idea that gas accretion fuels star formation primarily in galaxy disks.

astro-ph.GA↗

arXiv2025

Revisiting Data Auditing in Large Vision-Language Models

With the surge of large language models (LLMs), Large Vision-Language Models (VLMs)--which integrate vision encoders with LLMs for accurate visual grounding--have shown great potential in tasks like generalist agents and robotic control. However, VLMs are typically trained on massive web-scraped images, raising concerns over copyright infringement and privacy violations, and making data auditing increasingly urgent. Membership inference (MI), which determines whether a sample was used in training, has emerged as a key auditing technique, with promising results on open-source VLMs like LLaVA (AUC > 80%). In this work, we revisit these advances and uncover a critical issue: current MI benchmarks suffer from distribution shifts between member and non-member images, introducing shortcut cues that inflate MI performance. We further analyze the nature of these shifts and propose a principled metric based on optimal transport to quantify the distribution discrepancy. To evaluate MI in realistic settings, we construct new benchmarks with i.i.d. member and non-member images. Existing MI methods fail under these unbiased conditions, performing only marginally better than chance. Further, we explore the theoretical upper bound of MI by probing the Bayes Optimality within the VLM's embedding space and find the irreducible error rate remains high. Despite this pessimistic outlook, we analyze why MI for VLMs is particularly challenging and identify three practical scenarios--fine-tuning, access to ground-truth texts, and set-based inference--where auditing becomes feasible. Our study presents a systematic view of the limits and opportunities of MI for VLMs, providing guidance for future efforts in trustworthy data auditing.

cs.CV↗

arXiv2025

Identification and analysis of galactic bars in DESI Legacy Imaging Surveys

We present a comprehensive study of bar structures in the local Universe using data from the DESI Legacy Imaging Surveys. Through isophotal analysis of 232,142 galaxies, we identify bars and classify them into strong and weak categories based on normalized bar length, using a threshold of 0.4. We find a total bar fraction of 42.9%, rising to 62.0% in disk galaxies, with strong barred galaxies accounting for 30.0%. For barred galaxies in our sample, deprojected bar lengths are measured both in absolute terms and normalized by galaxy size. Most bars are found to have absolute lengths of 3-7 kpc, and normalized bar lengths concentrated around a median value of 0.4. Bar ellipticity mainly ranges from 0.2 to 0.6, with a median value of 0.3. Our analysis reveals a bimodal distribution of bar fractions with respect to galaxy color, with weak bars in our classification being more prevalent in intermediate-color systems. With respect to stellar mass, strong bars also present a bimodal distribution, while weak bars are distributed uniformly. Normalized bar length remains relatively stable across stellar masses, while absolute bar length positively correlates with stellar mass. Cross-validation with visual classifications from GZD catalog confirms a bar identification accuracy of 93%. These results validate our automated method for bar identification and measurement, demonstrating its reliability. Our findings underscore the importance of bars in galaxy evolution and highlight the potential of upcoming wide-field surveys to deepen our understanding of barred galaxies.

astro-ph.GA↗

arXiv2025

RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering

Medical question answering requires extensive access to specialized conceptual knowledge. The current paradigm, Retrieval-Augmented Generation (RAG), acquires expertise medical knowledge through large-scale corpus retrieval and uses this knowledge to guide a general-purpose large language model (LLM) for generating answers. However, existing retrieval approaches often overlook the importance of factual knowledge, which limits the relevance of retrieved conceptual knowledge and restricts its applicability in real-world scenarios, such as clinical decision-making based on Electronic Health Records (EHRs). This paper introduces RGAR, a recurrence generation-augmented retrieval framework that retrieves both relevant factual and conceptual knowledge from dual sources (i.e., EHRs and the corpus), allowing them to interact and refine each another. Through extensive evaluation across three factual-aware medical question answering benchmarks, RGAR establishes a new state-of-the-art performance among medical RAG systems. Notably, the Llama-3.1-8B-Instruct model with RGAR surpasses the considerably larger, RAG-enhanced GPT-3.5. Our findings demonstrate the benefit of extracting factual knowledge for retrieval, which consistently yields improved generation quality.

cs.CL↗

arXiv2024

Efficient and Effective Model Extraction

Model extraction aims to create a functionally similar copy from a machine learning as a service (MLaaS) API with minimal overhead, typically for illicit profit or as a precursor to further attacks, posing a significant threat to the MLaaS ecosystem. However, recent studies have shown that model extraction is highly inefficient, particularly when the target task distribution is unavailable. In such cases, even substantially increasing the attack budget fails to produce a sufficiently similar replica, reducing the adversary's motivation to pursue extraction attacks. In this paper, we revisit the elementary design choices throughout the extraction lifecycle. We propose an embarrassingly simple yet dramatically effective algorithm, Efficient and Effective Model Extraction (E3), focusing on both query preparation and training routine. E3 achieves superior generalization compared to state-of-the-art methods while minimizing computational costs. For instance, with only 0.005 times the query budget and less than 0.2 times the runtime, E3 outperforms classical generative model based data-free model extraction by an absolute accuracy improvement of over 50% on CIFAR-10. Our findings underscore the persistent threat posed by model extraction and suggest that it could serve as a valuable benchmarking algorithm for future security evaluations.

cs.CR↗

arXiv2024

A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules

System-level emulators have been used extensively for system design, debugging and evaluation. They work by providing a system-level virtual machine to support a guest operating system (OS) running on a platform with the same or different native OS that uses the same or different instruction-set architecture. For such system-level emulation, dynamic binary translation (DBT) is one of the core technologies. A recently proposed learning-based DBT approach has shown a significantly improved performance with a higher quality of translated code using automatically learned translation rules. However, it has only been applied to user-level emulation, and not yet to system-level emulation. In this paper, we explore the feasibility of applying this approach to improve system-level emulation, and use QEMU to build a prototype. ... To achieve better performance, we leverage several optimizations that include coordination overhead reduction to reduce the overhead of each coordination, and coordination elimination and code scheduling to reduce the coordination frequency. Experimental results show that it can achieve an average of 1.36X speedup over QEMU 6.1 with negligible coordination overhead in the system emulation mode using SPEC CINT2006 as application benchmarks and 1.15X on real-world applications.

cs.OS↗

arXiv2014

The high-speed after pulse measurement system for PMT

A system employing a desktop FADC has been developed to investigate the features of 8 inches Hamamatsu PMT. The system stands out for its high-speed and informative results as a consequence of adopting fast waveform sampling technology. Recording full waveforms allows us to perform digital signal processing, pulse shape analysis, and precision timing extraction. High precision after pulse time and charge distribution characteristics are presented in this manuscript. Other photomultipliers characteristics, such as dark rate and transit time spread, can also be obtained by exploiting waveform analysis using this system.

physics.ins-det↗