arXiv subjects

Yan Wang

Publications and source records attributed to Yan Wang.

At least 307 records · Page 17Linked to original sources

arXiv2025

Towards Efficient and Effective Multi-Camera Encoding for End-to-End Driving

We present Flex, an efficient and effective scene encoder that addresses the computational bottleneck of processing high-volume multi-camera data in end-to-end autonomous driving. Flex employs a small set of learnable scene tokens to jointly encode information from all image tokens across different cameras and timesteps. By design, our approach is geometry-agnostic, learning a compact scene representation directly from data without relying on the explicit 3D inductive biases, such as Bird-Eye-View (BEV), occupancy or tri-plane representations, which are common in prior work. This holistic encoding strategy aggressively compresses the visual input for the downstream Large Language Model (LLM) based policy model. Evaluated on a large-scale proprietary dataset of 20,000 driving hours, our Flex achieves 2.2x greater inference throughput while improving driving performance by a large margin compared to state-of-the-art methods. Furthermore, we show that these compact scene tokens develop an emergent capability for scene decomposition without any explicit supervision. Our findings challenge the prevailing assumption that 3D priors are necessary, demonstrating that a data-driven, joint encoding strategy offers a more scalable, efficient and effective path for future autonomous driving systems.

cs.CV↗

arXiv2025

Reference Recommendation based Membership Inference Attack against Hybrid-based Recommender Systems

Recommender systems have been widely deployed across various domains such as e-commerce and social media, and intelligently suggest items like products and potential friends to users based on their preferences and interaction history, which are often privacy-sensitive. Recent studies have revealed that recommender systems are prone to membership inference attacks (MIAs), where an attacker aims to infer whether or not a user's data has been used for training a target recommender system. However, existing MIAs fail to exploit the unique characteristic of recommender systems, and therefore are only applicable to mixed recommender systems consisting of two recommendation algorithms. This leaves a gap in investigating MIAs against hybrid-based recommender systems where the same algorithm utilizing user-item historical interactions and attributes of users and items serves and produces personalised recommendations. To investigate how the personalisation in hybrid-based recommender systems influences MIA, we propose a novel metric-based MIA. Specifically, we leverage the characteristic of personalisation to obtain reference recommendation for any target users. Then, a relative membership metric is proposed to exploit a target user's historical interactions, target recommendation, and reference recommendation to infer the membership of the target user's data. Finally, we theoretically and empirically demonstrate the efficacy of the proposed metric-based MIA on hybrid-based recommender systems.

cs.CR↗

arXiv2025

MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving

End-to-End autonomous driving (E2E-AD) has emerged as a new paradigm, where trajectory planning plays a crucial role. Existing studies mainly follow two directions: trajectory generation oriented, which focuses on producing high-quality trajectories with simple decision mechanisms, and trajectory selection oriented, which performs multi-dimensional evaluation to select the best trajectory yet lacks sufficient generative capability. In this work, we propose MindDrive, a harmonized framework that integrates high-quality trajectory generation with comprehensive decision reasoning. It establishes a structured reasoning paradigm of "context simulation - candidate generation - multi-objective trade-off". In particular, the proposed Future-aware Trajectory Generator (FaTG), based on a World Action Model (WaM), performs ego-conditioned "what-if" simulations to predict potential future scenes and generate foresighted trajectory candidates. Building upon this, the VLM-oriented Evaluator (VLoE) leverages the reasoning capability of a large vision-language model to conduct multi-objective evaluations across safety, comfort, and efficiency dimensions, leading to reasoned and human-aligned decision making. Extensive experiments on the NAVSIM-v1 and NAVSIM-v2 benchmarks demonstrate that MindDrive achieves state-of-the-art performance across multi-dimensional driving metrics, significantly enhancing safety, compliance, and generalization. This work provides a promising path toward interpretable and cognitively guided autonomous driving.

cs.CV↗

arXiv2025

UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement

Image quality assessment (IQA) and image restoration are fundamental problems in low-level vision. Although IQA and restoration are closely connected conceptually, most existing work treats them in isolation. Recent advances in unified multimodal understanding-generation models demonstrate promising results and indicate that stronger understanding can improve generative performance. This motivates a single model that unifies IQA and restoration and explicitly studies how IQA can guide restoration, a setting that remains largely underexplored yet highly valuable. In this paper, we propose UARE, to our knowledge the first Unified vision-language model for image quality Assessment, Restoration, and Enhancement. Built on pretrained unified understanding and generation models, we introduce a two-stage training framework. First, a progressive, easy-to-hard schedule expands from single-type distortions to higher-order mixed degradations, enabling UARE to handle multiple degradations. Second, we perform unified fine-tuning of quality understanding and restoration with interleaved text-image data, aligning IQA signals with restoration objectives. Through multi-task co-training, UARE leverages IQA to boost restoration and enhancement performance. Extensive experiments across IQA, restoration, and enhancement tasks demonstrate the effectiveness of UARE. The code and models will be available at https://github.com/lwq20020127/UARE.

cs.CV↗

arXiv2025

The Art of Storytelling in Authoritarian Regimes: Crafting State Narratives on Chinese Social Media

This article examines how authoritarian regimes construct state narratives about politically consequential events. Building on the narrative policy framework and existing research on authoritarian propaganda, we propose two dimensions that shape narrative construction: legitimacy implications -- whether events enhance or threaten regime legitimacy, and citizen verification capacity -- the extent to which citizens can evaluate official narratives through alternative sources. Using quantitative narrative analysis of Chinese social media posts by government, state media, and celebrity accounts, we extract subject-verb-object (SVO) triplets to map dominant narrative structures across four major events. Our findings show that legitimacy implications of the event shape regime's efforts in storytelling and the beliefs highlighted in the narratives, while citizen's verification capacity could balance the strategic choice between a top-down manipulation and bottom-up responsiveness of state narratives. Together, the results reveal propaganda as a complex process of narrative construction adaptive to specific contexts, offering new insights into how dynamic storytelling sustains authoritarian resilience.

cs.CY↗

arXiv2025

Exploring the topology induced by non-Markovian Liouvillian exceptional points

Non-Hermitian (NH) systems can display exotic topological phenomena without Hermitian counterparts, enabled by exceptional points (EPs). So far, investigations of NH topology have been restricted to EPs of the NH Hamiltonian, which governs the system dynamics conditional upon no quantum jumps occurring. The Liouvillian superoperator, which combines the effects of quantum jumps with NH Hamiltonian dynamics, possesses EPs (LEPs) that are significantly different from those of the corresponding NH Hamiltonian. We here study the topological features of the LEPs in the system consisting of a qubit coupled to a non-Markovian reservoir. We find that two distinct winding numbers can be simultaneously produced by executing a single closed path encircling the twofold LEP2, formed by two coinciding LEP2s, each involving a pair of coalescing eigenvectors of the extended Liouvillian superoperator. We experimentally demonstrate this purely non-Markovian phenomenon with a circuit, where a superconducting qubit is coupled to a decaying resonator which acts as a reservoir with memory effects. The results push the exploration of exceptional topology from the Markovian to non-Markovian regime.

quant-ph↗

arXiv2025

dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning

The autonomous driving community is increasingly focused on addressing the challenges posed by out-of-distribution (OOD) driving scenarios. A dominant research trend seeks to enhance end-to-end (E2E) driving systems by integrating vision-language models (VLMs), leveraging their rich world knowledge and reasoning abilities to improve generalization across diverse environments. However, most existing VLMs or vision-language agents (VLAs) are built upon autoregressive (AR) models. In this paper, we observe that existing AR-based VLMs -- limited by causal attention and sequential token generation -- often fail to maintain consistency and controllability between high-level reasoning and low-level planning. In contrast, recent discrete diffusion VLMs equipped with bidirectional attention exhibit superior controllability and reliability through iterative denoising. Building on these observations, we introduce dVLM-AD, a diffusion-based vision-language model that unifies perception, structured reasoning, and low-level planning for end-to-end driving. Evaluated on nuScenes and WOD-E2E, dVLM-AD yields more consistent reasoning-action pairs and achieves planning performance comparable to existing driving VLM/VLA systems despite a modest backbone, outperforming AR-based baselines with a 9 percent improvement in behavior-trajectory consistency and a 6 percent increase in RFS on long-tail WOD-E2E scenarios. These results suggest a controllable and reliable pathway for scalable end-to-end driving.

cs.CV↗

arXiv2025

Boundary-Aware Test-Time Adaptation for Zero-Shot Medical Image Segmentation

Due to the scarcity of annotated data and the substantial computational costs of model, conventional tuning methods in medical image segmentation face critical challenges. Current approaches to adapting pretrained models, including full-parameter and parameter-efficient fine-tuning, still rely heavily on task-specific training on downstream tasks. Therefore, zero-shot segmentation has gained increasing attention, especially with foundation models such as SAM demonstrating promising generalization capabilities. However, SAM still faces notable limitations on medical datasets due to domain shifts, making efficient zero-shot enhancement an urgent research goal. To address these challenges, we propose BA-TTA-SAM, a task-agnostic test-time adaptation framework that significantly enhances the zero-shot segmentation performance of SAM via test-time adaptation. This framework integrates two key mechanisms: (1) The encoder-level Gaussian prompt injection embeds Gaussian-based prompts directly into the image encoder, providing explicit guidance for initial representation learning. (2) The cross-layer boundary-aware attention alignment exploits the hierarchical feature interactions within the ViT backbone, aligning deep semantic responses with shallow boundary cues. Experiments on four datasets, including ISIC, Kvasir, BUSI, and REFUGE, show an average improvement of 12.4\% in the DICE score compared with SAM's zero-shot segmentation performance. The results demonstrate that our method consistently outperforms state-of-the-art models in medical image segmentation. Our framework significantly enhances the generalization ability of SAM, without requiring any source-domain training data. Extensive experiments on publicly available medical datasets strongly demonstrate the superiority of our framework. Our code is available at https://github.com/Emilychenlin/BA-TTA-SAM.

cs.CV↗

arXiv2025

Semore: VLM-guided Enhanced Semantic Motion Representations for Visual Reinforcement Learning

The growing exploration of Large Language Models (LLM) and Vision-Language Models (VLM) has opened avenues for enhancing the effectiveness of reinforcement learning (RL). However, existing LLM-based RL methods often focus on the guidance of control policy and encounter the challenge of limited representations of the backbone networks. To tackle this problem, we introduce Enhanced Semantic Motion Representations (Semore), a new VLM-based framework for visual RL, which can simultaneously extract semantic and motion representations through a dual-path backbone from the RGB flows. Semore utilizes VLM with common-sense knowledge to retrieve key information from observations, while using the pre-trained clip to achieve the text-image alignment, thereby embedding the ground-truth representations into the backbone. To efficiently fuse semantic and motion representations for decision-making, our method adopts a separately supervised approach to simultaneously guide the extraction of semantics and motion, while allowing them to interact spontaneously. Extensive experiments demonstrate that, under the guidance of VLM at the feature level, our method exhibits efficient and adaptive ability compared to state-of-art methods. All codes are released.

cs.CV↗

arXiv2025

TCC-Bench: Benchmarking the Traditional Chinese Culture Understanding Capabilities of MLLMs

Recent progress in Multimodal Large Language Models (MLLMs) have significantly enhanced the ability of artificial intelligence systems to understand and generate multimodal content. However, these models often exhibit limited effectiveness when applied to non-Western cultural contexts, which raises concerns about their wider applicability. To address this limitation, we propose the Traditional Chinese Culture understanding Benchmark (TCC-Bench), a bilingual (i.e., Chinese and English) Visual Question Answering (VQA) benchmark specifically designed for assessing the understanding of traditional Chinese culture by MLLMs. TCC-Bench comprises culturally rich and visually diverse data, incorporating images from museum artifacts, everyday life scenes, comics, and other culturally significant contexts. We adopt a semi-automated pipeline that utilizes GPT-4o in text-only mode to generate candidate questions, followed by human curation to ensure data quality and avoid potential data leakage. The benchmark also avoids language bias by preventing direct disclosure of cultural concepts within question texts. Experimental evaluations across a wide range of MLLMs demonstrate that current models still face significant challenges when reasoning about culturally grounded visual content. The results highlight the need for further research in developing culturally inclusive and context-aware multimodal systems. The code and data can be found at: https://tcc-bench.github.io/.

cs.MM↗

arXiv2025

ConfRover: Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression

Understanding protein dynamics is critical for elucidating their biological functions. The increasing availability of molecular dynamics (MD) data enables the training of deep generative models to efficiently explore the conformational space of proteins. However, existing approaches either fail to explicitly capture the temporal dependencies between conformations or do not support direct generation of time-independent samples. To address these limitations, we introduce ConfRover, an autoregressive model that simultaneously learns protein conformation and dynamics from MD trajectories, supporting both time-dependent and time-independent sampling. At the core of our model is a modular architecture comprising: (i) an encoding layer, adapted from protein folding models, that embeds protein-specific information and conformation at each time frame into a latent space; (ii) a temporal module, a sequence model that captures conformational dynamics across frames; and (iii) an SE(3) diffusion model as the structure decoder, generating conformations in continuous space. Experiments on ATLAS, a large-scale protein MD dataset of diverse structures, demonstrate the effectiveness of our model in learning conformational dynamics and supporting a wide range of downstream tasks. ConfRover is the first model to sample both protein conformations and trajectories within a single framework, offering a novel and flexible approach for learning from protein MD data. Project website: https://bytedance-seed.github.io/ConfRover.

cs.LG↗

arXiv2025

Hi-EF: Benchmarking Emotion Forecasting in Human-interaction

Affective Forecasting is an psychology task that involves predicting an individual's future emotional responses, often hampered by reliance on external factors leading to inaccuracies, and typically remains at a qualitative analysis stage. To address these challenges, we narrows the scope of Affective Forecasting by introducing the concept of Human-interaction-based Emotion Forecasting (EF). This task is set within the context of a two-party interaction, positing that an individual's emotions are significantly influenced by their interaction partner's emotional expressions and informational cues. This dynamic provides a structured perspective for exploring the patterns of emotional change, thereby enhancing the feasibility of emotion forecasting.

cs.CV↗

arXiv2025

Multi-Agent Cross-Entropy Method with Monotonic Nonlinear Critic Decomposition

Cooperative multi-agent reinforcement learning (MARL) commonly adopts centralized training with decentralized execution (CTDE), where centralized critics leverage global information to guide decentralized actors. However, centralized-decentralized mismatch (CDM) arises when the suboptimal behavior of one agent degrades others' learning. Prior approaches mitigate CDM through value decomposition, but linear decompositions allow per-agent gradients at the cost of limited expressiveness, while nonlinear decompositions improve representation but require centralized gradients, reintroducing CDM. To overcome this trade-off, we propose the multi-agent cross-entropy method (MCEM), combined with monotonic nonlinear critic decomposition (NCD). MCEM updates policies by increasing the probability of high-value joint actions, thereby excluding suboptimal behaviors. For sample efficiency, we extend off-policy learning with a modified k-step return and Retrace. Analysis and experiments demonstrate that MCEM outperforms state-of-the-art methods across both continuous and discrete action benchmarks.

cs.LG↗

arXiv2025

RefOnce: Distilling References into a Prototype Memory for Referring Camouflaged Object Detection

Referring Camouflaged Object Detection (Ref-COD) segments specified camouflaged objects in a scene by leveraging a small set of referring images. Though effective, current systems adopt a dual-branch design that requires reference images at test time, which limits deployability and adds latency and data-collection burden. We introduce a Ref-COD framework that distills references into a class-prototype memory during training and synthesizes a reference vector at inference via a query-conditioned mixture of prototypes. Concretely, we maintain an EMA-updated prototype per category and predict mixture weights from the query to produce a guidance vector without any test-time references. To bridge the representation gap between reference statistics and camouflaged query features, we propose a bidirectional attention alignment module that adapts both the query features and the class representation. Thus, our approach yields a simple, efficient path to Ref-COD without mandatory references. We evaluate the proposed method on the large-scale R2C7K benchmark. Extensive experiments demonstrate competitive or superior performance of the proposed method compared with recent state-of-the-arts. Code is available at https://github.com/yuhuan-wu/RefOnce.

cs.CV↗

arXiv2025

DeepRFTv2: Kernel-level Learning for Image Deblurring

It is well-known that if a network aims to learn how to deblur, it should understand the blur process. Blurring is naturally caused by the convolution of the sharp image with the blur kernel. Thus, allowing the network to learn the blur process in the kernel-level can significantly improve the image deblurring performance. But, current deep networks are still at the pixel-level learning stage, either performing end-to-end pixel-level restoration or stage-wise pseudo kernel-level restoration, failing to enable the deblur model to understand the essence of the blur. To this end, we propose Fourier Kernel Estimator (FKE), which considers the activation operation in Fourier space and converts the convolution problem in the spatial domain to a multiplication problem in Fourier space. Our FKE, jointly optimized with the deblur model, enables the network to learn the kernel-level blur process with low complexity and without any additional supervision. Furthermore, we change the convolution object of the kernel from ``image" to network extracted ``feature", whose rich semantic and structural information is more suitable to blur process learning. With the convolution of the feature and the estimated kernel, our model can learn the essence of blur in kernel-level. To further improve the efficiency of feature extraction, we design a decoupled multi-scale architecture with multiple hierarchical sub-unets with a reversible strategy, which allows better multi-scale encoding and decoding in low training memory. Extensive experiments indicate that our method achieves state-of-the-art motion deblurring results and show potential for handling other kernel-related problems. Analysis also shows our kernel estimator is able to learn physically meaningful kernels. The code will be available at https://github.com/DeepMed-Lab-ECNU/Single-Image-Deblur.

cs.CV↗

arXiv2025

Mitigating the Impact of Malware Evolution on API Sequence-based Windows Malware Detector

In dynamic Windows malware detection, deep learning models are extensively deployed to analyze API sequences. Methods based on API sequences play a crucial role in malware prevention. However, due to the continuous updates of APIs and the changes in API sequence calls leading to the constant evolution of malware variants, the detection capability of API sequence-based malware detection models significantly diminishes over time. We observe that the API sequences of malware samples before and after evolution usually have similar malicious semantics. Specifically, compared to the original samples, evolved malware samples often use the API sequences of the pre-evolution samples to achieve similar malicious behaviors. For instance, they access similar sensitive system resources and extend new malicious functions based on the original functionalities. In this paper, we propose a framework MME(Mitigating the impact of Malware Evolution), a framework that can enhance existing API sequence-based malware detectors and mitigate the adverse effects of malware evolution. To help detection models capture the similar semantics of these post-evolution API sequences, our framework represents API sequences using API knowledge graphs and system resource encodings and applies contrastive learning to enhance the model's encoder. Results indicate that, compared to regular Text-CNN, our framework can significantly reduce the false positive rate by 13.10% and improve the F1-Score by 8.47% on five years of data, achieving the best experimental results. Additionally, evaluations show that our framework can save on the human costs required for model maintenance. We only need 1% of the budget per month to reduce the false positive rate by 11.16% and improve the F1-Score by 6.44%.

cs.CR↗

arXiv2025

SparseWorld: A Flexible, Adaptive, and Efficient 4D Occupancy World Model Powered by Sparse and Dynamic Queries

Semantic occupancy has emerged as a powerful representation in world models for its ability to capture rich spatial semantics. However, most existing occupancy world models rely on static and fixed embeddings or grids, which inherently limit the flexibility of perception. Moreover, their ``in-place classification" over grids exhibits a potential misalignment with the dynamic and continuous nature of real scenarios. In this paper, we propose SparseWorld, a novel 4D occupancy world model that is flexible, adaptive, and efficient, powered by sparse and dynamic queries. We propose a Range-Adaptive Perception module, in which learnable queries are modulated by the ego vehicle states and enriched with temporal-spatial associations to enable extended-range perception. To effectively capture the dynamics of the scene, we design a State-Conditioned Forecasting module, which replaces classification-based forecasting with regression-guided formulation, precisely aligning the dynamic queries with the continuity of the 4D environment. In addition, We specifically devise a Temporal-Aware Self-Scheduling training strategy to enable smooth and efficient training. Extensive experiments demonstrate that SparseWorld achieves state-of-the-art performance across perception, forecasting, and planning tasks. Comprehensive visualizations and ablation studies further validate the advantages of SparseWorld in terms of flexibility, adaptability, and efficiency.

cs.CV↗

arXiv2025

Commonality in Few: Few-Shot Multimodal Anomaly Detection via Hypergraph-Enhanced Memory

Few-shot multimodal industrial anomaly detection is a critical yet underexplored task, offering the ability to quickly adapt to complex industrial scenarios. In few-shot settings, insufficient training samples often fail to cover the diverse patterns present in test samples. This challenge can be mitigated by extracting structural commonality from a small number of training samples. In this paper, we propose a novel few-shot unsupervised multimodal industrial anomaly detection method based on structural commonality, CIF (Commonality In Few). To extract intra-class structural information, we employ hypergraphs, which are capable of modeling higher-order correlations, to capture the structural commonality within training samples, and use a memory bank to store this intra-class structural prior. Firstly, we design a semantic-aware hypergraph construction module tailored for single-semantic industrial images, from which we extract common structures to guide the construction of the memory bank. Secondly, we use a training-free hypergraph message passing module to update the visual features of test samples, reducing the distribution gap between test features and features in the memory bank. We further propose a hyperedge-guided memory search module, which utilizes structural information to assist the memory search process and reduce the false positive rate. Experimental results on the MVTec 3D-AD dataset and the Eyecandies dataset show that our method outperforms the state-of-the-art (SOTA) methods in few-shot settings. Code is available at https://github.com/Sunny5250/CIF.

cs.CV↗