Chenxi Zhao

Chenxi Zhao, Chen Zhu, Xiaokun Feng et al.

Few-step generation has been a long-standing goal, with recent one-step generation methods exemplified by MeanFlow achieving remarkable results. Existing research on MeanFlow primarily focuses on class-to-image generation. However, an intuitive yet unexplored direction is to extend the condition from fixed class labels to flexible text inputs, enabling richer content creation. Compared to the limited class labels, text conditions pose greater challenges to the model's understanding capability, necessitating the effective integration of powerful text encoders into the MeanFlow framework. Surprisingly, although incorporating text conditions appears straightforward, we find that integrating powerful LLM-based text encoders using conventional training strategies results in unsatisfactory performance. To uncover the underlying cause, we conduct detailed analyses and reveal that, due to the extremely limited number of refinement steps in the MeanFlow generation, such as only one step, the text feature representations are required to possess sufficiently high discriminability. This also explains why discrete and easily distinguishable class features perform well within the MeanFlow framework. Guided by these insights, we leverage a powerful LLM-based text encoder validated to possess the required semantic properties and adapt the MeanFlow generation process to this framework, resulting in efficient text-conditioned synthesis for the first time. Furthermore, we validate our approach on the widely used diffusion model, demonstrating significant generation performance improvements. We hope this work provides a general and practical reference for future research on text-conditioned MeanFlow generation. The code is available at https://github.com/AMAP-ML/EMF.

Peixi Wu, Ke Mei, Feipeng Ma et al.

Multimodal Large Language Models (MLLMs) have emerged as a promising foundation for universal multimodal embeddings. Recent studies have shown that reasoning-driven generative multimodal embeddings can outperform discriminative embeddings on several embedding tasks. However, Chain-of-Thought (CoT) reasoning tends to generate redundant thinking steps and introduce semantic ambiguity in the summarized answers in broader retrieval scenarios. To address this limitation, we propose Rewrite-driven Multimodal Embedding (RIME), a unified framework that jointly optimizes generation and embedding through a retrieval-friendly rewrite. Meanwhile, we present the Cross-Mode Alignment (CMA) to bridge the generative and discriminative embedding spaces, enabling flexible mutual retrieval to trade off efficiency and accuracy. Based on this, we also introduce Refine Reinforcement Learning (Refine-RL) that treats discriminative embeddings as stable semantic anchors to guide the rewrite optimization. Extensive experiments on MMEB-V2, MRMR and UVRB demonstrate that RIME substantially outperforms prior generative embedding models while significantly reducing the length of thinking.

Lincan Li, Bolin Shen, Chenxi Zhao et al.

Graph-structured data, which captures non-Euclidean relationships and interactions between entities, is growing in scale and complexity. As a result, training state-of-the-art graph machine learning (GML) models have become increasingly resource-intensive, turning these models and data into invaluable Intellectual Property (IP). To address the resource-intensive nature of model training, graph-based Machine-Learning-as-a-Service (GMLaaS) has emerged as an efficient solution by leveraging third-party cloud services for model development and management. However, deploying such models in GMLaaS also exposes them to potential threats from attackers. Specifically, while the APIs within a GMLaaS system provide interfaces for users to query the model and receive outputs, they also allow attackers to exploit and steal model functionalities or sensitive training data, posing severe threats to the safety of these GML models and the underlying graph data. To address these challenges, this survey systematically introduces the first taxonomy of threats and defenses at the level of both GML model and graph-structured data. Such a tailored taxonomy facilitates an in-depth understanding of GML IP protection. Furthermore, we present a systematic evaluation framework to assess the effectiveness of IP protection methods, introduce a curated set of benchmark datasets across various domains, and discuss their application scopes and future challenges. Finally, we establish an open-sourced versatile library named PyGIP, which evaluates various attack and defense techniques in GMLaaS scenarios and facilitates the implementation of existing benchmark methods. The library resource can be accessed at: https://labrai.github.io/PyGIP. We believe this survey will play a fundamental role in intellectual property protection for GML and provide practical recipes for the GML community.

Chenxi Zhao, Jianqiang Li, Qing Zhao et al.

Alzheimer's Disease (AD) is a neurodegenerative disorder characterized by amyloid-beta plaques and tau neurofibrillary tangles, which serve as key histopathological features. The identification and segmentation of these lesions are crucial for understanding AD progression but remain challenging due to the lack of large-scale annotated datasets and the impact of staining variations on automated image analysis. Deep learning has emerged as a powerful tool for pathology image segmentation; however, model performance is significantly influenced by variations in staining characteristics, necessitating effective stain normalization and enhancement techniques. In this study, we address these challenges by introducing an open-source dataset (ADNP-15) of neuritic plaques (i.e., amyloid deposits combined with a crown of dystrophic tau-positive neurites) in human brain whole slide images. We establish a comprehensive benchmark by evaluating five widely adopted deep learning models across four stain normalization techniques, providing deeper insights into their influence on neuritic plaque segmentation. Additionally, we propose a novel image enhancement method that improves segmentation accuracy, particularly in complex tissue structures, by enhancing structural details and mitigating staining inconsistencies. Our experimental results demonstrate that this enhancement strategy significantly boosts model generalization and segmentation accuracy. All datasets and code are open-source, ensuring transparency and reproducibility while enabling further advancements in the field.

Zhicheng Zhang, Wuyou Xia, Chenxi Zhao et al.

Multimodal large language models (MLLMs) recently showed strong capacity in integrating data among multiple modalities, empowered by a generalizable attention architecture. Advanced methods predominantly focus on language-centric tuning while less exploring multimodal tokens mixed through attention, posing challenges in high-level tasks that require fine-grained cognition and emotion understanding. In this work, we identify the attention deficit disorder problem in multimodal learning, caused by inconsistent cross-modal attention and layer-by-layer decayed attention activation. To address this, we propose a novel attention mechanism, termed MOdular Duplex Attention (MODA), simultaneously conducting the inner-modal refinement and inter-modal interaction. MODA employs a correct-after-align strategy to effectively decouple modality alignment from cross-layer token mixing. In the alignment phase, tokens are mapped to duplex modality spaces based on the basis vectors, enabling the interaction between visual and language modality. Further, the correctness of attention scores is ensured through adaptive masked attention, which enhances the model's flexibility by allowing customizable masking patterns for different modalities. Extensive experiments on 21 benchmark datasets verify the effectiveness of MODA in perception, cognition, and emotion tasks. Source code and demo are available in https://zzcheng.top/MODA.

Chenxi Zhao, Min Sheng, Junyu Liu et al.

The limited energy and computing resources of unmanned aerial vehicles (UAVs) hinder the application of aerial artificial intelligence. The utilization of split inference in UAVs garners significant attention due to its effectiveness in mitigating computing and energy requirements. However, achieving energy-efficient split inference in UAVs remains complex considering of various crucial parameters such as energy level and delay constraints, especially involving multiple tasks. In this paper, we present a two-timescale approach for energy minimization in split inference, where discrete and continuous variables are segregated into two timescales to reduce the size of action space and computational complexity. This segregation enables the utilization of tiny reinforcement learning (TRL) for selecting discrete transmission modes for sequential tasks. Moreover, optimization programming (OP) is embedded between TRL's output and reward function to optimize the continuous transmit power. Specifically, we replace the optimization of transmit power with that of transmission time to decrease the computational complexity of OP since we reveal that energy consumption monotonically decreases with increasing transmission time. The replacement significantly reduces the feasible region and enables a fast solution according to the closed-form expression for optimal transmit power. Simulation results show that the proposed algorithm can achieve a higher probability of successful task completion with lower energy consumption.

Chenxi Zhao, Daochang Wang, Siqian Zhang et al.

Deep learning methods based synthetic aperture radar (SAR) image target recognition tasks have been widely studied currently. The existing deep methods are insufficient to perceive and mine the scattering information of SAR images, resulting in performance bottlenecks and poor robustness of the algorithms. To this end, this paper proposes a novel bottom-up scattering information perception network for more interpretable target recognition by constructing the proprietary interpretation network for SAR images. Firstly, the localized scattering perceptron is proposed to replace the backbone feature extractor based on CNN networks to deeply mine the underlying scattering information of the target. Then, an unsupervised scattering part feature extraction model is proposed to robustly characterize the target scattering part information and provide fine-grained target representation. Finally, by aggregating the knowledge of target parts to form the complete target description, the interpretability and discriminative ability of the model is improved. We perform experiments on the FAST-Vehicle dataset and the SAR-ACD dataset to validate the performance of the proposed method.

Chenxi Zhao, Daochang Wang, Siqian Zhang et al.

Simulated data-assisted SAR target recognition methods are the research hotspot currently, devoted to solving the problem of limited samples. Existing works revolve around simulated images, but the large amount of irrelevant information embedded in the images, such as background, noise, etc., seriously affects the quality of the migrated information. Our work explores a new simulated data to migrate purer and key target knowledge, i.e., forward scattering center model (FSCM) which models the actual local structure of the target with strong physical meaning and interpretability. To achieve this purpose, multi-level heterogeneous knowledge transfer (MHKT) network is proposed, which fully migrates FSCM knowledge from the feature, distribution and category levels, respectively. Specifically, we permit the more suitable feature representations for the heterogeneous data and separate non-informative knowledge by task-associated information selector (TAIS), to complete purer target feature migration. In the distribution alignment, the new metric function maximum discrimination divergence (MDD) in target generic knowledge transfer (TGKT) module perceives transferable knowledge efficiently while preserving discriminative structure about classes. Moreover, category relation knowledge transfer (CRKT) module leverages the category relation consistency constraint to break the dilemma of optimization bias towards simulation data due to imbalance between simulated and measured data. Such stepwise knowledge selection and migration will ensure the integrity of the migrated FSCM knowledge. Notably, extensive experiments on two new datasets formed by FSCM data and measured SAR images demonstrate the superior performance of our method.

Ziwei Cai, Min Sheng, Junju Liu et al.

The utilization of existing terrestrial infrastructures to provide coverage for aerial users is a potentially low-cost solution. However, the already deployed terrestrial base stations (TBSs) result in weak ground-to-air (G2A) coverage due to the down-tilted antennas. Furthermore, achieving optimal coverage across the entire airspace through antenna adjustment is challenging due to the complex signal coverage requirements in three-dimensional space, especially in the vertical direction. In this paper, we propose a cooperative tri-point (CoTP) model-based method that utilizes cooperative beams to enhance the G2A coverage extension. To utilize existing TBSs for establishing effective cooperation, we prove that the cooperation among three TBSs can ensure G2A coverage with a minimum coverage overlap, and design the CoTP model to analyze the G2A coverage extension. Using the model, a cooperative coverage structure based on Delaunay triangulation is designed to divide triangular prism-shaped subspaces and corresponding TBS cooperation sets. To enable TBSs in the cooperation set to cover different height subspaces while maintaining ground coverage, we design a cooperative beam generation algorithm to maximize the coverage in the triangular prism-shaped airspace. The simulation results and field trials demonstrate that the proposed method can efficiently enhance the G2A coverage extension while guaranteeing ground coverage.