Xu Zhou

Chaoyang Wang, Kaituo Feng, Dongyang Chen et al.

Recent advances have shown that multimodal large language models (MLLMs) benefit from multimodal interleaved chain-of-thought (CoT) with vision tool interactions. However, existing open-source models often exhibit blind tool-use reasoning patterns, invoking vision tools even when they are unnecessary, which significantly increases inference overhead and degrades model performance. To this end, we propose AdaTooler-V, an MLLM that performs adaptive tool-use by determining whether a visual problem truly requires tools. First, we introduce AT-GRPO, a reinforcement learning algorithm that adaptively adjusts reward scales based on the Tool Benefit Score of each sample, encouraging the model to invoke tools only when they provide genuine improvements. Moreover, we construct two datasets to support training: AdaTooler-V-CoT-100k for SFT cold start and AdaTooler-V-300k for RL with verifiable rewards across single-image, multi-image, and video data. Experiments across twelve benchmarks demonstrate the strong reasoning capability of AdaTooler-V, outperforming existing methods in diverse visual reasoning tasks. Notably, AdaTooler-V-7B achieves an accuracy of 89.8\% on the high-resolution benchmark V*, surpassing the commercial proprietary model GPT-4o and Gemini 1.5 Pro. All code, models, and data are released.

Weisong Zhao, Tong Wang, Zichang Tan et al.

Group-based reinforcement learning has evolved from the arithmetic mean of GRPO to the geometric mean of GMPO. While GMPO improves stability by constraining a conservative objective, it shares a fundamental limitation with GRPO: reliance on a fixed aggregation geometry that ignores the evolving and heterogeneous nature of each trajectory. In this work, we unify these approaches under Power-Mean Policy Optimization (PMPO), a generalized framework that parameterizes the aggregation geometry via the power-mean geometry exponent p. Within this framework, GRPO and GMPO are recovered as special cases. Theoretically, we demonstrate that adjusting p modulates the concentration of gradient updates, effectively reweighting tokens based on their advantage contribution. To determine p adaptively, we introduce a Clip-aware Effective Sample Size (ESS) mechanism. Specifically, we propose a deterministic rule that maps a trajectory clipping fraction to a target ESS. Then, we solve for the specific p to align the trajectory induced ESS with this target one. This allows PMPO to dynamically transition between the aggressive arithmetic mean for reliable trajectories and the conservative geometric mean for unstable ones. Experiments on multiple mathematical reasoning benchmarks demonstrate that PMPO outperforms strong baselines.

Chaoyang Wang, Zeyu Zhang, Meng Meng et al.

Visual reasoning is crucial for understanding complex multimodal data and advancing Artificial General Intelligence. Existing methods enhance the reasoning capability of Multimodal Large Language Models (MLLMs) through Reinforcement Learning (RL) fine-tuning (e.g., GRPO). However, current RL approaches sample action groups solely from the policy model itself, which limits the upper boundary of the model's reasoning capability and leads to inefficient training. To address these limitations, this paper proposes a novel RL framework called \textbf{Vision-EKIPL}. The core of this framework lies in introducing high-quality actions generated by external auxiliary models during the RL training process to guide the optimization of the policy model. The policy learning with knowledge infusion from external models significantly expands the model's exploration space, effectively improves the reasoning boundary, and substantially accelerates training convergence speed and efficiency. Experimental results demonstrate that our proposed Vision-EKIPL achieved up to a 5\% performance improvement on the Reason-RFT-CoT Benchmark compared to the state-of-the-art (SOTA). It reveals that Vision-EKIPL can overcome the limitations of traditional RL methods, significantly enhance the visual reasoning performance of MLLMs, and provide a new effective paradigm for research in this field.

Songhao Han, Wei Huang, Hairong Shi et al.

The advancement of Large Vision Language Models (LVLMs) has significantly improved multimodal understanding, yet challenges remain in video reasoning tasks due to the scarcity of high-quality, large-scale datasets. Existing video question-answering (VideoQA) datasets often rely on costly manual annotations with insufficient granularity or automatic construction methods with redundant frame-by-frame analysis, limiting their scalability and effectiveness for complex reasoning. To address these challenges, we introduce VideoEspresso, a novel dataset that features VideoQA pairs preserving essential spatial details and temporal coherence, along with multimodal annotations of intermediate reasoning steps. Our construction pipeline employs a semantic-aware method to reduce redundancy, followed by generating QA pairs using GPT-4o. We further develop video Chain-of-Thought (CoT) annotations to enrich reasoning processes, guiding GPT-4o in extracting logical relationships from QA pairs and video content. To exploit the potential of high-quality VideoQA pairs, we propose a Hybrid LVLMs Collaboration framework, featuring a Frame Selector and a two-stage instruction fine-tuned reasoning LVLM. This framework adaptively selects core frames and performs CoT reasoning using multimodal evidence. Evaluated on our proposed benchmark with 14 tasks against 9 popular LVLMs, our method outperforms existing baselines on most tasks, demonstrating superior video reasoning capabilities. Our code and dataset will be released at: https://github.com/hshjerry/VideoEspresso

Yinchao Ma, Yuyang Tang, Wenfei Yang et al.

Single object tracking aims to localize target object with specific reference modalities (bounding box, natural language or both) in a sequence of specific video modalities (RGB, RGB+Depth, RGB+Thermal or RGB+Event.). Different reference modalities enable various human-machine interactions, and different video modalities are demanded in complex scenarios to enhance tracking robustness. Existing trackers are designed for single or several video modalities with single or several reference modalities, which leads to separate model designs and limits practical applications. Practically, a unified tracker is needed to handle various requirements. To the best of our knowledge, there is still no tracker that can perform tracking with these above reference modalities across these video modalities simultaneously. Thus, in this paper, we present a unified tracker, UniSOT, for different combinations of three reference modalities and four video modalities with uniform parameters. Extensive experimental results on 18 visual tracking, vision-language tracking and RGB+X tracking benchmarks demonstrate that UniSOT shows superior performance against modality-specific counterparts. Notably, UniSOT outperforms previous counterparts by over 3.0\% AUC on TNL2K across all three reference modalities and outperforms Un-Track by over 2.0\% main metric across all three RGB+X video modalities.

Shaofei Huang, Rui Ling, Tianrui Hui et al.

Audio-Visual Segmentation (AVS) aims to segment sound-producing objects in video frames based on the associated audio signal. Prevailing AVS methods typically adopt an audio-centric Transformer architecture, where object queries are derived from audio features. However, audio-centric Transformers suffer from two limitations: perception ambiguity caused by the mixed nature of audio, and weakened dense prediction ability due to visual detail loss. To address these limitations, we propose a new Vision-Centric Transformer (VCT) framework that leverages vision-derived queries to iteratively fetch corresponding audio and visual information, enabling queries to better distinguish between different sounding objects from mixed audio and accurately delineate their contours. Additionally, we also introduce a Prototype Prompted Query Generation (PPQG) module within our VCT framework to generate vision-derived queries that are both semantically aware and visually rich through audio prototype prompting and pixel context grouping, facilitating audio-visual information aggregation. Extensive experiments demonstrate that our VCT framework achieves new state-of-the-art performances on three subsets of the AVSBench dataset. The code is available at https://github.com/spyflying/VCT_AVS.

Chi Liu, Xin Chen, Xu Zhou et al.

Large Language Models (LLMs) have achieved remarkable success, underpinning diverse AI applications. However, they often suffer from performance degradation due to factors such as catastrophic forgetting during Supervised Fine-Tuning (SFT), quantization, and pruning. In this work, we introduce a performance recovery framework based on Self-Distillation Fine-Tuning (SDFT) that effectively restores model capabilities. Complementing this practical contribution, we provide a rigorous theoretical explanation for the underlying recovery mechanism. We posit that an LLM's generative capability fundamentally relies on the high-dimensional manifold constructed by its hidden layers. To investigate this, we employ Centered Kernel Alignment (CKA) to quantify the alignment between student and teacher activation trajectories, leveraging its invariance to orthogonal transformations and scaling. Our experiments demonstrate a strong correlation between performance recovery and manifold alignment, substantiating the claim that self-distillation effectively aligns the student's high-dimensional manifold with the optimal structure represented by the teacher. This study bridges the gap between practical recovery frameworks and geometric representation theory, offering new insights into the internal mechanisms of self-distillation.

Zhixin Cheng, Xiaotian Yin, Jiacheng Deng et al.

Typical detection-free methods for image-to-point cloud registration leverage transformer-based architectures to aggregate cross-modal features and establish correspondences. However, they often struggle under challenging conditions, where noise disrupts similarity computation and leads to incorrect correspondences. Moreover, without dedicated designs, it remains difficult to effectively select informative and correlated representations across modalities, thereby limiting the robustness and accuracy of registration. To address these challenges, we propose a novel cross-modal registration framework composed of two key modules: the Iterative Agents Selection (IAS) module and the Reliable Agents Interaction (RAI) module. IAS enhances structural feature awareness with phase maps and employs reinforcement learning principles to efficiently select reliable agents. RAI then leverages these selected agents to guide cross-modal interactions, effectively reducing mismatches and improving overall robustness. Extensive experiments on the RGB-D Scenes v2 and 7-Scenes benchmarks demonstrate that our method consistently achieves state-of-the-art performance.

Yiheng Li, Zichang Tan, Zhen Lei et al.

In AI-generated image detection, current cutting-edge methods typically adapt pre-trained foundation models through partial-parameter fine-tuning. However, these approaches often struggle to generalize to forgeries from unseen generators, as the fine-tuned models capture only limited patterns from training data and fail to reflect the evolving traits of new ones. To overcome this limitation, we propose Image-Adaptive Prompt Learning (IAPL), a novel paradigm that dynamically adjusts the prompts fed into the encoder according to each testing image, rather than fixing them after training. This design significantly enhances robustness and adaptability to diverse forged images. The dynamic prompts integrate conditional information with test-time adaptive tokens through a lightweight learnable scaling factor. The conditional information is produced by a Conditional Information Learner, which leverages CNN-based feature extractors to model both forgery-specific and general conditions. The test-time adaptive tokens are optimized during inference on a single sample by enforcing prediction consistency across multiple views, ensuring that the parameters align with the current image. For the final decision, the optimal input with the highest prediction confidence is selected. Extensive experiments show that IAPL achieves state-of-the-art performance, with mean accuracies of 95.61% and 96.7% on the widely used UniversalFakeDetect and GenImage datasets, respectively. Codes and weights will be released on https://github.com/liyih/IAPL.

Leilei Du, Xu Zhou, Peng Cheng et al.

In applications such as event monitoring, log analysis, and video querying, $w$-event privacy protects individual data within a sliding time window while supporting accurate stream statistics. Existing studies on infinite data streams mainly assume homogeneous privacy requirements for all users, which cannot capture user-specific privacy preferences. This paper studies personalized $w$-event privacy for private data stream estimation. We first design the Personalized Window Size Mechanism (PWSM), which supports personalized privacy requirements at each time slot. Based on PWSM, we propose Personalized Budget Distribution (PBD) and Personalized Budget Absorption (PBA) to estimate streaming statistics under $\boldsymbol{w}$-Event $\boldsymbol{\mathcal{E}}$ Personalized Differential Privacy (($\boldsymbol{w}$, $\boldsymbol{\mathcal{E}}$)-EPDP). PBD guarantees that the budget reserved for the next time step is no smaller than the budget consumed in the previous release, while PBA improves the current budget by absorbing unused budgets from the previous $k$ time slots and borrowing from the next $k$ time slots. We further develop Dynamic Personalized Budget Distribution (DPBD) and Dynamic Personalized Budget Absorption (DPBA), which allow users to dynamically adjust privacy requirements while satisfying $(τ, \boldsymbol{w}_B, \boldsymbol{w}_F)$-Event $(\boldsymbol{\mathcal{E}}_B, \boldsymbol{\mathcal{E}}_F)$-Personalized Differential Privacy. We prove that all proposed methods achieve the corresponding personalized differential privacy guarantees and derive their error upper bounds. Experiments show that our methods reduce estimation error by at least $53.6\%$ compared with state-of-the-art algorithms.

Renjie Xu, Daowen Qiu, Ligang Xiao et al.

Solving the discrete logarithm problem (DLP) with quantum computers is a fundamental task with important implications. Beyond Shor's algorithm, many researchers have proposed alternative solutions in recent years. However, due to current hardware limitations, the scale of DLP instances that can be addressed by quantum computers remains insufficient. To overcome this limitation, we propose a distributed quantum discrete logarithm algorithm that reduces the required quantum register size for solving DLPs. Specifically, we design a distributed quantum algorithm to determine whether the solution is contained in a given set. Based on this procedure, our method solves DLPs by identifying the intersection of sets containing the solution. Compared with Shor's original algorithm, our approach reduces the register size and can improve the success probability, while requiring no quantum communication.

Wenji Du, Wanghong Yang, Baosen Zhao et al.

Real-time broadband communication (RTBC) scenarios, such as cloud virtual reality and 8K live streaming, further raise the criteria of the performance triangle, requiring video bitrates exceeding 30 Mbps, tail delay below 50 ms, and fairness guarantees for multi-user concurrent access. Based on our testing and analysis, existing RTBC-oriented rate control solutions, including end-to-end algorithms and network-assisted algorithms, fail to simultaneously satisfy all performance metrics. The native dynamic delay and physical-layer resource allocation strategy inherent to the 5G radio access network (RAN) are the key reasons. These solutions lack adaptation to the 5G architecture, leading to reduced decision performance. This paper proposes Choir, an innovative collaborative solution mainly deployed on 5G base stations that deeply integrates 5G radio characteristics and video streaming traffic patterns to guide efficient sender-side rate control. Extensive simulation and testbed evaluations demonstrate Choir's significant performance in achieving high average bitrate, low tail delay, and inter-flow fairness across different 5G network scenarios.

Xu Zhou, Xinyu Lei, Cong Yang et al.

Federated learning (FL) supports distributed training of a global machine learning model across multiple devices with the help of a central server. However, data heterogeneity across different devices leads to the client model drift issue and results in model performance degradation and poor model fairness. To address the issue, we design Federated learning with global-local Knowledge Fusion (FedKF) scheme in this paper. The key idea in FedKF is to let the server return the global knowledge to be fused with the local knowledge in each training round so that the local model can be regularized towards the global optima. Therefore, the client model drift issue can be mitigated. In FedKF, we first propose the active-inactive model aggregation technique that supports a precise global knowledge representation. Then, we propose a data-free knowledge distillation (KD) approach to enable each client model to learn the global knowledge (embedded in the global model) while each client model can still learn the local knowledge (embedded in the local dataset) simultaneously, thereby realizing the global-local knowledge fusion process. The theoretical analysis and intensive experiments demonstrate the superiority of FedKF over previous solutions.

Xin Liu, Jiamin Wu, and Wenfei Yang et al.

Pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques primarily focus on global text and image representations, yet overlooking multi-modal attribute characteristics. This limitation hinders the model's ability to perceive fine-grained visual details and restricts its generalization ability to a broader range of unseen classes. To address this issue, we propose a Multi-modal Attribute Prompting method (MAP) by jointly exploring textual attribute prompting, visual attribute prompting, and attribute-level alignment. The proposed MAP enjoys several merits. First, we introduce learnable visual attribute prompts enhanced by textual attribute semantics to adaptively capture visual attributes for images from unknown categories, boosting fine-grained visual perception capabilities for CLIP. Second, the proposed attribute-level alignment complements the global alignment to enhance the robustness of cross-modal alignment for open-vocabulary objects. To our knowledge, this is the first work to establish cross-modal attribute-level alignment for CLIP-based few-shot adaptation. Extensive experimental results on 11 datasets demonstrate that our method performs favorably against state-of-the-art approaches.

Jiahao Lu, Jiacheng Deng, Ruijie Zhu et al.

Dynamic scenes rendering is an intriguing yet challenging problem. Although current methods based on NeRF have achieved satisfactory performance, they still can not reach real-time levels. Recently, 3D Gaussian Splatting (3DGS) has garnered researchers attention due to their outstanding rendering quality and real-time speed. Therefore, a new paradigm has been proposed: defining a canonical 3D gaussians and deforming it to individual frames in deformable fields. However, since the coordinates of canonical 3D gaussians are filled with noise, which can transfer noise into the deformable fields, and there is currently no method that adequately considers the aggregation of 4D information. Therefore, we propose Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Rendering (DN-4DGS). Specifically, a Noise Suppression Strategy is introduced to change the distribution of the coordinates of the canonical 3D gaussians and suppress noise. Additionally, a Decoupled Temporal-Spatial Aggregation Module is designed to aggregate information from adjacent points and frames. Extensive experiments on various real-world datasets demonstrate that our method achieves state-of-the-art rendering quality under a real-time level.

Linqing Zhong, Chen Gao, Zihan Ding et al.

The Zero-Shot Object Navigation (ZSON) task requires embodied agents to find a previously unseen object by navigating in unfamiliar environments. Such a goal-oriented exploration heavily relies on the ability to perceive, understand, and reason based on the spatial information of the environment. However, current LLM-based approaches convert visual observations to language descriptions and reason in the linguistic space, leading to the loss of spatial information. In this paper, we introduce TopV-Nav, an MLLM-based method that directly reasons on the top-view map with sufficient spatial information. To fully unlock the MLLM's spatial reasoning potential in top-view perspective, we propose the Adaptive Visual Prompt Generation (AVPG) method to adaptively construct semantically-rich top-view map. It enables the agent to directly utilize spatial information contained in the top-view map to conduct thorough reasoning. Besides, we design a Dynamic Map Scaling (DMS) mechanism to dynamically zoom top-view map at preferred scales, enhancing local fine-grained reasoning. Additionally, we devise a Potential Target Driven (PTD) mechanism to predict and to utilize target locations, facilitating global and human-like exploration. Experiments on MP3D and HM3D datasets demonstrate the superiority of our TopV-Nav.

Peihong Lin, Pengfei Wang, Xu Zhou et al.

The state-of-the-art DGF techniques redefine and optimize the fitness metric to reach the target sites precisely and quickly. However, optimizations for fitness metrics are mainly based on heuristic algorithms, which usually rely on historical execution information and lack foresight on paths that have not been exercised yet. Thus, those hard-to-execute paths with complex constraints would hinder DGF from reaching the targets, making DGF less efficient. In this paper, we propose DeepGo, a predictive directed grey-box fuzzer that can combine historical and predicted information to steer DGF to reach the target site via an optimal path. We first propose the path transition model, which models DGF as a process of reaching the target site through specific path transition sequences. The new seed generated by mutation would cause the path transition, and the path corresponding to the high-reward path transition sequence indicates a high likelihood of reaching the target site through it. Then, to predict the path transitions and the corresponding rewards, we use deep neural networks to construct a Virtual Ensemble Environment (VEE), which gradually imitates the path transition model and predicts the rewards of path transitions that have not been taken yet. To determine the optimal path, we develop a Reinforcement Learning for Fuzzing (RLF) model to generate the transition sequences with the highest sequence rewards. The RLF model can combine historical and predicted path transitions to generate the optimal path transition sequences, along with the policy to guide the mutation strategy of fuzzing. Finally, to exercise the high-reward path transition sequence, we propose the concept of an action group, which comprehensively optimizes the critical steps of fuzzing to realize the optimal path to reach the target efficiently.

Si Liu, Zihan Ding, Jiahui Fu et al.

The objective of the collaborative vehicle-to-everything perception task is to enhance the individual vehicle's perception capability through message communication among neighboring traffic agents. Previous methods focus on achieving optimal performance within bandwidth limitations and typically adopt BEV maps as the basic collaborative message units. However, we demonstrate that collaboration with dense representations is plagued by object feature destruction during message packing, inefficient message aggregation for long-range collaboration, and implicit structure representation communication. To tackle these issues, we introduce a brand new message unit, namely point cluster, designed to represent the scene sparsely with a combination of low-level structure information and high-level semantic information. The point cluster inherently preserves object information while packing messages, with weak relevance to the collaboration range, and supports explicit structure modeling. Building upon this representation, we propose a novel framework V2X-PC for collaborative perception. This framework includes a Point Cluster Packing (PCP) module to keep object feature and manage bandwidth through the manipulation of cluster point numbers. As for effective message aggregation, we propose a Point Cluster Aggregation (PCA) module to match and merge point clusters associated with the same object. To further handle time latency and pose errors encountered in real-world scenarios, we propose parameter-free solutions that can adapt to different noisy levels without finetuning. Experiments on two widely recognized collaborative perception benchmarks showcase the superior performance of our method compared to the previous state-of-the-art approaches relying on BEV maps.

Yong Zhang, Rui Zhu, Shifeng Zhang et al.

Self-supervised contrastive learning heavily relies on the view variance brought by data augmentation, so that it can learn a view-invariant pre-trained representation. Beyond increasing the view variance for contrast, this work focuses on improving the diversity of training data, to improve the generalization and robustness of the pre-trained models. To this end, we propose a unified framework to conduct data augmentation in the feature space, known as feature augmentation. This strategy is domain-agnostic, which augments similar features to the original ones and thus improves the data diversity. We perform a systematic investigation of various feature augmentation architectures, the gradient-flow skill, and the relationship between feature augmentation and traditional data augmentation. Our study reveals some practical principles for feature augmentation in self-contrastive learning. By integrating feature augmentation on the instance discrimination or the instance similarity paradigm, we consistently improve the performance of pre-trained feature learning and gain better generalization over the downstream image classification and object detection task.

Ruipu Wu, Yige Zhang, Jinyu Chen et al.

Aerial Vision-and-Language Navigation (VLN) is an emerging task that enables Unmanned Aerial Vehicles (UAVs) to navigate outdoor environments using natural language instructions and visual cues. However, due to the extended trajectories and complex maneuverability of UAVs, achieving reliable UAV-VLN performance is challenging and often requires human intervention or overly detailed instructions. To harness the advantages of UAVs' high mobility, which could provide multi-grained perspectives, while maintaining a manageable motion space for learning, we introduce a novel task called Dual-Altitude UAV Collaborative VLN (DuAl-VLN). In this task, two UAVs operate at distinct altitudes: a high-altitude UAV responsible for broad environmental reasoning, and a low-altitude UAV tasked with precise navigation. To support the training and evaluation of the DuAl-VLN, we construct the HaL-13k, a dataset comprising 13,838 collaborative high-low UAV demonstration trajectories, each paired with target-oriented language instructions. This dataset includes both unseen maps and an unseen object validation set to systematically evaluate the model's generalization capabilities across novel environments and unfamiliar targets. To consolidate their complementary strengths, we propose a dual-UAV collaborative VLN framework, AeroDuo, where the high-altitude UAV integrates a multimodal large language model (Pilot-LLM) for target reasoning, while the low-altitude UAV employs a lightweight multi-stage policy for navigation and target grounding. The two UAVs work collaboratively and only exchange minimal coordinate information to ensure efficiency.

Yijie Zheng, Weijie Wu, Qingyun Li et al.

Language-Guided object recognition in remote sensing imagery is crucial for large-scale mapping and automated data annotation. However, existing open-vocabulary and visual grounding methods rely on explicit category cues, limiting their ability to handle complex or implicit queries that require advanced reasoning. To address this issue, we introduce a new suite of tasks, including Instruction-Oriented Object Counting, Detection, and Segmentation (InstructCDS), covering open-vocabulary, open-ended, and open-subclass scenarios. We further present EarthInstruct, the first InstructCDS benchmark for earth observation. It is constructed from two diverse remote sensing datasets with varying spatial resolutions and annotation rules across 20 categories, necessitating models to interpret dataset-specific instructions. Given the scarcity of semantically rich labeled data in remote sensing, we propose InstructSAM, a training-free framework for instruction-driven object recognition. InstructSAM leverages large vision-language models to interpret user instructions and estimate object counts, employs SAM2 for mask proposal, and formulates mask-label assignment as a binary integer programming problem. By integrating semantic similarity with counting constraints, InstructSAM efficiently assigns categories to predicted masks without relying on confidence thresholds. Experiments demonstrate that InstructSAM matches or surpasses specialized baselines across multiple tasks while maintaining near-constant inference time regardless of object count, reducing output tokens by 89% and overall runtime by over 32% compared to direct generation approaches. We believe the contributions of the proposed tasks, benchmark, and effective approach will advance future research in developing versatile object recognition systems.

Haolong Yan, Jia Wang, Xin Huang et al.

Recent advances in multimodal large language models unlock unprecedented opportunities for GUI automation. However, a fundamental challenge remains: how to efficiently acquire high-quality training data while maintaining annotation reliability? We introduce a self-evolving training pipeline powered by the Calibrated Step Reward System, which converts model-generated trajectories into reliable training signals through trajectory-level calibration, achieving >90% annotation accuracy with 10-100x lower cost. Leveraging this pipeline, we introduce Step-GUI, a family of models (4B/8B) that achieves state-of-the-art GUI performance (8B: 80.2% AndroidWorld, 48.5% OSWorld, 62.6% ScreenShot-Pro) while maintaining robust general capabilities. As GUI agent capabilities improve, practical deployment demands standardized interfaces across heterogeneous devices while protecting user privacy. To this end, we propose GUI-MCP, the first Model Context Protocol for GUI automation with hierarchical architecture that combines low-level atomic operations and high-level task delegation to local specialist models, enabling high-privacy execution where sensitive data stays on-device. Finally, to assess whether agents can handle authentic everyday usage, we introduce AndroidDaily, a benchmark grounded in real-world mobile usage patterns with 3146 static actions and 235 end-to-end tasks across high-frequency daily scenarios (8B: static 89.91%, end-to-end 52.50%). Our work advances the development of practical GUI agents and demonstrates strong potential for real-world deployment in everyday digital interactions.

Xu Zhou, Ivor Prado, AIFPDS participants et al.

Artificial intelligence is accelerating a new era of food innovation, connecting data from farm to consumer to improve formulation, processing, and health outcomes. Recent advances in deep learning, natural language processing, and multi-omics integration make it possible to understand and optimize food systems with unprecedented depth. However, AI adoption across the food sector remains uneven due to heterogeneous datasets, limited model and system interoperability, and a persistent skills gap between data scientists and food domain experts. To address these challenges and advance responsible innovation, the AI Institute for Next Generation Food Systems (AIFS) convened the inaugural AI for Food Product Development Symposium at University of California, Davis, in October 2025. This white paper synthesizes insights from the symposium, organized around five domains where AI can have the greatest near-term impact: supply chain; formulation and processing; consumer insights and sensory prediction; nutrition and health; and education and workforce development. Across the areas, participants emphasized the importance of interoperable data standards, transparent and interpretable models, and cross-sector collaboration to accelerate the translation of AI research into practice. The discussions further highlighted the need for robust digital infrastructure, privacy-preserving data-sharing mechanisms, and interdisciplinary training pathways that integrate AI literacy with domain expertise. Collectively, the priorities outline a roadmap for integrating AI into food manufacturing in ways that enhance innovation, sustainability, and human well-being while ensuring that technological progress remains grounded in ethics, scientific rigor, and societal benefit.

Weiqi Yang, Xu Zhou, Jingfu Guan et al.

Multi-modal fusion is crucial for Internet of Things (IoT) perception, widely deployed in smart homes, intelligent transport, industrial automation, and healthcare. However, existing systems often face challenges: high model complexity hinders deployment in resource-constrained environments, unidirectional modal alignment neglects inter-modal relationships, and robustness suffers when sensor data is missing. These issues impede efficient and robust multimodal perception in real-world IoT settings. To overcome these limitations, we propose GRAM-MAMBA. This framework utilizes the linear-complexity Mamba model for efficient sensor time-series processing, combined with an optimized GRAM matrix strategy for pairwise alignment among modalities, addressing the shortcomings of traditional single-modality alignment. Inspired by Low-Rank Adaptation (LoRA), we introduce an adaptive low-rank layer compensation strategy to handle missing modalities post-training. This strategy freezes the pre-trained model core and irrelevant adaptive layers, fine-tuning only those related to available modalities and the fusion process. Extensive experiments validate GRAM-MAMBA's effectiveness. On the SPAWC2021 indoor positioning dataset, the pre-trained model shows lower error than baselines; adapting to missing modalities yields a 24.5% performance boost by training less than 0.2% of parameters. On the USC-HAD human activity recognition dataset, it achieves 93.55% F1 and 93.81% Overall Accuracy (OA), outperforming prior work; the update strategy increases F1 by 23% while training less than 0.3% of parameters. These results highlight GRAM-MAMBA's potential for achieving efficient and robust multimodal perception in resource-constrained environments.

Xing Wang, Juan Zhao, Lin Zhu et al.

Mobile network traffic forecasting is one of the key functions in daily network operation. A commercial mobile network is large, heterogeneous, complex and dynamic. These intrinsic features make mobile network traffic forecasting far from being solved even with recent advanced algorithms such as graph convolutional network-based prediction approaches and various attention mechanisms, which have been proved successful in vehicle traffic forecasting. In this paper, we cast the problem as a spatial-temporal sequence prediction task. We propose a novel deep learning network architecture, Adaptive Multi-receptive Field Spatial-Temporal Graph Convolutional Networks (AMF-STGCN), to model the traffic dynamics of mobile base stations. AMF-STGCN extends GCN by (1) jointly modeling the complex spatial-temporal dependencies in mobile networks, (2) applying attention mechanisms to capture various Receptive Fields of heterogeneous base stations, and (3) introducing an extra decoder based on a fully connected deep network to conquer the error propagation challenge with multi-step forecasting. Experiments on four real-world datasets from two different domains consistently show AMF-STGCN outperforms the state-of-the-art methods.

Xugang Wu, Huijun Wu, Xu Zhou et al.

Graph neural networks exhibit remarkable performance in graph data analysis. However, the robustness of GNN models remains a challenge. As a result, they are not reliable enough to be deployed in critical applications. Recent studies demonstrate that GNNs could be easily fooled with adversarial perturbations, especially structural perturbations. Such vulnerability is attributed to the excessive dependence on the structure information to make predictions. To achieve better robustness, it is desirable to build the prediction of GNNs with more comprehensive features. Graph data, in most cases, has two views of information, namely structure information and feature information. In this paper, we propose CoG, a simple yet effective co-training framework to combine these two views for the purpose of robustness. CoG trains sub-models from the feature view and the structure view independently and allows them to distill knowledge from each other by adding their most confident unlabeled data into the training set. The orthogonality of these two views diversifies the sub-models, thus enhancing the robustness of their ensemble. We evaluate our framework on three popular datasets, and results show that CoG significantly improves the robustness of graph models against adversarial attacks without sacrificing their performance on clean data. We also show that CoG still achieves good robustness when both node features and graph structures are perturbed.

Xindi Hu, Limin Wang, Xin Yang et al.

The ultrasound (US) screening of the infant hip is vital for the early diagnosis of developmental dysplasia of the hip (DDH). The US diagnosis of DDH refers to measuring alpha and beta angles that quantify hip joint development. These two angles are calculated from key anatomical landmarks and structures of the hip. However, this measurement process is not trivial for sonographers and usually requires a thorough understanding of complex anatomical structures. In this study, we propose a multi-task framework to learn the relationships among landmarks and structures jointly and automatically evaluate DDH. Our multi-task networks are equipped with three novel modules. Firstly, we adopt Mask R-CNN as the basic framework to detect and segment key anatomical structures and add one landmark detection branch to form a new multi-task framework. Secondly, we propose a novel shape similarity loss to refine the incomplete anatomical structure prediction robustly and accurately. Thirdly, we further incorporate the landmark-structure consistent prior to ensure the consistency of the bony rim estimated from the segmented structure and the detected landmark. In our experiments, 1,231 US images of the infant hip from 632 patients are collected, of which 247 images from 126 patients are tested. The average errors in alpha and beta angles are 2.221 degrees and 2.899 degrees. About 93% and 85% estimates of alpha and beta angles have errors less than 5 degrees, respectively. Experimental results demonstrate that the proposed method can accurately and robustly realize the automatic evaluation of DDH, showing great potential for clinical application.

Xu Zhou, Pengfei Wang, Chenyifan Liu et al.

Recent research has sought to improve fuzzing performance via parallel computing. However, researchers focus on improving efficiency while ignoring the increasing cost of testing resources. Parallel fuzzing in the distributed environment amplifies the resource-wasting problem caused by the random nature of fuzzing. In the parallel mode, owing to the lack of an appropriate task dispatching scheme and timely fuzzing status synchronization among different fuzzing instances, task conflicts and workload imbalance occur, making the resource-wasting problem severe. In this paper, we design UltraFuzz, a fuzzer for resource-saving in distributed fuzzing. Based on centralized dynamic scheduling, UltraFuzz can dispatch tasks and schedule power globally and reasonably to avoid resource-wasting. Besides, UltraFuzz can elastically allocate computing power for fuzzing and seed evaluation, thereby avoiding the potential bottleneck of seed evaluation that blocks the fuzzing process. UltraFuzz was evaluated using real-world programs, and the results show that with the same testing resource, UltraFuzz outperforms state-of-the-art tools, such as AFL, AFL-P, PAFL, and EnFuzz. Most importantly, the experiment reveals certain results that seem counter-intuitive, namely that parallel fuzzing can achieve ``super-linear acceleration'' when compared with single-core fuzzing. We conduct additional experiments to reveal the deep reasons behind this phenomenon and dig deep into the inherent advantages of parallel fuzzing over serial fuzzing, including the global optimization of seed energy scheduling and the escape of local optimal seed. Additionally, 24 real-world vulnerabilities were discovered using UltraFuzz.

Zhan Shi, Xu Zhou, Xipeng Qiu et al.

Image captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community. In this paper, we present a novel image captioning architecture to better explore semantics available in captions and leverage that to enhance both image representation and caption generation. Our models first construct caption-guided visual relationship graphs that introduce beneficial inductive bias using weakly supervised multi-instance learning. The representation is then enhanced with neighbouring and contextual nodes with their textual and visual features. During generation, the model further incorporates visual relationships using multi-task learning for jointly predicting word and object/predicate tag sequences. We perform extensive experiments on the MSCOCO dataset, showing that the proposed framework significantly outperforms the baselines, resulting in the state-of-the-art performance under a wide range of evaluation metrics.

Pengfei Wang, Xu Zhou, Tai Yue et al.

Greybox fuzzing is a scalable and practical approach for software testing. Most greybox fuzzing tools are coverage-guided as reaching high code coverage is more likely to find bugs. However, since most covered codes may not contain bugs, blindly extending code coverage is less efficient, especially for corner cases. Unlike coverage-guided greybox fuzzing which increases code coverage in an undirected manner, directed greybox fuzzing (DGF) spends most of its time allocation on reaching specific targets (e.g., the bug-prone zone) without wasting resources stressing unrelated parts. Thus, DGF is particularly suitable for scenarios such as patch testing,bug reproduction, and special bug detection. For now, DGF has become an active research area. However, DGF has general limitations and challenges that are worth further studying. Based on the investigation of 42 state-of-the-art fuzzers that are closely related to DGF, we conduct the first in-depth study to summarize the empirical evidence on the research progress of DGF. This paper studies DGF from a broader view, which takes into account not only the location-directed type that targets specific code parts, but also the behavior-directed type that aims to expose abnormal program behaviors. By analyzing the benefits and limitations of DGF research, we try to identify gaps in current research, meanwhile, reveal new research opportunities, and suggest areas for further investigation.

Lingfeng Tao, Michael Bowman, Xu Zhou et al.

Enabling robots to provide effective assistance yet still accommodating the operator's commands for telemanipulation of an object is very challenging because robot's assistive action is not always intuitive for human operators and human behaviors and preferences are sometimes ambiguous for the robot to interpret. Although various assistance approaches are being developed to improve the control quality from different optimization perspectives, the problem still remains in determining the appropriate approach that satisfies the fine motion constraints for the telemanipulation task and preference of the operator. To address these problems, we developed a novel preference-aware assistance knowledge learning approach. An assistance preference model learns what assistance is preferred by a human, and a stagewise model updating method ensures the learning stability while dealing with the ambiguity of human preference data. Such a preference-aware assistance knowledge enables a teleoperated robot hand to provide more active yet preferred assistance toward manipulation success. We also developed knowledge transfer methods to transfer the preference knowledge across different robot hand structures to avoid extensive robot-specific training. Experiments to telemanipulate a 3-finger hand and 2-finger hand, respectively, to use, move, and hand over a cup have been conducted. Results demonstrated that the methods enabled the robots to effectively learn the preference knowledge and allowed knowledge transfer between robots with less training effort.

Xugang Wu, Xiaoping Wang, Xu Zhou et al.

Recently, the majority of visual trackers adopt Convolutional Neural Network (CNN) as their backbone to achieve high tracking accuracy. However, less attention has been paid to the potential adversarial threats brought by CNN, including Siamese network. In this paper, we first analyze the existing vulnerabilities in Siamese trackers and propose the requirements for a successful adversarial attack. On this basis, we formulate the adversarial generation problem and propose an end-to-end pipeline to generate a perturbed texture map for the 3D object that causes the trackers to fail. Finally, we conduct thorough experiments to verify the effectiveness of our algorithm. Experiment results show that adversarial examples generated by our algorithm can successfully lower the tracking accuracy of victim trackers and even make them drift off. To the best of our knowledge, this is the first work to generate 3D adversarial examples on visual trackers.

Jianguo Chen, Kenli Li, Kashif Bilal et al.

Benefitting from large-scale training datasets and the complex training network, Convolutional Neural Networks (CNNs) are widely applied in various fields with high accuracy. However, the training process of CNNs is very time-consuming, where large amounts of training samples and iterative operations are required to obtain high-quality weight parameters. In this paper, we focus on the time-consuming training process of large-scale CNNs and propose a Bi-layered Parallel Training (BPT-CNN) architecture in distributed computing environments. BPT-CNN consists of two main components: (a) an outer-layer parallel training for multiple CNN subnetworks on separate data subsets, and (b) an inner-layer parallel training for each subnetwork. In the outer-layer parallelism, we address critical issues of distributed and parallel computing, including data communication, synchronization, and workload balance. A heterogeneous-aware Incremental Data Partitioning and Allocation (IDPA) strategy is proposed, where large-scale training datasets are partitioned and allocated to the computing nodes in batches according to their computing power. To minimize the synchronization waiting during the global weight update process, an Asynchronous Global Weight Update (AGWU) strategy is proposed. In the inner-layer parallelism, we further accelerate the training process for each CNN subnetwork on each computer, where computation steps of convolutional layer and the local weight training are parallelized based on task-parallelism. We introduce task decomposition and scheduling strategies with the objectives of thread-level load balancing and minimum waiting time for critical paths. Extensive experimental results indicate that the proposed BPT-CNN effectively improves the training performance of CNNs while maintaining the accuracy.

Xu Zhou, Xiaoli Zhang, Jiucai Zhang et al.

Stabilization and trajectory control of a quadrotor carrying a suspended load with a fixed known mass has been extensively studied in recent years. However, the load mass is not always known beforehand or may vary during the practical transportations. This mass uncertainty brings uncertain disturbances to the quadrotor system, causing existing controllers to have worse stability and trajectory tracking performance. To improve the quadrotor stability and trajectory tracking capability in this situation, we fully investigate the impacts of the uncertain load mass on the quadrotor. By comparing the performances of three different controllers -- the proportional-derivative (PD) controller, the sliding mode controller (SMC), and the model predictive controller (MPC) -- stabilization rather than trajectory tracking error is proved to be the main influence in the load mass uncertainty. A critical motion mass exists for the quadrotor to maintain a desired transportation performance. Moreover, simulation results verify that a controller with strong robustness against disturbances is a good choice for practical applications.