Hua Wu

While vision-language models (VLMs) have been widely applied in zero-shot anomaly detection (ZSAD), their performance remains limited by the inability to distinguish fine-grained normal and abnormal textures, coupled with inadequate capabilities in detecting complex morphological anomalies. To address these limitations, this paper proposes BAG-CLIP (Bifurcated Attention Graph-Enhanced CLIP), a dual-path graph-enhanced zero-shot anomaly detection method. This approach employs a Bifurcated Self-Attention (BSA) module to decouple visual features, processing global semantics and spatial details separately to mitigate the inherent conflict between abstract semantic representation and precise spatial localization. A Self-Attention Graph (SAG) module is designed to model the topological structure of complex morphological anomalies. This module dynamically constructs visual features’ topological relationships and utilizes graph convolutions to aggregate neighborhood information, thereby enhancing the model’s representational capacity for diverse and complex morphological anomalies. Extensive experiments are conducted on five diverse industrial datasets, featuring complex transmission line backgrounds alongside general industrial scenarios. The proposed method is comprehensively evaluated against 11 state-of-the-art (SOTA) methods. On the EPED (Electrical Power Equipment Dataset) and MPDD datasets, BAG-CLIP outperforms the second-best methods in image-level AUROC (Area Under the Receiver Operating Characteristic Curve) by 3.7% and 2.8%, respectively. BAG-CLIP achieves superior performance in both zero-shot anomaly detection and segmentation.

We present Eureka-Audio, a compact yet high-performance audio language model that achieves competitive performance against models that are 4 to 18 times larger across a broad range of audio understanding benchmarks. Despite containing only 1.7B parameters, Eureka-Audio demonstrates strong performance on automatic speech recognition (ASR), audio understanding, and dense audio captioning, matching or surpassing multiple 7B to 30B audio and omni-modal baselines. The model adopts a unified end-to-end architecture composed of a lightweight language backbone, a Whisper-based audio encoder, and a sparsely activated Mixture-of-Experts (MoE) adapter that explicitly accounts for audio heterogeneity and alleviates cross-modal optimization conflicts under limited capacity. To further enhance paralinguistic reasoning, we introduce DataFlux, a closed loop audio instruction data synthesis and verification pipeline that constructs high quality, logically consistent supervision from raw audio. Extensive evaluations across ASR, knowledge reasoning, safety, instruction following, and paralinguistic benchmarks, demonstrate that Eureka-Audio achieves an efficient balance between computational cost and performance. These results establish Eureka Audio as a strong and practical baseline for lightweight audio understanding models.

Graphical User Interface (GUI) agents show great potential for enabling foundation models to complete real-world tasks, revolutionizing human-computer interaction and improving human productivity. In this report, we present OmegaUse, a general-purpose GUI agent model for autonomous task execution on both mobile and desktop platforms, supporting computer-use and phone-use scenarios. Building an effective GUI agent model relies on two factors: (1) high-quality data and (2) effective training methods. To address these, we introduce a carefully engineered data-construction pipeline and a decoupled training paradigm. For data construction, we leverage rigorously curated open-source datasets and introduce a novel automated synthesis framework that integrates bottom-up autonomous exploration with top-down taxonomy-guided generation to create high-fidelity synthetic data. For training, to better leverage these data, we adopt a two-stage strategy: Supervised Fine-Tuning (SFT) to establish fundamental interaction syntax, followed by Group Relative Policy Optimization (GRPO) to improve spatial grounding and sequential planning. To balance computational efficiency with agentic reasoning capacity, OmegaUse is built on a Mixture-of-Experts (MoE) backbone. To evaluate cross-terminal capabilities in an offline setting, we introduce OS-Nav, a benchmark suite spanning multiple operating systems: ChiM-Nav, targeting Chinese Android mobile environments, and Ubu-Nav, focusing on routine desktop interactions on Ubuntu. Extensive experiments show that OmegaUse is highly competitive across established GUI benchmarks, achieving a state-of-the-art (SOTA) score of 96.3% on ScreenSpot-V2 and a leading 79.1% step success rate on AndroidControl. OmegaUse also performs strongly on OS-Nav, reaching 74.24% step success on ChiM-Nav and 55.9% average success on Ubu-Nav.

Large Audio Language Models (LALMs) have garnered significant research interest. Despite being built upon text-based large language models (LLMs), LALMs frequently exhibit a degradation in knowledge and reasoning capabilities. We hypothesize that this limitation stems from the failure of current training paradigms to effectively bridge the acoustic-semantic gap within the feature representation space. To address this challenge, we propose CORD, a unified alignment framework that performs online cross-modal self-distillation. Specifically, it aligns audio-conditioned reasoning with its text-conditioned counterpart within a unified model. Leveraging the text modality as an internal teacher, CORD performs multi-granularity alignment throughout the audio rollout process. At the token level, it employs on-policy reverse KL divergence with importance-aware weighting to prioritize early and semantically critical tokens. At the sequence level, CORD introduces a judge-based global reward to optimize complete reasoning trajectories via Group Relative Policy Optimization (GRPO). Empirical results across multiple benchmarks demonstrate that CORD consistently enhances audio-conditioned reasoning and substantially bridges the audio-text performance gap with only 80k synthetic training samples, validating the efficacy and data efficiency of our on-policy, multi-level cross-modal alignment approach.

Extending the input modality of Large Language Models~(LLMs) to the audio domain is essential for achieving comprehensive multimodal perception. However, it is well-known that acoustic information is intrinsically \textit{heterogeneous}, entangling attributes such as speech, music, and environmental context. Existing research is limited to a dense, parameter-shared adapter to model these diverse patterns, which induces \textit{gradient conflict} during optimization, as parameter updates required for distinct attributes contradict each other. To address this limitation, we introduce the \textit{\textbf{MoE-Adapter}}, a sparse Mixture-of-Experts~(MoE) architecture designed to decouple acoustic information. Specifically, it employs a dynamic gating mechanism that routes audio tokens to specialized experts capturing complementary feature subspaces while retaining shared experts for global context, thereby mitigating gradient conflicts and enabling fine-grained feature learning. Comprehensive experiments show that the MoE-Adapter achieves superior performance on both audio semantic and paralinguistic tasks, consistently outperforming dense linear baselines with comparable computational costs. Furthermore, we will release the related code and models to facilitate future research.

The foreign object debris (FOD) on airport runways poses a serious threat to the safe operation of airports. However, accurately identifying FOD during runway inspections is challenging due to its small pixel size and irregular shape in detection images. To address this issue, we propose a FOD detection network that incorporates deformable kernel selection and multi-channel hybrid attention fusion. A deformable large kernel selection module that automatically selects suitable receptive fields is introduced to enhance the learning capability for complex shape features of FODs. Additionally, a multi-channel hybrid attention fusion feature pyramid network and a Beast-Fusion module are designed to improve the efficiency of feature transmission and detection performance across FODs of varying scales. Experimental results indicate that the proposed method achieves an average precision of 90.9% on the FOD dataset, significantly outperforming existing object detection algorithms.

Test-time scaling has emerged as a promising paradigm in language modeling, wherein additional computational resources are allocated during inference to enhance model performance. Recent approaches, such as DeepConf, have demonstrated the efficacy of this strategy, however, they often incur substantial computational overhead to achieve competitive results. In this work, we propose MatryoshkaThinking, a novel method that significantly reduces computational cost while maintaining state-of-the-art performance. Specifically, MatryoshkaThinking attains a score of 99.79 on AIME2025 using only 4% of the computation required by DeepConf. The core of our approach lies in the recursive exploitation of the model's intrinsic capabilities in reasoning, verification, and summarization, which collectively enhance the retention of correct solutions and reduce the disparity between Pass@k and Pass@1. Comprehensive evaluations across multiple open-source models and challenging multi-modal reasoning benchmarks validate the effectiveness and generality of our method. These findings offer new insights into the design of efficient and scalable test-time inference strategies for advanced language models.

Viewpoint planning is crucial to ensure both inspection efficiency and observation precision in UAV inspection tasks. To address the issues of excessive waypoints and inadequate observation precision in traditional methods, this paper proposes a hierarchical reinforcement learning-based viewpoint planning method. The proposed method decomposes the viewpoint planning task into a high-level waypoint planning strategy and a low-level pose and zoom planning strategy. Additionally, a reward function is designed to enhance inspection precision, enabling collaborative optimization of waypoint positions, viewpoint poses, and focal lengths. Experimental results show that, compared with the classic coverage path planning method and non-hierarchical reinforcement learning approaches, the proposed method reduces the number of waypoints by at least 70% across multiple inspection objects. Furthermore, experiments with viewpoint planning at different precision levels demonstrate that the proposed method achieves scalable precision during inspection, with the observation resolution improving to 1.51 pixels/mm. Finally, a qualitative comparison is made between the proposed method in this paper and other representative methods in viewpoint planning. These results effectively demonstrate the validity and superiority of the proposed method in improving both inspection task efficiency and observation precision.