Zhongyu Yang

Zhongyu Yang, Chen Shen, Wei Shao et al.

Lane detection is challenging due to the complicated on road scenarios and line deformation from different camera perspectives. Lots of solutions were proposed, but can not deal with corner lanes well. To address this problem, this paper proposes a new top-down deep learning lane detection approach, CANET. A lane instance is first responded by the heat-map on the U-shaped curved guide line at global semantic level, thus the corresponding features of each lane are aggregated at the response point. Then CANET obtains the heat-map response of the entire lane through conditional convolution, and finally decodes the point set to describe lanes via adaptive decoder. The experimental results show that CANET reaches SOTA in different metrics. Our code will be released soon.

Zuhao Yang, Kaichen Zhang, Sudong Wang et al.

Training large multimodal models (LMMs) via reinforcement learning (RL) to natively invoke video-processing tools (e.g., cropping) has become a promising route to long-video understanding. However, existing native-RL methods dispatch tool calls sequentially (i.e., one per turn): a single wrong crop propagates errors without peer correction, multi-turn tool calls corrupt context, and inference cost scales linearly with the number of turns. We introduce ParaVT, the first multi-agent end-to-end RL-trained framework for Parallel Video Tool calling, dispatching multiple time-window crops in a single turn for cleaner context and better fault tolerance. Yet applying standard RL to ParaVT reveals an obstacle we term the Tool Prior Paradox: the pretrained tool priors that enable tool exploration also destabilize cold-started structural format and expose the skip-tool reward shortcut under temperature sampling. A cross-model contrast on a weaker-prior LMM supports this claim: format stays stable but RL elicits zero tool calls, indicating that prior strength is the shared driver of both format collapse and tool exploration. We propose PARA-GRPO (Parseability-Anchored and Ratio-gAted GRPO), which augments standard RL with two complementary mechanisms: (i) a targeted format reward applied only at the structural-token positions most prone to collapse, and (ii) a per-prompt frame-budget randomization that creates training prompts where calling the tool yields a measurable reward signal over skipping it. Across six long-video understanding benchmarks, ParaVT improves over the Qwen3-VL baseline by +7.9% on average, with PARA-GRPO lifting training-time format compliance from 0.13 to 0.64. As tool capabilities become increasingly internalized in modern LMMs, RL must cooperate with the resulting priors, and ParaVT offers a general recipe for agentic RL. Code, data, and model weights are publicly available.

Xinan Zhang, Haolin Wang, Zhongyu Yang et al.

Raveling, the loss of aggregates, is a major form of asphalt pavement surface distress, especially on highways. While research has shown that machine learning and deep learning-based methods yield promising results for raveling detection by classification on range images, their performance often degrades in large-scale deployments where more diverse inference data may originate from different runs, sensors, and environmental conditions. This degradation highlights the need of a more generalizable and robust solution for real-world implementation. Thus, the objectives of this study are to 1) identify and assess potential variations that impact model robustness, such as the quantity of training data, illumination difference, and spatial shift; and 2) leverage findings to enhance model robustness under real-world conditions. To this end, we propose RavelingArena, a benchmark designed to evaluate model robustness to variations in raveling detection. Instead of collecting extensive new data, it is built by augmenting an existing dataset with diverse, controlled variations, thereby enabling variation-controlled experiments to quantify the impact of each variation. Results demonstrate that both the quantity and diversity of training data are critical to the accuracy of models, achieving at least a 9.2% gain in accuracy under the most diverse conditions in experiments. Additionally, a case study applying these findings to a multi-year test section in Georgia, U.S., shows significant improvements in year-to-year consistency, laying foundations for future studies on temporal deterioration modeling. These insights provide guidance for more reliable model deployment in raveling detection and other real-world tasks that require adaptability to diverse conditions.

Zhongyu Yang, Zuhao Yang, Shuo Zhan et al.

Video question answering (VideoQA) is a challenging task that requires integrating spatial, temporal, and semantic information to capture the complex dynamics of video sequences. Although recent advances have introduced various approaches for video understanding, most existing methods still rely on locating relevant frames to answer questions rather than reasoning through the evolving storyline as humans do. Humans naturally interpret videos through coherent storylines, an ability that is crucial for making robust and contextually grounded predictions. To address this gap, we propose SVAgent, a storyline-guided cross-modal multi-agent framework for VideoQA. The storyline agent progressively constructs a narrative representation based on frames suggested by a refinement suggestion agent that analyzes historical failures. In addition, cross-modal decision agents independently predict answers from visual and textual modalities under the guidance of the evolving storyline. Their outputs are then evaluated by a meta-agent to align cross-modal predictions and enhance reasoning robustness and answer consistency. Experimental results demonstrate that SVAgent achieves superior performance and interpretability by emulating human-like storyline reasoning in video understanding.

Zhongyu Yang, Dannong Xu, Wei Pang et al.

The rapid growth of visual tokens in multimodal large language models (MLLMs) leads to excessive memory consumption and inference latency, especially when handling high-resolution images and videos. Token pruning is a technique used to mitigate this issue by removing redundancy, but existing methods often ignore relevance to the user query or suffer from the limitations of attention mechanisms, reducing their adaptability and effectiveness. To address these challenges, we propose Script, a plug-and-play pruning method that requires no retraining and generalizes across diverse MLLMs. Script comprises two modules: a graph-structured pruning module that removes visually redundant tokens, and a query-conditioned semantic pruning module that preserves query-relevant visual information. Together, they enhance performance on multimodal tasks. Experiments on fourteen benchmarks across image and video understanding tasks show that Script consistently achieves higher model efficiency and predictive accuracy compared to existing pruning methods. On LLaVA-NeXT-7B, it achieves up to 6.8x prefill speedup and 10x FLOP reduction, while retaining 96.88% of the original performance.

Zhongyu Yang, Yingfang Yuan, Xuanming Jiang et al.

Hallucination remains a critical challenge in large language models (LLMs), hindering the development of reliable multimodal LLMs (MLLMs). Existing solutions often rely on human intervention or underutilize the agent's ability to autonomously mitigate hallucination. To address these limitations, we draw inspiration from how humans make reliable decisions in the real world. They begin with introspective reasoning to reduce uncertainty and form an initial judgment, then rely on external verification from diverse perspectives to reach a final decision. Motivated by this cognitive paradigm, we propose InEx, a training-free, multi-agent framework designed to autonomously mitigate hallucination. InEx introduces internal introspective reasoning, guided by entropy-based uncertainty estimation, to improve the reliability of the decision agent's reasoning process. The agent first generates a response, which is then iteratively verified and refined through external cross-modal multi-agent collaboration with the editing agent and self-reflection agents, further enhancing reliability and mitigating hallucination. Extensive experiments show that InEx consistently outperforms existing methods, achieving 4%-27% gains on general and hallucination benchmarks, and demonstrating strong robustness.

Zhongyu Yang, Jun Chen, Dannong Xu et al.

Knowledge discovery and collection are intelligence-intensive tasks that traditionally require significant human effort to ensure high-quality outputs. Recent research has explored multi-agent frameworks for automating Wikipedia-style article generation by retrieving and synthesizing information from the internet. However, these methods primarily focus on text-only generation, overlooking the importance of multimodal content in enhancing informativeness and engagement. In this work, we introduce WikiAutoGen, a novel system for automated multimodal Wikipedia-style article generation. Unlike prior approaches, WikiAutoGen retrieves and integrates relevant images alongside text, enriching both the depth and visual appeal of generated content. To further improve factual accuracy and comprehensiveness, we propose a multi-perspective self-reflection mechanism, which critically assesses retrieved content from diverse viewpoints to enhance reliability, breadth, and coherence, etc. Additionally, we introduce WikiSeek, a benchmark comprising Wikipedia articles with topics paired with both textual and image-based representations, designed to evaluate multimodal knowledge generation on more challenging topics. Experimental results show that WikiAutoGen outperforms previous methods by 8%-29% on our WikiSeek benchmark, producing more accurate, coherent, and visually enriched Wikipedia-style articles. Our code and examples are available at https://wikiautogen.github.io/

Xinan Zhang, Haolin Wang, Yung-An Hsieh et al.

Crack detection plays a crucial role in civil infrastructures, including inspection of pavements, buildings, etc., and deep learning has significantly advanced this field in recent years. While numerous technical and review papers exist in this domain, emerging trends are reshaping the landscape. These shifts include transitions in learning paradigms (from fully supervised learning to semi-supervised, weakly-supervised, unsupervised, few-shot, domain adaptation and fine-tuning foundation models), improvements in generalizability (from single-dataset performance to cross-dataset evaluation), and diversification in dataset acquisition (from RGB images to specialized sensor-based data). In this review, we systematically analyze these trends and highlight representative works. Additionally, we introduce a new annotated dataset collected with 3D laser scans, 3DCrack, to support future research and conduct extensive benchmarking experiments to establish baselines for commonly used deep learning methodologies, including recent foundation models. Our findings provide insights into the evolving methodologies and future directions in deep learning-based crack detection. Project page: https://github.com/nantonzhang/Awesome-Crack-Detection

Keming Wu, Zuhao Yang, Kaichen Zhang et al.

Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consistency, and causal understanding. We argue that the field should move beyond appearance synthesis toward intelligent visual generation: plausible visuals grounded in structure, dynamics, domain knowledge, and causal relations. To frame this shift, we introduce a five-level taxonomy: Atomic Generation, Conditional Generation, In-Context Generation, Agentic Generation, and World-Modeling Generation, progressing from passive renderers to interactive, agentic, world-aware generators. We analyze key technical drivers, including flow matching, unified understanding-and-generation models, improved visual representations, post-training, reward modeling, data curation, synthetic data distillation, and sampling acceleration. We further show that current evaluations often overestimate progress by emphasizing perceptual quality while missing structural, temporal, and causal failures. By combining benchmark review, in-the-wild stress tests, and expert-constrained case studies, this roadmap offers a capability-centered lens for understanding, evaluating, and advancing the next generation of intelligent visual generation systems.

Zhongyu Yang, Chen Shen, Wei Shao et al.

Despite recent advances in lane detection methods, scenarios with limited- or no-visual-clue of lanes due to factors such as lighting conditions and occlusion remain challenging and crucial for automated driving. Moreover, current lane representations require complex post-processing and struggle with specific instances. Inspired by the DETR architecture, we propose LDTR, a transformer-based model to address these issues. Lanes are modeled with a novel anchor-chain, regarding a lane as a whole from the beginning, which enables LDTR to handle special lanes inherently. To enhance lane instance perception, LDTR incorporates a novel multi-referenced deformable attention module to distribute attention around the object. Additionally, LDTR incorporates two line IoU algorithms to improve convergence efficiency and employs a Gaussian heatmap auxiliary branch to enhance model representation capability during training. To evaluate lane detection models, we rely on Frechet distance, parameterized F1-score, and additional synthetic metrics. Experimental results demonstrate that LDTR achieves state-of-the-art performance on well-known datasets.

Yifan Zhou, Wanli Peng, Zhongyu Yang et al.

The perception of transparent objects for grasp and manipulation remains a major challenge, because existing robotic grasp methods which heavily rely on depth maps are not suitable for transparent objects due to their unique visual properties. These properties lead to gaps and inaccuracies in the depth maps of the transparent objects captured by depth sensors. To address this issue, we propose an end-to-end network for transparent object depth completion that combines the strengths of single-view RGB-D based depth completion and multi-view depth estimation. Moreover, we introduce a depth refinement module based on confidence estimation to fuse predicted depth maps from single-view and multi-view modules, which further refines the restored depth map. The extensive experiments on the ClearPose and TransCG datasets demonstrate that our method achieves superior accuracy and robustness in complex scenarios with significant occlusion compared to the state-of-the-art methods.

Zhongyu Yang, Mai Liu, Jinluo Xie et al.

Autonomous driving without high-definition (HD) maps demands a higher level of active scene understanding. In this competition, the organizers provided the multi-perspective camera images and standard-definition (SD) maps to explore the boundaries of scene reasoning capabilities. We found that most existing algorithms construct Bird's Eye View (BEV) features from these multi-perspective images and use multi-task heads to delineate road centerlines, boundary lines, pedestrian crossings, and other areas. However, these algorithms perform poorly at the far end of roads and struggle when the primary subject in the image is occluded. Therefore, in this competition, we not only used multi-perspective images as input but also incorporated SD maps to address this issue. We employed map encoder pre-training to enhance the network's geometric encoding capabilities and utilized YOLOX to improve traffic element detection precision. Additionally, for area detection, we innovatively introduced LDTR and auxiliary tasks to achieve higher precision. As a result, our final OLUS score is 0.58.