45 citations · 72 across the 39 of their papers we have counts for
43 papers
Anchor and Adapt: Asymmetric Prompt Adaptation for Few-Shot Industrial Anomaly Detection
Mengyang Zhao, Teng Fu, Haiyang Yu +3
In few-shot industrial anomaly detection, the few normal target images provide no direct defect supervision, making anomaly prompts difficult to learn from these samples alone. Som…
IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views
Yuchuan Wu, Ke Niu, Haiyang Yu +3
Generating executable parametric CAD code from dimension-annotated orthographic drawings is a challenging task requiring geometric understanding, procedural reasoning, and precise…
SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding
Yuchuan Wu, Xuan Luo, Yinglian Zhu +3
Chinese ancient document understanding demands complex visual, linguistic, and historical reasoning. Current Large Vision-Language Models (LVLMs) typically rely on an opaque, singl…
ResPrune: Text-Conditioned Subspace Reconstruction for Visual Token Pruning in Large Vision-Language Models
Xu Li, Yi Zheng, Yuxuan Liang +5
Large Vision-Language Models (LVLMs) rely on dense visual tokens to capture fine-grained visual information, but processing all these tokens incurs substantial computational and me…
DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Driving
Zhuolin He, Jing Li, Guanghao Li +9
Dynamic scene reconstruction in autonomous driving remains a fundamental challenge due to significant temporal variations, moving objects, and complex scene dynamics. Existing feed…
AMR-CCR: Anchored Modular Retrieval for Continual Chinese Character Recognition
Yuchuan Wu, Yinglian Zhu, Haiyang Yu +3
Ancient Chinese character recognition is a core capability for cultural heritage digitization, yet real-world workflows are inherently non-stationary: newly excavated materials are…
DocCogito: Aligning Layout Cognition and Step-Level Grounded Reasoning for Document Understanding
Yuchuan Wu, Minghan Zhuo, Teng Fu +3
Document understanding with multimodal large language models (MLLMs) requires not only accurate answers but also explicit, evidence-grounded reasoning, especially in high-stakes sc…
CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation
Ke Niu, Haiyang Yu, Zhuofan Chen +7
Computer-Aided Design (CAD) is essential in industrial design, but the complexity of traditional CAD modeling and workflows presents significant challenges for automating the gener…
Pyramid Token Pruning for High-Resolution Large Vision-Language Models via Region, Token, and Instruction-Guided Importance
Yuxuan Liang, Xu Li, Xiaolei Chen +4
Large Vision-Language Models (LVLMs) have recently demonstrated strong multimodal understanding, yet their fine-grained visual perception is often constrained by low input resoluti…
HERO: Rethinking Visual Token Early Dropping in High-Resolution Large Vision-Language Models
Xu Li, Yuxuan Liang, Xiaolei Chen +4
By cropping high-resolution images into local tiles and encoding them independently, High-Resolution Large Vision-Language Models (HR-LVLMs) have demonstrated remarkable fine-grain…
From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation
Ke Niu, Haiyang Yu, Zhuofan Chen +4
Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent adv…
Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning
Fan Shi, Bin Li, Xiangyang Xue
Abstract visual reasoning (AVR) enables humans to quickly discover and generalize abstract rules to new scenarios. Designing intelligent systems with human-like AVR abilities has b…
CrowdTrack: A Benchmark for Difficult Multiple Pedestrian Tracking in Real Scenarios
Teng Fu, Yuwen Chen, Zhuofan Chen +3
Multi-object tracking is a classic field in computer vision. Among them, pedestrian tracking has extremely high application value and has become the most popular research category.…
CoLa: Chinese Character Decomposition with Compositional Latent Components
Fan Shi, Haiyang Yu, Bin Li +1
Humans can decompose Chinese characters into compositional components and recombine them to recognize unseen characters. This reflects two cognitive principles: Compositionality, t…
CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning
Ke Niu, Zhuofan Chen, Haiyang Yu +5
Computer-Aided Design (CAD) plays a pivotal role in industrial manufacturing. Orthographic projection reasoning underpins the entire CAD workflow, encompassing design, manufacturin…
Zero-Shot Chinese Character Recognition with Hierarchical Multi-Granularity Image-Text Aligning
Yinglian Zhu, Haiyang Yu, Qizao Wang +3
Chinese Character Recognition (CCR) is a fundamental technology for intelligent document processing. Unlike Latin characters, Chinese characters exhibit unique spatial structures a…
PHT-CAD: Efficient CAD Parametric Primitive Analysis with Progressive Hierarchical Tuning
Ke Niu, Yuwen Chen, Haiyang Yu +4
Computer-Aided Design (CAD) plays a pivotal role in industrial manufacturing, yet 2D Parametric Primitive Analysis (PPA) remains underexplored due to two key challenges: structural…
ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models
Ke Niu, Haiyang Yu, Mengyang Zhao +6
Person re-identification (Re-ID) is a crucial task in computer vision, aiming to recognize individuals across non-overlapping camera views. While recent advanced vision-language mo…
Global Semantic-Guided Sub-image Feature Weight Allocation in High-Resolution Large Vision-Language Models
Yuxuan Liang, Xu Li, Xiaolei Chen +5
As the demand for high-resolution image processing in Large Vision-Language Models (LVLMs) grows, sub-image partitioning has become a popular approach for mitigating visual informa…
Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models
Xu Li, Yi Zheng, Haotian Chen +5
Large Vision-Language Models (LVLMs) have achieved remarkable success in a wide range of multimodal tasks by integrating pre-trained vision encoders and large language models. Howe…
When Large Vision-Language Models Meet Person Re-Identification
Qizao Wang, Bin Li, Xiangyang Xue
Large Vision-Language Models (LVLMs) that incorporate visual models and large language models have achieved impressive results across cross-modal understanding and reasoning tasks.…
Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection
Yinxuan Huang, Chengmin Gao, Bin Li +1
Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpo…
Learning Global Object-Centric Representations via Disentangled Slot Attention
Tonglin Chen, Yinxuan Huang, Zhimeng Shen +3
Humans can discern scene-independent features of objects across various environments, allowing them to swiftly identify objects amidst changing factors such as lighting, perspectiv…
FedDEO: Description-Enhanced One-Shot Federated Learning with Diffusion Models
Mingzhao Yang, Shangchao Su, Bin Li +1
In recent years, the attention towards One-Shot Federated Learning (OSFL) has been driven by its capacity to minimize communication. With the development of the diffusion model (DM…