6 papers
Hierarchical 3D Scene Graph Construction and Belief-based Planning for Semantic Navigation
Bing Wu, Zuyao Chen, Changwen Chen
Semantic navigation is a fundamental task for embodied agents operating in unseen environments, requiring both semantic understanding and long-term decision-making. Recent foundati…
Anatomy-R1: Enhancing Anatomy Reasoning in Multimodal Large Language Models via Anatomical Similarity Curriculum and Group Diversity Augmentation
Ziyang Song, Zelin Zang, Zuyao Chen +6
Multimodal Large Language Models (MLLMs) have achieved impressive progress in natural image reasoning, yet their potential in medical imaging remains underexplored, especially in c…
From Data to Modeling: Fully Open-vocabulary Scene Graph Generation
Zuyao Chen, Jinlin Wu, Zhen Lei +1
We present OvSGTR, a novel transformer-based framework for fully open-vocabulary scene graph generation that overcomes the limitations of traditional closed-set models. Conventiona…
Compile Scene Graphs with Reinforcement Learning
Zuyao Chen, Jinlin Wu, Zhen Lei +2
Next-token prediction is the fundamental principle for training large language models (LLMs), and reinforcement learning (RL) further enhances their reasoning performance. As an ef…
What Makes a Scene ? Scene Graph-based Evaluation and Feedback for Controllable Generation
Zuyao Chen, Jinlin Wu, Zhen Lei +1
While text-to-image generation has been extensively studied, generating images from scene graphs remains relatively underexplored, primarily due to challenges in accurately modelin…
Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention
Zuyao Chen, Jinlin Wu, Zhen Lei +2
Scene Graph Generation (SGG) offers a structured representation critical in many computer vision applications. Traditional SGG approaches, however, are limited by a closed-set assu…