8 papers
UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models
Yukun Dai, Mingzhe Dai, Tianshi Wang +3
Vision-Language-Action (VLA) models have emerged as generalist robotic policies capable of following diverse language instructions and performing a wide range of manipulation tasks…
World Craft: Agentic Framework to Create Visualizable Worlds via Text
Jianwen Sun, Yukang Feng, Kaining Ying +8
Large Language Models (LLMs) motivate generative agent simulation (e.g., AI Town) to create a ``dynamic world'', holding immense value across entertainment and research. However, f…
From Pixels to Paths: A Multi-Agent Framework for Editable Scientific Illustration
Jianwen Sun, Fanrui Zhang, Yukang Feng +6
Scientific illustrations demand both high information density and post-editability. However, current generative models have two major limitations: Frist, image generation models ou…
BLM: A Boundless Large Model for Cross-Space, Cross-Task, and Cross-Embodiment Learning
Wentao Tan, Bowen Wang, Heng Zhi +15
Multimodal large language models (MLLMs) have advanced vision-language reasoning and are increasingly deployed in embodied agents. However, significant limitations remain: MLLMs ge…
Closing the Expression Gap in LLM Instructions via Socratic Questioning
Jianwen Sun, Yukang Feng, Yifan Chang +6
A fundamental bottleneck in human-AI collaboration is the ``intention expression gap," the difficulty for humans to effectively convey complex, high-dimensional thoughts to AI. Thi…
A High-Quality Dataset and Reliable Evaluation for Interleaved Image-Text Generation
Yukang Feng, Jianwen Sun, Chuanhao Li +8
Recent advancements in Large Multimodal Models (LMMs) have significantly improved multimodal understanding and generation. However, these models still struggle to generate tightly…
ARMOR: Empowering Multimodal Understanding Model with Interleaved Multimodal Generation Capability
Jianwen Sun, Yukang Feng, Chuanhao Li +7
Unified multimodal understanding and generation have recently received much attention in the area of vision and language. Existing UniMs are designed to simultaneously learn both m…
VGA: Vision GUI Assistant -- Minimizing Hallucinations through Image-Centric Fine-Tuning
Ziyang Meng, Yu Dai, Zezheng Gong +3
Recent advances in Large Vision-Language Models (LVLMs) have significantly improve performance in image comprehension tasks, such as formatted charts and rich-content images. Yet,…