8 papers
Seek to Segment: Active Perception for Panoramic Referring Segmentation
Song Tang, Shuming Hu, Xincheng Shuai +2
Existing referring segmentation models passively process static images captured from fixed perspectives, limiting their applicability in Embodied AI, where agents must perform acti…
AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs
Yaoting Wang, Ziyi Zhang, Wenming Tu +10
Recent advances in Omni-Multimodal Large Language Models (Omni-MLLMs) have enabled strong integration of vision, audio, and language. However, their audio-visual intelligence (AVI)…
ROSE: Retrieval-Oriented Segmentation Enhancement
Song Tang, Guangquan Jie, Henghui Ding +1
Existing segmentation models based on multimodal large language models (MLLMs), such as LISA, often struggle with novel or emerging entities due to their inability to incorporate u…
PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow
Xincheng Shuai, Song Tang, Yutong Huang +2
Graphic design is a creative and innovative process that plays a crucial role in applications such as e-commerce and advertising. However, developing an automated design system tha…
GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering
Xincheng Shuai, Ziye Li, Henghui Ding +1
Generating accurate glyphs for visual text rendering is essential yet challenging. Existing methods typically enhance text rendering by training on a large amount of high-quality s…
FMBench: Adaptive Large Language Model Output Formatting
Yaoting Wang, Yun Zhou, Henghui Ding
Producing outputs that satisfy both semantic intent and format constraints is essential for deploying large language models in user-facing and system-integrated workflows. In this…