collaborators

8 papers

cs.CV2026

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…

cs.CV2026

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)…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CL2026

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…