3 papers
cs.CV2025
JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation
Siheng Wan, Zhengtao Yao, Zhengdao Li +9
Modern Text-to-Image (T2I) generation increasingly relies on token-centric architectures that are trained with self-supervision, yet effectively fusing text with visual tokens rema…
cs.CV2025
Unified Multimodal Understanding via Byte-Pair Visual Encoding
Wanpeng Zhang, Yicheng Feng, Hao Luo +4
Multimodal large language models (MLLMs) have made significant progress in vision-language understanding, yet effectively aligning different modalities remains a fundamental challe…
cs.CV2024
VideoOrion: Tokenizing Object Dynamics in Videos
Yicheng Feng, Yijiang Li, Wanpeng Zhang +4
We present VideoOrion, a Video Large Language Model (Video-LLM) that explicitly captures the key semantic information in videos - the spatial-temporal dynamics of objects throughou…