Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
Released CreatiPoster, an AI-driven graphic design generation system (2025)
Unified-MLLM for image layer decomposition accepted by ICML 2025 (2025)
RelationLMM accepted by TPAMI-25 (2025)
GRES selected as an 'Excellent Science & Technology Academic Paper' for the 2024 Shenzhen 4th Excellent Science & Technology Academic Paper Selection (2024)
Graphist accepted by AAAI 2025 (2025)
One paper accepted by CVPR 2024 (2024)
D-Cube accepted by NeurlPS 2023 (2023)
Released Link-Context Learning for MLLMs and an interesting dataset ISEKAI (2023)
GRES accepted by ICCV 2023 (2023)
Released Shikra, an awesome MLLM for Referential Dialogue (2023)
One paper accepted by TPAMI (2023)
One paper accepted by ECCV 2022 (2022)
Two papers accepted by ACM MM 2022 (2022)
One paper accepted by CVMJ (2022)
One paper accepted by CVPR 2022 as oral presentation (2022)
One paper accepted by TIP 2021 (2020)
One paper accepted by ECCV 2020 (2020)
One paper accepted by TNNLS 2020 (2020)
One paper accepted by CVPR 2020 (2020)
One paper accepted by ICASSP 2018 (2018)
Two papers accepted by ICONIP 2017, one of which is an oral paper (2017)
Background
Currently working as a Vision-Language Researcher at ByteDance, focusing on multimodal LLMs and their applications.
Miscellany
Seeking interns passionate about Graphic Design to collaborate on impactful research projects. Please feel free to contact via email.