OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models [ICML 2026]
arXiv preprint arXiv:2602.04804, 2026
About Me
I am an incoming Ph.D. student at the School of Intelligence Science and Technology, Nanjing University. I am also a research intern on Kuaishou's Kling team.
My research focuses on multimodal large language model reasoning, planning, evaluation, and efficient multimodal systems. I am very interested in research on multimodal agents, particularly topics related to embodied agents that align with embodied intelligence.
Research
- Audio-visual and omni-modal understanding for multimodal large language models.
- Efficient omni-modal modeling, token compression, and evaluation.
- Multimodal reasoning and planning for Agent-based solutions to complex Real-world Problems.
Publications
OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs [ICLR 2026]
arXiv preprint arXiv:2510.10689, 2025
MPCC: A Novel Benchmark for Multimodal Planning with Complex Constraints in Multimodal Large Language Models [ACM MM 2025]
arXiv preprint arXiv:2507.23382, 2025
Work Experience
Research Intern, Kling Team, Kuaishou Technology
Working on multimodal and omni-modal model research.
Education
Ph.D., School of Intelligence Science and Technology, Nanjing University
Incoming doctoral student.
Undergraduate Study, School of Future Technology, Harbin Institute of Technology
Focused on deep learning, large language models, and multimodal large language models.
Contact
I am open to discussions and collaboration on multimodal understanding, efficient reasoning, agents, and related applications. I am currently exploring the application of agents in embodied scenarios. Anyone interested in my research is welcome to contact me via email.