Publications

(2024). RLHF-V: Towards trustworthy MLLMs via behavior alignment from fine-grained correctional human feedback. In CVPR 2024.

PDF Cite Code

(2024). SeqGPT: An Out-of-the-Box Large Language Model for Open Domain Sequence Understanding. In AAAI 2024.

PDF Cite Code

(2022). Visually Grounded Commonsense Knowledge Acquisition. In AAAI 2023.

PDF Cite Code

(2020). Cross-Modal Omni Interaction Modeling for Phrase Grounding. In ACM MM 2020.

PDF Cite Code