Full Professor, Huazhong University of Science and Technology
3 papers at NeurIPS 2025
This paper introduces TopLoRA, which learns token-wise LoRA weights (i.e., token-wise input-output projections).
To address inefficiency from excessive visual tokens in LVLMs, we propose an information-flow perspective revealing dynamic redundancy emergence and introduce a method aligned with the model’s inherent behavior, outperforming all existing approaches.
We develop reliable methods to accurately identify whether an interlocutor in real-time dialogue is human or chatbot
