Assistant Professor, Shenzhen University
3 papers at NeurIPS 2025
This paper introduces TopLoRA, which learns token-wise LoRA weights (i.e., token-wise input-output projections).
This paper proposes a novel framework that generates better contrastive pairs for contrastive learning by integrating LLM-based semantic retrieval with a learnable sample synthesizer.
Training- and GPU-free Spatial Prompting for Multimodal Large Language Models