Author

Jingdi Lei

h-index 5 View on Semantic Scholar

We have 2 of 17 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models

Long visual token sequences often account for a substantial fraction of the computational overhead in multimodal large language models~(MLLMs). Existing approaches reduce this cost by pruning redundant visual tokens, but permanently discard visual evidence that may become useful in subsequent layers. We instead ask whe...

Jing-Di Lei, Junxian Li, Di Zhang et al. · 0 citations

Open access Nov 2024

MolReFlect: Toward In-Context Fine-Grained Alignments Between Molecules and Texts

MolReFlect is proposed, a novel teacher-student framework, where a teacher LLM first generates and refines mappings between caption phrases and SMILES substructures and then explicitly teaches these detailed alignments to a student LLM, enabling LLMs to significantly outperform previous baselines.

Jiatong Li, Yunqing Liu, Wei Liu et al. · IEEE Transactions on Knowled... · 13 citations