This is your work, valued

Beijing / Shanghai / Shenzhen

Lai Wei

Expert
@waltonfuture

Second-year Ph.D. candidate at School of Computer Science, SJTU. Working on continual learning and context learning of MLLMs.

waltonfuture.github.io/

MM-UPT. [NeurIPS 2025] First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

87

Diff-eRank. [NeurIPS 2024] A Novel Rank-Based Metric for Evaluating Large Language Models

59

Diabetica. [SCI-FM@ICLR 2025] Specialized LLMs capable of handling various diabetes tasks

57

RL-with-Cold-Start. SFT+RL boosts multimodal reasoning

47

InstructionGPT-4. InstructionGPT-4

42

NLP_basic. Some basic algorithms in NLP

6

NLP-projects. Python

5

waltonfuture.github.io. HTML

2