Weitai Kang's picture

Weitai Kang

weitaikang

·

https://weitaikang.github.io/

AI & ML interests

Large Multimodal Models, Visual Grounding

Recent Activity

updated a dataset about 1 month ago

weitaikang/Edit_eval_benchmarks

published a dataset about 1 month ago

weitaikang/Edit_eval_benchmarks

authored a paper 10 months ago

InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction

View all activity

Organizations

None yet

Papers 9

arxiv:2505.10887

arxiv:2410.00255

arxiv:2409.12963

arxiv:2407.03251

models 1

weitaikang/RL-Qwen2.5VL-lora-7B-ckpt500

8B • Updated Apr 12, 2025

datasets 1

weitaikang/Edit_eval_benchmarks

Updated Feb 13 • 11