Huang Qidong's picture

24 8

Huang Qidong

shikiw

·

https://shikiw.github.io/

AI & ML interests

efficient & trustworthy AI

Recent Activity

liked a model about 1 month ago

Qwen/Qwen3-VL-235B-A22B-Instruct

liked a model about 1 month ago

Qwen/Qwen3-VL-235B-A22B-Thinking

authored a paper 4 months ago

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing

View all activity

Organizations

None yet

Papers 4

arxiv:2506.19848

arxiv:2410.17247

arxiv:2410.07167

arxiv:2311.17911

models 2

shikiw/LLaVA-v1.5-MoCa-7B

Image-Text-to-Text • 7B • Updated Oct 28, 2024 • 1 • 2

shikiw/LLaVA-v1.5-MoCa-7B-pretrain

Image-Text-to-Text • 7B • Updated Oct 28, 2024 • 2 • 1

datasets 0

None public yet