Huang Qidong's picture

15 5

Huang Qidong

shikiw

·

https://shikiw.github.io/

AI & ML interests

efficient & trustworthy AI

Recent Activity

upvoted a paper 5 days ago

OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?

upvoted a paper 11 days ago

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning

upvoted a paper 11 days ago

Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction

View all activity

Organizations

None yet

Papers 3

arxiv:2410.17247

arxiv:2410.07167

arxiv:2311.17911

models 2

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

Image-Text-to-Text • Updated Oct 28, 2024 • 19 • 2

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

Image-Text-to-Text • Updated Oct 28, 2024 • 17 • 1

datasets

None public yet