Hugging Face's logo
Delin Qu's picture
4 3 7

Delin Qu

delinqu
gentlebowl's profile picture ysy0515's profile picture
·
https://delinqu.github.io/

AI & ML interests

Embodied AI, 3D Vision

Recent Activity

upvoted a collection about 9 hours ago
Foundation Vision-language-action Model
commented on a paper about 9 hours ago
SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
authored a paper about 9 hours ago
Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction
View all activity

Organizations

IPEC at Shanghai AI Laboratory's profile picture

delinqu's activity

commented a paper about 9 hours ago
New activity in google/paligemma2-3b-pt-224 2 months ago

model._vocab_size vs len(tokenizer) Mismatch

3
#2 opened 2 months ago by
delinqu

Weird Behavior of Eager Attention Implementation during Fine-tuning

1
#5 opened 2 months ago by
delinqu
New activity in depth-anything/Depth-Anything-V2-Metric-Indoor-Base-hf 4 months ago

The real scene metric depth estimation accuracy?
#2 opened 4 months ago by
delinqu