Doğuş Can Korkmaz
doguscank
·
AI & ML interests
Vision, LLMs, vLLMs, semantic segmentation, forecasting
Recent Activity
updated
a collection
15 days ago
to read
updated
a collection
15 days ago
to read
upvoted
a
paper
about 2 months ago
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion
Generation in Video Models
Organizations
None yet
Collections
10
-
GenEx: Generating an Explorable World
Paper • 2412.09624 • Published • 95 -
IamCreateAI/Ruyi-Mini-7B
Image-to-Video • Updated • 1.22k • 606 -
Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation
Paper • 2412.06016 • Published • 20 -
Byte Latent Transformer: Patches Scale Better Than Tokens
Paper • 2412.09871 • Published • 95
models
1
datasets
None public yet