Jiasenlu's picture

3 3 2

Jiasenlu

Jiasenlu

·

https://jiasenlu.github.io/

AI & ML interests

Vision and Language

Recent Activity

commented on a paper 6 days ago

AToken: A Unified Tokenizer for Vision

commented on a paper 11 days ago

AToken: A Unified Tokenizer for Vision

authored a paper about 1 month ago

CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching

View all activity

Organizations

None yet

upvoted a paper about 1 month ago

AToken: A Unified Tokenizer for Vision

Paper • 2509.14476 • Published Sep 17 • 36

upvoted a paper 11 months ago

One Diffusion to Generate Them All

Paper • 2411.16318 • Published Nov 25, 2024 • 30

upvoted a paper almost 2 years ago

Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action

Paper • 2312.17172 • Published Dec 28, 2023 • 30