7 4 2

Quan Sun

QuanSun

Quan-Sun

AI & ML interests

Deep Learning, Foundation Model

Recent Activity

authored a paper about 1 month ago

Taming Teacher Forcing for Masked Autoregressive Video Generation

upvoted a paper 5 months ago

Emu3: Next-Token Prediction is All You Need

authored a paper 5 months ago

Emu3: Next-Token Prediction is All You Need

View all activity

Organizations

QuanSun's activity

authored a paper about 1 month ago

Taming Teacher Forcing for Masked Autoregressive Video Generation

Paper • 2501.12389 • Published Jan 21 • 10

upvoted a paper 5 months ago

Emu3: Next-Token Prediction is All You Need

Paper • 2409.18869 • Published Sep 27, 2024 • 94

authored a paper 5 months ago

Emu3: Next-Token Prediction is All You Need

Paper • 2409.18869 • Published Sep 27, 2024 • 94

upvoted a paper 7 months ago

Diffusion Feedback Helps CLIP See Better

Paper • 2407.20171 • Published Jul 29, 2024 • 36

authored a paper 7 months ago

Diffusion Feedback Helps CLIP See Better

Paper • 2407.20171 • Published Jul 29, 2024 • 36

updated a model 12 months ago

BAAI/EVA-CLIP-18B

Feature Extraction • Updated Mar 7, 2024 • 563 • 8

authored a paper about 1 year ago

EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters

Paper • 2402.04252 • Published Feb 6, 2024 • 26

updated 2 models about 1 year ago

BAAI/EVA-CLIP-8B

Feature Extraction • Updated Feb 7, 2024 • 1.56k • 47

BAAI/EVA-CLIP-8B-448

Feature Extraction • Updated Feb 7, 2024 • 33 • 12

New activity in BAAI/Emu2-Gen about 1 year ago

Bf16 not supported

#1 opened about 1 year ago by

samuelqy

New activity in timm/eva_giant_patch14_224.clip_ft_in1k about 1 year ago

total downloads of EVA-CLIP models

#2 opened about 1 year ago by

QuanSun

upvoted a paper about 1 year ago

Generative Multimodal Models are In-Context Learners

Paper • 2312.13286 • Published Dec 20, 2023 • 36

updated 2 models about 1 year ago

BAAI/Emu2-Chat

Text Generation • Updated Dec 21, 2023 • 66 • 28

BAAI/Emu2

Text Generation • Updated Dec 21, 2023 • 299 • 88

authored a paper about 1 year ago

Generative Multimodal Models are In-Context Learners

Paper • 2312.13286 • Published Dec 20, 2023 • 36

liked a Space about 1 year ago

Emu2

👁

New activity in apple/DFN5B-CLIP-ViT-H-14 over 1 year ago

Data

#1 opened over 1 year ago by

QuanSun

authored a paper over 1 year ago

CapsFusion: Rethinking Image-Text Data at Scale

Paper • 2310.20550 • Published Oct 31, 2023 • 26

upvoted a paper over 1 year ago

CapsFusion: Rethinking Image-Text Data at Scale

Paper • 2310.20550 • Published Oct 31, 2023 • 26

authored a paper over 1 year ago

Generative Pretraining in Multimodality

Paper • 2307.05222 • Published Jul 11, 2023 • 22