alex choi's picture

alex choi

heyalexchoi

·

heyalexchoi

AI & ML interests

None yet

Recent Activity

upvoted a paper 15 days ago

AudioX: Diffusion Transformer for Anything-to-Audio Generation

upvoted an article 16 days ago

Open-R1: a fully open reproduction of DeepSeek-R1

liked a Space 30 days ago

lmarena-ai/chatbot-arena-leaderboard

View all activity

Organizations

heyalexchoi's activity

upvoted a paper 15 days ago

AudioX: Diffusion Transformer for Anything-to-Audio Generation

Paper • 2503.10522 • Published 22 days ago • 21

upvoted an article 16 days ago

Article

Open-R1: a fully open reproduction of DeepSeek-R1

Jan 28

• 834

upvoted a collection about 1 month ago

🤖 Agents

21 items • Updated Dec 31, 2024 • 148

upvoted a paper about 1 month ago

Executable Code Actions Elicit Better LLM Agents

Paper • 2402.01030 • Published Feb 1, 2024 • 112

upvoted 2 papers 2 months ago

Search-o1: Agentic Search-Enhanced Large Reasoning Models

Paper • 2501.05366 • Published Jan 9 • 100

UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs

Paper • 2311.09257 • Published Nov 14, 2023 • 48

upvoted a collection 2 months ago

Deepseek Papers

Deepseek papers collection • 18 items • Updated Feb 18 • 179

upvoted a paper 3 months ago

Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

Paper • 2410.13863 • Published Oct 17, 2024 • 37

upvoted a paper 6 months ago

Cognitive Architectures for Language Agents

Paper • 2309.02427 • Published Sep 5, 2023 • 8

upvoted 2 papers 7 months ago

Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency

Paper • 2409.02634 • Published Sep 4, 2024 • 97

VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time

Paper • 2404.10667 • Published Apr 16, 2024 • 19

upvoted an article 9 months ago

Article

LoRA training scripts of the world, unite!

Jan 2, 2024

• 57

upvoted 2 collections 9 months ago

DFN Models + Data

CLIP Models trained using DFN-2B/DFN-5B datasets • 7 items • Updated Oct 4, 2024 • 14

MobileCLIP Models + DataCompDR Data

MobileCLIP: Mobile-friendly image-text models with SOTA zero-shot capabilities. DataCompDR: Improved datasets for training image-text SOTA models. • 22 items • Updated Oct 4, 2024 • 26

upvoted a paper about 1 year ago

Rethinking FID: Towards a Better Evaluation Metric for Image Generation

Paper • 2401.09603 • Published Nov 30, 2023 • 18