57 15 112

chansung park PRO

chansung

AI & ML interests

None yet

Recent Activity

published a Space about 15 hours ago

chansung/adaptsum

reacted to their post with 👍 2 days ago

Simple summary on DeepSeek AI's Janus-Pro: A fresh take on multimodal AI! It builds on its predecessor, Janus, by tweaking the training methodology rather than the model architecture. The result? Improved performance in understanding and generating multimodal data. Janus-Pro uses a three-stage training strategy, similar to Janus, but with key modifications: ✦ Stage 1 & 2: Focus on separate training for specific objectives, rather than mixing data. ✦ Stage 3: Fine-tuning with a careful balance of multimodal data. Benchmarks show Janus-Pro holds its own against specialized models like TokenFlow XL and MetaMorph, and other multimodal models like SD3 Medium and DALL-E 3. The main limitation? Low image resolution (384x384). However, this seems like a strategic choice to focus on establishing a solid "recipe" for multimodal models. Future work will likely leverage this recipe and increased computing power to achieve higher resolutions.

posted an update 2 days ago

View all activity

Articles

Organizations

Posts 15

Post

1819

Simple summary on DeepSeek AI's Janus-Pro: A fresh take on multimodal AI!

It builds on its predecessor, Janus, by tweaking the training methodology rather than the model architecture. The result? Improved performance in understanding and generating multimodal data.

Janus-Pro uses a three-stage training strategy, similar to Janus, but with key modifications:
✦ Stage 1 & 2: Focus on separate training for specific objectives, rather than mixing data.
✦ Stage 3: Fine-tuning with a careful balance of multimodal data.

Benchmarks show Janus-Pro holds its own against specialized models like TokenFlow XL and MetaMorph, and other multimodal models like SD3 Medium and DALL-E 3.

The main limitation? Low image resolution (384x384). However, this seems like a strategic choice to focus on establishing a solid "recipe" for multimodal models. Future work will likely leverage this recipe and increased computing power to achieve higher resolutions.

Post

1660

New look for AI powered paper reviews from the list by Hugging Face Daily Papers ( managed by the @akhaliq )

Bookmark the webpage along, check comprehensive reviews by Google DeepMind Gemini 1.5, and listen to audio podcast made by the same tech used in NotebookLM.

Link: https://deep-diver.github.io/ai-paper-reviewer/

This is not an official service by Hugging Face. It is just a service developed by an individual developer using his own money :)

View all posts