Rui Wang

ByteDance Seed Multimodal & Vision. Previously @Uber AI @UberEng PhD @ECEILLINOIS

[Rui Wang @ruiwang2uiuc]

🔗 Demo Video: https://t.co/fQ2bJUz9BE
🔗 Technical Report: https://t.co/5NclteUJD4
🔗 Hugging Face Daily Paper: https://t.co/V30vlEwGzc （Currently #1 Paper of the day at Huggingface papers）

[Rui Wang @ruiwang2uiuc]

I'm pleased to introduce, Self-Forcing++, a simple yet effective training framework for long video generation.

w/ @cuijiaxingfb, @JieWu_10, @liming_ai, T. Yang, @Xiaojie__Li, @ruiwang2uiuc, A. Bai, Y. Ban, Cho-Jui Hsieh

https://t.co/gbrPWLzxI5
https://t.co/V30vlEwGzc (1/n)

[Rui Wang @ruiwang2uiuc]

Currently, Self-Forcing++ has been validated on Wan2.1-T2V-1.3B, demonstrating strong scalability of generation length with increased training budget — offering a simple yet powerful path toward robust long-video generation models.

[Rui Wang @ruiwang2uiuc]

huge congrats to the team. @kenneth0stanley

[Andrew Beam @AndrewLBeam]

Can science create the next scaling paradigm for AI?

We think so, and we'll be using our recent Series A raise to build a new kind of scientific reasoning model at scale.

If you're interested in how we think all of science is subject to the bitter lesson, read on in the 🧵👇

[Rui Wang @ruiwang2uiuc]

Seedream 4.0 is released!

[Artificial Analysis @ArtificialAnlys]

ByteDance Seed launches Seedream 4.0, combining Text to Image and Image Editing in a single unified model!

Seedream 4.0 represents a significant evolution from ByteDance Seed's previous models, merging the capabilities of Seedream 3.0 (Text to Image) and SeedEdit 3.0 (Image Editing) into one powerful unified model. The model performs much better in generating readable, accurate text within images compared to the previous Seedream 3.0 model.

Seedream 4.0 is priced the same as Seedream 3.0 at $30 per 1k generations despite the expanded functionality, and is currently available on @fal.

See below for comparisons between Seedream 4.0 and other leading models in our arena

[Zoubin Ghahramani @ZoubinGhahrama1]

WoZ at the Sphere was a tour de force of AI for creative industries, combining state-of-the-art super-resolution, outpainting generative video and computer vision research at @GoogleDeepMind to bring it all to life.

[Rui Wang @ruiwang2uiuc]

Huge Congrats to Piero , Paul and the team!

[Piero Molino @w4nderlus7]

Today I'm excited to share that @StudioAtelico has raised $5M in seed funding.

We'll use these funds to build games that couldn't exist before with AI tools that empower developers, all while following a clear ethical line on AI.

The other piece of news is that the amazing Chris Olson is joining the team! He already started supercharging our game production.

Thank you to @nathanbenaich of @airstreet, with support from @MinifigVC and @talfanevans from Clay, @HazyResearch and @samjackson from Factory, @TommasoMoraca11 and Isabella Timossi at @vento_ventures , angels including @Thom_Wolf , @doppenhe, @ajratner, @Tkaraletsos, @msciglio, @jacopotagliabue, @pancrazioauteri and @alexfo and @MarcusZe at @prediidata for partnering with us in this journey.

Read more about it the blog post, https://t.co/zMZyGdNiIL.

By the way, we are hiring for an Art Director role! Feel free to reach out.

[AK @_akhaliq]

ByteDance just announced Seaweed-7B on Hugging Face

Cost-Effective Training of Video Generation Foundation Model

[Rui Wang @ruiwang2uiuc]

Read about our newly released Seedream 3.0 technical report at https://t.co/87rjV8gOpT

Blog: https://t.co/TqygP2NQxK

[Artificial Analysis @ArtificialAnlys]

The Mogao Reveal: Congratulations to ByteDance Seed on launching Seedream 3.0, the new leading model on the Artificial Analysis Image Leaderboard, beating out GPT-4o, HiDream-I1-Dev, and Recraft V3

Seedream 3.0 is the latest in the Seedream family of bilingual image diffusion models developed by ByteDance Seed. It leads by a wide margin in the “General and Photorealistic” category, though other models lead in certain categories such as GPT-4o in UI/UX.

The model supports outputs up to 2048x2048 pixels and will soon be rolled out to users on the @dreamina_ai AI creative suite.

See below for example images and a link to see Seedream 3.0 for yourself on the Artificial Analysis Image Arena

[Rui Wang @ruiwang2uiuc]

ByteDance's Image Generation Foundation Model! Proud to be part of the team!

[JIE WU @JieWu_10]

🚀 Introducing Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model by ByteDance. Currently powering Dreamina and Doubao apps.
✨ Key Features:
1. Powerful General Capability
2. Native Bilingual Comprehension Ability
3. Excellent Text Rendering
4. Deep Understanding of Chinese Characteristics
📢 For the first time, we’re sharing the technical details of our text-to-image model.
🙌Through extensive experimentation, we demonstrate that Seedream 2.0 achieves SOTA performance across multiple aspects, including prompt-following, aesthetics, text rendering, and structural correctness.
💡 Compared to Flux 1.1 Pro, MJv6.1, DALL·E,Hunyuan, and 4o, Seedream 2.0 delivers outstanding overall performance.
ArXiv: https://t.co/5wKW3SjJDD
Website: https://t.co/aAhgdcsCRW