Yonglong Tian

118 posts

Yonglong Tian

Yonglong Tian

@YonglongT

Research Scientist @OpenAI. Prev RS @GoogleDeepMind , PhD @MIT. Opinions are my own.

Boston, MA Katılım Haziran 2019
253 Takip Edilen4.2K Takipçiler
Sabitlenmiş Tweet
Yonglong Tian
Yonglong Tian@YonglongT·
Excited to see the effort I led brings significant improvements on visual reasoning! Also such a relief! I have been nervous since I was the biggest internal GPU burner for a while - what if I was wasting too many of my colleague's opportunities to improve the model? phew a bit
OpenAI@OpenAI

GPT-5.2 Thinking evals

English
28
17
405
56.5K
Ryan Hanrui Wang
Ryan Hanrui Wang@hanrui_w·
I’ve been reflecting a lot on this journey, and I feel incredibly grateful. To the Eigen AI team: thank you for choosing to build something hard together, and for bringing so much ambition, intensity, and care every day. I’m truly proud of what we have built, and even more grateful that we get to continue this next chapter together. To our customers and developers: thank you for trusting us early, bringing us meaningful problems to solve, and shaping Eigen through your feedback, partnership, and belief in what we were building. To our advisors, investors, and supporters: thank you for believing in us early, guiding us along the way, challenging us to think bigger, and standing with us through every stage of the journey. And to the Nebius team: thank you for the conviction, trust, and partnership throughout this process. We’re excited to join forces, keep building with the same ambition, and take this next chapter even further. This milestone would not have been possible without all of you. I’m deeply thankful, proud of what we have built together, and excited for what comes next! ❤️
Eigen AI@Eigen_AI_Labs

Today, we're announcing that Eigen AI is joining Nebius (NASDAQ: NBIS). From day one, our mission has been Artificial Efficient Intelligence — building the world's most efficient engines for generating intelligence. Together with Nebius, we're working toward the best AI cloud, uniting Eigen's full-stack model and inference software, ranked #1 on Artificial Analysis for inference speed, with Nebius's global hardware and infrastructure footprint, so any developer or enterprise can run the best models at the best price, with no capacity ceiling. After close, Eigen's optimization stack will be integrated directly into Nebius Token Factory. The entire Eigen AI team is joining Nebius in full, establishing Nebius's engineering and research presence in the San Francisco Bay Area. To our customers, our team, our investors at Tectonic Ventures, E14 Fund, Uncorrelated Ventures, and AGI House Ventures, our angel investors, advisors, mentors, and supporters — and to the Nebius team for the conviction and partnership — thank you. The mission doesn't change. The leverage behind it does. Ryan Hanrui Wang, co-founder and CEO of Eigen AI, said: “We’re proud to join Nebius and work alongside the Token Factory team to push the boundaries of inference performance. Nebius has built a world-class AI cloud with a deep engineering culture that perfectly aligns with our own. Together, we are removing the friction of AI model customization and deployment so developers can run models reliably in production without managing the underlying infrastructure.” Full announcement at: eigenai.com/blog/eigen-ai-…

English
26
15
233
24K
Yonglong Tian
Yonglong Tian@YonglongT·
It's fun to directly optimize FID. But it's even more scientifically satisfying to see Jiawei shows that some generations with very low FID can be bad. We need to go beyond optimizing FID or optimizing towards reporting better FID.
Jiawei Yang@JiaweiYang118

Two months ago, I vaguely posted a number: 0.9 FID, one-step, pixel space. Now it is 0.75, and can be even lower. Many wonder how. I thought it might end as a small FID prank: simple and deliberate. It started with one question: can FID be optimized directly, and what does it reveal? Introducing FD-loss.

English
1
1
66
9.1K
Boyuan Chen
Boyuan Chen@BoyuanChen0·
This is what I’ve been cooking in the past 4 months . GPT Image 2 is over a massive 240 elo jump over the second place model, marking the biggest jump bigger than the rest of the leaderboard combined
Arena.ai@arena

Exciting news - GPT-Image-2 by @OpenAI has claimed the #1 spot across all Image Arena leaderboards! A clean sweep with a record-breaking +242 point lead in Text-to-Image - the largest gap we’ve seen to date. - #1 Text-to-Image (1512), +242 over #2 (Nano-banana-2 with web-search aka gemini-3.1-flash-image) - #1 Single-Image Edit (1513), +125 over #2 (Nano-banana-pro aka gemini-3-pro-image) - #1 Multi-Image Edit (1464), +90 over #2 (Nano-banana-2) No model has dominated Image Arena with margins this wide. Huge congratulations to @OpenAI on this major breakthrough in image generation! More performance breakdowns by category in the thread below.

English
74
76
1.6K
151.1K
Hongyu Ren
Hongyu Ren@ren_hongyu·
Check out Muse Spark, our first milestone in the quest for personal superintelligence! Scaling this with the team has been a total blast. Give it a spin and let us know what you think! 🥑
Hongyu Ren tweet mediaHongyu Ren tweet media
English
18
59
316
69.7K
Hieu Pham
Hieu Pham@hyhieu226·
I have made the difficult decision to leave @OpenAI. Working here and at @xai before was a once-in-a-lifetime experience. I have met the best people. Not the best people in AI. Not the best people in tech. Simply the best people. At these companies, I have helped creating extremely intelligent entities that will meaningfully improve our lives. The work makes me proud. But the intensive work came with a price. I cannot believe I would say this one day, but I am burnt out. All the mental health deteriorating that I used to scoff at is real, miserable, scary, and dangerous. I am going to take a break from frontier AI labs, and will take my family to my home country Vietnam. There, I will try something new, and also search for a cure for my conditions. I hope I will heal. Until then.
English
1.1K
411
14K
1.2M
Yonglong Tian
Yonglong Tian@YonglongT·
Excited to see the effort I led brings significant improvements on visual reasoning! Also such a relief! I have been nervous since I was the biggest internal GPU burner for a while - what if I was wasting too many of my colleague's opportunities to improve the model? phew a bit
OpenAI@OpenAI

GPT-5.2 Thinking evals

English
28
17
405
56.5K

Keşfet

@hanrui_w @openpcma @CVPR @BoyuanChen0 @ren_hongyu @hyhieu226 @OpenAI @xai