Jianfeng Wang

19 posts

Jianfeng Wang

Jianfeng Wang

@jianfw

Research scientist at OpenAI; 4o imagen; o3/o4-mini.

Katılım Eylül 2013
114 Takip Edilen587 Takipçiler
Jianfeng Wang retweetledi
Arena.ai
Arena.ai@arena·
GPT-Image-2 had a 93% win rate in Image Arena. Arena rankings come from blind, pairwise battles where voters pick between two anonymized image outputs for the same prompt. GPT-Image-2 from @OpenAI was preferred 93% of the time, resulting in a record-breaking +242 point leap ahead of the competition on Arena's Text-to-Image leaderboard.
Arena.ai tweet media
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
49
99
1.4K
160.5K
Jianfeng Wang retweetledi
Kenji Hata
Kenji Hata@kenjihata·
I highly recommend everyone check out the Images 2.0 blog post. The marketing and design teams KILLED IT! openai.com/index/introduc…
English
0
4
22
2.1K
Jianfeng Wang retweetledi
Gabriel Goh
Gabriel Goh@gabeeegoooh·
wow
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.

QST
60
48
959
854.6K
Jianfeng Wang retweetledi
Design Arena
Design Arena@Designarena·
GPT-Image-1.5 has taken #1 on Image Arena This marks a sizeable 9-place improvement since GPT-Image-1, establishing the new frontier for Image Generation Congratulations to the team at @OpenAI for this significant contribution
Design Arena tweet media
English
30
63
510
149K
Jianfeng Wang retweetledi
OpenAI Developers
OpenAI Developers@OpenAIDevs·
Meet GPT-5.1-Codex-Max, our latest frontier agentic coding model, available in Codex starting today. It’s faster, more capable and token-efficient, and able to work persistently on long tasks with built-in compaction abilities.
English
100
219
2.7K
398.4K
Jianfeng Wang retweetledi
Aditya Ramesh
Aditya Ramesh@model_mechanic·
The value of fast iteration in AI is overrated. The best results are obtained by knowing the right things to do and doing each thing with neurotic precision and attention to detail.
English
26
37
434
40.9K
Jianfeng Wang retweetledi
OpenAI
OpenAI@OpenAI·
Sora 2 is here.
English
1.7K
2.3K
20.9K
9M
Jianfeng Wang retweetledi
Sam Altman
Sam Altman@sama·
Excited to launch Sora 2! Video models have come a long way; this is a tremendous research achievement. Sora is also the most fun I've had with a new product in a long time. The iOS app is available in the App Store in the US and Canada; we will expand quickly.
English
394
318
3.9K
381.7K
Jianfeng Wang retweetledi
OpenAI
OpenAI@OpenAI·
Both gpt-oss models are free to download on Hugging Face, with native MXFP4 quantization built in for efficient deployment. Full list of day-one support is available on our blog. huggingface.co/collections/op…
English
28
71
748
176.7K
Jianfeng Wang retweetledi
Mark Chen
Mark Chen@markchen90·
We achieved gold medal level performance on this year's IMO! Our model thinks and writes proofs in clear, plain‑English - no formal code required. Unlike the narrower systems used in past competitions, our model is built to reason broadly, far beyond contest problems.
Alexander Wei@alexwei_

1/N I’m excited to share that our latest @OpenAI experimental reasoning LLM has achieved a longstanding grand challenge in AI: gold medal-level performance on the world’s most prestigious math competition—the International Math Olympiad (IMO).

English
53
61
1.1K
197.2K
Jianfeng Wang retweetledi
Sam Altman
Sam Altman@sama·
the chatgpt launch 26 months ago was one of the craziest viral moments i'd ever seen, and we added one million users in five days. we added one million users in the last hour.
English
2K
2.9K
57.5K
5.5M
Jianfeng Wang
Jianfeng Wang@jianfw·
4o image gen can also generate transparent images. [images blended with a checkerboard background for visualization]
Jianfeng Wang tweet mediaJianfeng Wang tweet media
English
2
4
40
17.3K
Jianfeng Wang retweetledi
Dian Ang Yap
Dian Ang Yap@yapdianang·
GPT-4o can now seamlessly generate images! imo it could be a big step toward intuitive AI interactions (Pictured: visual poetry + text rendering + photorealism) @OpenAI
Dian Ang Yap tweet mediaDian Ang Yap tweet mediaDian Ang Yap tweet mediaDian Ang Yap tweet media
English
3
14
250
43K
Jianfeng Wang retweetledi
OpenAI
OpenAI@OpenAI·
4o image generation has arrived. It's beginning to roll out today in ChatGPT and Sora to all Plus, Pro, Team, and Free users.
OpenAI tweet media
English
962
1.9K
20.6K
4.9M
Jianfeng Wang retweetledi
OpenAI
OpenAI@OpenAI·
OpenAI tweet media
ZXX
567
508
8.6K
1.1M

Keşfet

@OpenAI @gabeeegoooh @ajabri @eliza_luth @kenjihata @dmed256 @elonmusk @BarackObama