@JerryLiJiaming

Interactive Multimodal LLM eng / researcher

 San Francisco, CA
Joined April 2016
  • Tweets55
  • Following324
  • Followers677
2Media
The call for the NeurIPS 2026 Creative AI Track is out! In its fourth year, NeurIPS 2026 Creative AI Track invites research papers and artworks that explore emerging applications, methods, and critiques of artificial intelligence and machine learning in art, design, and creative practice. Focusing on the theme of Agency, this year’s track asks: how agency emerges, is exercised, is negotiated, and is contested through creative practice with AI. Agency may belong to an artist, a collaborator, a model, an audience, a platform, a community, or even a larger social and technical system, and may be asserted, delegated, shared, resisted, constrained, or redistributed. Important dates: June 30: Submission Portal Opens August 3 (Anywhere on earth): Submission Deadline September 18: Decision October 23: Final Camera-Ready Submission For more information, visit: neurips.cc/Conferences/2026/…
3
34
6
161
35,729
We built an AI writer arena: 5 AI writers compete, evolve plots, and get shaped by AI readers’ feedback. It could be an IP factory for short-form drama 🎬 Built in a weekend by @JerryLiJiaming, @ywang485, and me → ipfactory.cc What we learned 👇
5
2
12
1,084
A year ago, I left DeepMind to chase a crazy dream with Spellbrush: to bring anime characters to life. Last week, my colleague and I put our in-house AI models to the test. We made this short anime from scratch in 48 hours. 1/3
76
108
21
1,689
232,501
Growing up, I loved anime and games as an art form. To finally cross to the other side—to build the worlds I once only imagined—feels surreal. We’re working on a 3D first-person adventure game, where the core of the experience is an AI character you can truly connect with. 2/3
1
1
91
10,736
We are looking for: 👉 LLM researchers jobs.ashbyhq.com/spellbrush/… 👉 3D Motion researchers jobs.ashbyhq.com/spellbrush/… 👉 Unity developers jobs.ashbyhq.com/spellbrush/… If you know someone who would love to push the boundaries of anime and AI, share this with them—or join us yourself 3/3

AI Anime Researcher - LLM

Make our anime characters come to life

jobs.ashbyhq.com
8
6
100
10,446
【お知らせ】Niji Videoがついにリリース！✨ （音声あり🎶） リリースを記念して、テーマソングをご用意しました！ ぜひ新機能とあわせてお楽しみください。 使い方の紹介はリプライ欄から👇
23
347
125
1,699
398,791
We watched #GoogleIO with Project Astra. 👀
59
215
92
1,258
467,050
Relari just launched on @ycombinator's Launch YC! Congratulations to Yi's team! Relari - Testing and simulation stack for GenAI systems. Check them out: ycombinator.com/launches/KdO…
1
1
751
Mixed Integer Programming is an NP-hard optimisation problem arising in planning, logistics, resource allocation, etc. Presenting a solver with neural heuristics that learns to adapt to the problem domain, outperforming SCIP on Google-scale MIPs: dpmd.ai/13349 (1/)
14
271
40
1,240
Crypkoがスマートフォン向けアプリケーション『進化する少女型情報体 MEMES/ミームズ』（@prj_MEMES）のコアテクノロジーとして提供されます！ wfs.games/memes/ #Crypko #MEMES #ミームズ
101
15
207
RL Unplugged🔌: Offline RL benchmark that comes with both data and implementations of existing offline RL agents. It makes it easy to enter RL research and allows reproducibility.More agents in Acme will come soon. Github: git.io/JJUhd arxiv: arxiv.org/abs/2006.13888
4
82
14
330
Check out the new blog post by @notwaldorf! Extending previous work, she shows you can personalize a pretrained MuiscVAE model by training a tiny VAE in the latent space. Efficiently trained (in the browser!), and on just a couple of data points. magenta.tensorflow.org/midi-…

MidiMe: Personalizing MusicVAE

One of the areas of interest for the Magenta project is to empower individual expression. But how do you personalize a machine learning model and make it you...

magenta.tensorflow.org
Monica Dinculescu@notwaldorf6 Aug 2019
What's better than using a MusicVAE to generate music? Personalizing a MusicVAEVAE for just the music you like! Meet MidiMe, a small magenta.js model that you can train directly ✨IN THE BROWSER✨ with music you give it! 👓 g.co/magenta/midime 🎹 midi-me.glitch.me
1
11
36
紙と厚紙と鉛筆などを使って工作しました。 #花火 #夏祭り #夫婦 #認知症
90
11,985
293
35,831
←なんで怒ってるかわからない俺 →その態度がさらにムカつく嫁
131
77,218
892
327,491
Another great paper from Samsung AI lab! @egorzakharovdl et al. animate heads using only few shots of target person (or even 1 shot). Keypoints, adaptive instance norms and GANs, no 3D face modelling at all. ▶️ youtu.be/p1b5aiTrGzY 📝 arxiv.org/abs/1905.08233
741
11,978
4,178
29,646
Here’s a video of a guy putting a camera on a sushi conveyer belt. It’s wonderful. Every table has a little story!
1,480
114,252
9,436
351,000
The Anti-twitter: Pair two people with different views together in a 1:1 discussion. At the end, pay them both some money if they both can describe why the other believes what they do. Hell, if the gov't put aside $1B a year for this, we'd probably all be better off.
3
24
Huge thanks to the teams at Google Magenta (g.co/Magenta) & Google PAIR for partnering with us to create the first ever AI-powered #GoogleDoodle! #TrioGoals → bit.ly/2TN9umZ #BachDoodle
6
18
2
109
有毒
つよきパンダ🌏▶ﾊｯﾋﾟｰﾊﾞｽﾞｰｶｰｽﾞ!!!@panda045623 Feb 2019
うちのSiriは猟奇的
Cool work doing transfer from image to audio
Yingtao Tian@alanyttian25 Feb 2019
Our work (by @jesseengel and me) is now available on arxiv here arxiv.org/abs/1902.08261 ! Tldr: Cross-modal domain transfer as unsupervised translation between the latent spaces of pretrained generative models.

Latent Translation: Crossing Modalities by Bridging Generative Models

End-to-end optimization has achieved state-of-the-art performance on many specific problems, but there is no straight-forward way to combine pretrained models for new problems. Here, we explore...

arxiv.org
Load more