Shu Zhang (@shugerdou) profile picture

Shu Zhang AI researcher

Palo Alto, CA
Joined November 2015
Shu Zhang retweeted
🎉ULIP-2 is accepted to #CVPR2024.🎉 May the recaptioning force be with your 3D multimodal learning. Paper: arxiv.org/pdf/2305.08275.pdf Code: github.com/salesforce/ULIP Blog: blog.salesforceairesearch.co… Team: @Le_Xue01 @realNingYu @shugerdou Artemis Panagopoulou @LiJunnan0409 @RobobertoMM @jiajunwu_cs @CaimingXiong @stanleyran @jcniebles @silviocinguetta
Excited to release our ULIP-2, a SOTA multimodal pre-training for 3D understanding that is free from manual annotations. Big salute to the great authors @Le_Xue01 @realNingYu @shugerdou @LiJunnan0409 @RobobertoMM @jiajunwu_cs @CaimingXiong @stanleyran @jcniebles @silviocinguetta
1
7
35
2,665
Shu Zhang retweeted
📢 Our BannerGen open-source library incorporates LayoutDETR, LayoutInstructPix2Pix, and RetrieveAdapter in parallel for diversified experience of banner designs. Great work from the team: Chia-Chih Chen*, @realNingYu*, Zeyuan Chen, @shugerdou, @stanleyran
We introduce our 🔥BannerGen🔥 which enhances the experience of designers. It integrates three in-house multimodal GenAI to empower graphic design workflows, bring forward ideas, & scale up productivity. Lib: github.com/salesforce/Banner… Blog: blog.salesforceairesearch.co…
2
1
5
1,274
Excited to share our GlueGen. Thanks everyone for your wonderful work! See you in ICCV!
We present ✍️GlueGen✍️, efficient adapters for diffusion models, that achieves X-to-image generation by multimodal controls: multilingual texts, sounds, and their mixes. arXiv: arxiv.org/pdf/2303.10056.pdf Web: canqin001.github.io/GlueGen-… Code: github.com/salesforce/GlueGe… (1/n)
1
5
346
We present ✍️GlueGen✍️, efficient adapters for diffusion models, that achieves X-to-image generation by multimodal controls: multilingual texts, sounds, and their mixes. arXiv: arxiv.org/pdf/2303.10056.pdf Web: canqin001.github.io/GlueGen-… Code: github.com/salesforce/GlueGe… (1/n)
1
24
2
68
9,999
Amazing @silviocinguetta Salesforce AI new generative large multi-modal for image generation & editing w/ NLP! Great collaboration @SFResearch & ⁦@Stanford⁩. Web: shorturl.at/lmMX6 ArXiv: arxiv.org/abs/2305.11147 Code: github.com/salesforce/UniCon… github.com/salesforce/UniCon…
10
37
2
174
62,932
Excited to introduce a new generative large multi-modal model for image generation and editing using natural language! Great collaboration Salesforce AI Research @SFResearch and Stanford U! Web: shorturl.at/lmMX6 ArXiv: arxiv.org/abs/2305.11147 Code: github.com/salesforce/UniCon…
2
18
3
73
24,761
Shu Zhang retweeted
Introducing ULIP-2, our latest work scaling multimodal pre-training for 3D understanding without the need for any manual annotations. Check out our code & released large-scale tri-modal datasets! github.com/salesforce/ULIP Arxiv: arxiv.org/abs/2305.08275 Blog: blog.salesforceairesearch.co…
2
28
5
82
18,546
New blog post on our #AAAI2018 FlowGAN paper by @adityagrover_ and Manik Dhar: surprising results comparing GAN vs. mixture of Gaussians! goo.gl/WiiVbM (btw Manik is applying to PhD programs - check out his folder if you are hiring)
Released paper: "Adversarial Generator-Encoder Networks" with V. Lempitsky, A. Vedaldi. arxiv.org/abs/1704.02304 code github.com/DmitryUlyanov/AGE
2
39
3
100
I'll be in New Orleans for the annual AAAI conference this week! Visit our page to learn more about Amazon Research and our publications at #AAAI2018 amazon.jobs/en/landing_pages…