zengyh1900 Profile Banner
Yanhong Zeng Profile
Yanhong Zeng

@zengyh1900

Followers
234
Following
601
Statuses
66

Researcher in Shanghai AI Lab. Previously: PhD @MSFTResearch (MSRA) & SYSU.

Shanghai, China
Joined July 2022
Don't wanna be here? Send us removal request.
@zengyh1900
Yanhong Zeng
2 months
RT @IAMJBDEL: DiffSensei is on 🤗 Hugging Face 🤗 Models: 🤗 Dataset: 💡 An excellent way to…
0
23
0
@zengyh1900
Yanhong Zeng
2 months
😆 I absolutely love the generated manga about the Nobel Prize—so funny! This really shows how crucial datasets are! We put a lot of effort into building high-quality datasets for #manga generation. 📚✨ #AI #MangaArt
@xtl994
Xiangtai Li
2 months
Thanks for your attention to our work. The code is also available. In addition, we also give an introduction video at youtube.
0
0
11
@zengyh1900
Yanhong Zeng
5 months
0
0
4
@zengyh1900
Yanhong Zeng
6 months
WOW!!! A GAME FROM NIJI 😍
@nijijourney
niji・journey ✨
6 months
🎩 ✨ Ready for an adventure? Join Tuxedo Cat as he wields dark magic to craft the ultimate bribe for Saika! No niji sub needed - anyone can help him out in this event! ✨⭐ 🎁 Win the exclusive Tuxedo Cat Fan Club badge and stand out in the Niji Discord with HALF A MILLION community members! 🚀 Stay tuned for more info tomorrow! 👀 #Nijijourney #TuxedoCat
1
1
11
@zengyh1900
Yanhong Zeng
6 months
Tweet media one
@atptour
ATP Tour
6 months
NOVAK DJOKOVIC IS AN OLYMPIC #GOLD MEDALIST 🇷🇸 #Paris2024 | #Olympics | #tennis
Tweet media one
0
0
2
@zengyh1900
Yanhong Zeng
6 months
RT @robrombach: 🔥 I am so damn excited to announce the launch of Black Forest Labs. We set ourselves on a mission to advance state-of-the-a…
0
156
0
@zengyh1900
Yanhong Zeng
7 months
Still just generating dance videos? Check the latest progress HumanVid in camera trajectory control and recreating classic movie shots 😍😍
@zhenzhiwang
Zhenzhi Wang
7 months
Want to generate camera controllable human videos like a real movie clip? Try our HumanVid dataset and a baseline model combined by AnimateAnyone and CameraCtrl. Project Page: Paper: Data and code coming soon.
1
0
23
@zengyh1900
Yanhong Zeng
7 months
RT @LeoXing8: @_akhaliq Code, HuggingFace demo and Introduction Video has been released✨! Welcom to have a try🤗! Huggingface Space: http…
0
3
0
@zengyh1900
Yanhong Zeng
7 months
RT @XingangP: 📺Live Stream Translation via Uni-directional Attention Uni-directional Attention is common in LLMs. We study uni-directional…
0
3
0
@zengyh1900
Yanhong Zeng
7 months
BTW, ONE full registration can only cover ONE main conference paper 🥲 (CVPR allows to cover multiple papers
@jon_barron
Jon Barron
7 months
Baffling @eccvconf policy: Students cannot register their own paper, and must either rely on a non-student co-author's full registration, or must pay more money. Is the idea that we should be taxing students who write papers without faculty/industry support? Seems bad.
Tweet media one
0
0
1
@zengyh1900
Yanhong Zeng
7 months
RT @LeoXing8: @_akhaliq More demo case:
0
3
0
@zengyh1900
Yanhong Zeng
7 months
Our first attempt to introduce uni-directional attention into video diffusion models, for real-time streaming video processing. Nice demo by @LeoXing8 😍😍
@LeoXing8
LeoXing
7 months
Thanks @_akhaliq to share our work. Pleas check more demo on our project page: Code will be released at More demo case ⬇️:
0
6
23
@zengyh1900
Yanhong Zeng
7 months
SO CUTE😍
@nijijourney
niji・journey ✨
7 months
🎉 Niji Emoji Challenge - July 2024 🎉 Hey everyone! We are excited to announce our new event for July: The Niji-Moji Challenge! ✨ Show us your best niji-made emoji! (You can make emojis with niji?! Yes.) The winner gets their emoji added to our server! Event details below👇
Tweet media one
0
0
2
@zengyh1900
Yanhong Zeng
7 months
@skarlywarly @heartereum AMAZING! it might be hard to get even if it's released though 🥲🥲🥲 thanks for your reply
0
0
1
@zengyh1900
Yanhong Zeng
7 months
@skarlywarly @heartereum are there any information about gr4 this year 😅
1
0
0
@zengyh1900
Yanhong Zeng
7 months
@l2NXwDRPjdkBlVA はい、24年にはGR4がありますか?
0
0
0
@zengyh1900
Yanhong Zeng
7 months
@bdsqlsz xs 这期真的精彩
0
0
2
@zengyh1900
Yanhong Zeng
7 months
@Arata_Fukoe IT IS TOO WILD
0
0
0
@zengyh1900
Yanhong Zeng
7 months
thank you for sharing! @AdeenaY8 😍Looking forward to more user cases and feedbacks from using #foleycrafter
@AdinaYakup
Adina Yakup
7 months
FoleyCrafter 🔥 a video-to-audio generation framework from @OpenMMLab , which can produce realistic sound effects semantically relevant and synchronized with videos! Model: Demo: Paper: ✨ High-Quality Audio Generation: Ensures audio quality using a pre-trained text-to-audio model. ✨ Semantic Adapter: Aligns audio generation with video features through parallel cross-attention layers. ✨ Temporal Controller: Achieves precise audio-video synchronization with an onset detector and timestamp-based adapter. ✨ Text Prompt Compatibility: Supports controllable and diverse audio generation using text descriptions.
0
0
4
@zengyh1900
Yanhong Zeng
7 months
@noahthihawin19 @camenduru yes. source codes and weights are publicly available
0
0
2