Jeff Li
@jiefengli_jeff
Followers
1K
Following
1K
Media
9
Statuses
94
Research Scientist at @NVIDIA | PhD from SJTU @sjtu1896 | Interested in 3D Computer Vision, Human Digitization | Views are my own
Joined February 2015
š£š£š£ Excited to share GENMO: A Generalist Model for Human Motion. Words canāt perfectly describe human motionāso we build GENMO. Itās everything to motion. š„Video, Text, Music, Audio, Keyframes, Spatial Controlā¦š„ -- GENMO handles it all within a single model. š¹ Two
2
33
120
RT @dimtzionas: š¢ I am #hiring 2x #PhD candidates to work on Human-centric #3D #ComputerVision at the University of #Amsterdam! š¢. The posā¦.
0
21
0
RT @ducha_aiki: BLADE: Single-view Body Mesh Learning through Accurate Depth Estimation. @mct1224 Jiefeng Li, @_TianyeLi Ye Yuan, Henry Fuā¦.
0
9
0
RT @songyoupeng: Dreaming of very accurate metric depth in stunning 4K resolution at speed? Check out our Prompt Depth Anything! . We "promā¦.
0
14
0
RT @PavloMolchanov: š Our team is hiring! Join to Advance Efficiency in Deep Learning at NVIDIA! š. š Apply here: .
0
32
0
RT @TsungYiLinCV: NVIDIA Graduate Fellowship Program (2025-2026) is now open for applications. Awards are up to $60,000, along with mentorā¦.
0
14
0
RT @JiaweiYang118: Very excited to get this out: āDVT: Denoising Vision Transformersā. We've identified and combated those annoying positioā¦.
0
81
0
A day of excitement, join NVIDIA Research and get two papers accepted to ECCV on the same dayš.
12
1
168
Congrats @willbokuishen and the team! Canāt wait to try this out.
Introducing Proteus 0.1, REAL-TIME video generation that brings life to your AI. Proteus can laugh, rap, sing, blink, smile, talk, and more. From a single image!. Come meet Proteus on Twitch in real-time. ā.Sign up for API waitlist: 1/11
0
0
4
RT @MattNiessner: Visiting Shenzhen this week and honored to give a keynote at China3DV!. Looking forward to an exciting technical program:ā¦.
0
4
0
RT @davrempe: Check out our recent work led by @MathisPetrovich that generates human motions from a timeline of text prompts, similar to aā¦.
0
12
0
Wonder why there are artifacts in Vision Transformers and how to address them? Check out our latest work!. Website: Code: Paper:
github.com
This is the official code release for our work, Denoising Vision Transformers. - Jiawei-Yang/Denoising-ViT
Denoising Vision Transformers. paper page: identify crucial artifacts in ViTs caused by positional embeddings and propose a two-stage approach to remove these artifacts, which significantly improves the feature quality of different pre-trained ViTs
0
4
42
RT @yuewang314: Ever wonder why well-trained Vision Transformers still exhibit noises? We introduce Denoising Vision Transformers (DVT), leā¦.
0
28
0
RT @JiaweiYang118: Have you ever seen some artifacts inherent in ViT's feature maps? Wonder why and how to address them? Check out our lateā¦.
github.com
This is the official code release for our work, Denoising Vision Transformers. - Jiawei-Yang/Denoising-ViT
0
5
0
RT @haoshu_fang: š¤Joint-level control + portability = robot data in the wild! We present AirExo, a low-cost hardware, and showcase how in-tā¦.
0
37
0
RT @DrJimFan: A neural network can smell like humans do for the first time!šš½. Digital smell is a modality that AI community has long ignorā¦.
0
756
0
RT @yuliangxiu: Thanks @_akhaliq for sharing our new work TeCH. Reconstruction is a form of Conditional Generation, especially for one-shā¦.
0
21
0
RT @leonard_bruns: Tracking any point in a video is a fundamental problem in computer vision. The recent @DeepMind paper TAPIR by @CarlDoerā¦.
0
31
0
RT @Michael_J_Black: French bread, red wine, cheese, the Eiffel Tower. And now @ICCVConference is coming to Paris. All that's missing is yoā¦.
0
12
0
RT @wenlong_huang: How to harness foundation models for *generalization in the wild* in robot manipulation?. Introducing VoxPoser: use LLM+ā¦.
0
142
0