Yuliang Xiu
@yuliangxiu
Followers
6K
Following
3K
Statuses
4K
Incoming TTAP @Westlake_Uni, Ph.D. at @MPI_IS, previously @USC_ICT. Focusing on democratizing human-centric digitization. Intern at @RealityLabs @Ubisoft
Tübingen, Germany
Joined August 2014
💡 Released the PuzzleIOI dataset ( with 933 subjects, each including "puzzle" captures, A-posed SMPL‑X models, colored scans, and text description. Competing for #CVPR2025 and need a dataset to benchmark your 3D GenAI algorithms with 𝙋𝙎𝙉𝙍 or 𝙘𝙝𝙖𝙢𝙛𝙚𝙧 metrics? Check it out! Kudos to Jinlong Yang and @PriyankaP1201 for building PuzzleIOI.
Code of PuzzleAvatar (#SIGGRAPHAsia2024) gets released. 3D Human reconstruction from unconstrained photo collections (your album), in ANY poses, from ANY views, with ANY cropping or occlusion. NO estimation of body pose or camera is required.
0
6
53
RT @trajan317: Tonight I found out that the NSF math postdoctoral fellowship I applied for is being deleted because it does not comply with…
0
714
0
RT @hila_chefer: VideoJAM is our new framework for improved motion generation from @AIatMeta We show that video generators struggle with m…
0
192
0
RT @GerardPonsMoll1: I will talk today at 17 at the AI doctoral academy, if you are interested feel free to join remotely:
0
2
0
RT @YiMaTweets: Also, many of my students and colleagues working in the field of AI feel that there is an unfair competition between the ac…
0
29
0
RT @YiMaTweets: Given recent events, in both the US and China, many perceive there is now a competition between the two countries for AI te…
0
24
0
RT @akanazawa: Very excited about this work!!! The ability to continuously update your representation opens up many possibilities. Its simp…
0
28
0
RT @ZhidingYu: Zizheng was one of our interns at NVIDIA back in summer 2023. Later, when we were considering to make him a FT offer, he cho…
0
1K
0
RT @Yuchenj_UW: "Tighten export controls on chips" is a loser's attitude. - DeepSeek can already run inference on Huawei Ascend chips - Th…
0
474
0
RT @dimtzionas: 📢 I am #hiring 2x #PhD candidates to work on Human-centric #3D #ComputerVision at the University of #Amsterdam! 📢 The pos…
0
21
0
RT @QuanquanGu: With the stellar performance of DeepSeek V3 and R1, along with their open-sourcing, it’s time to adopt these models as Judg…
0
35
0
RT @soumithchintala: i'm comically impressed that people are coping on deepseek by spewing bizarre conspiracy theories -- despite deepseek…
0
446
0
RT @LunjunZhang: Maybe the sweet lesson of DeepSeek R1 is that, the strongest driver of productivity on earth is hiring senior-year phd stu…
0
37
0
RT @kaiyangzhou: Interestingly, we found some reviews are kind of repetitive of what we put in the paper, and some comments are even nonsen…
0
1
0
RT @Michael_J_Black: Is there an official latex style file for @ICCVConference? I can't find an author kit on-line. Should we use the CVPR2…
0
3
0
RT @ItsTheZhen: Excited to have our Nabla-GFlowNet accepted by #ICLR2025! We propose a novel GFlowNet objective to finetune a diffusion mo…
0
10
0
RT @Almorgand: Video Depth Anything: Consistent Depth Estimation for Super-Long Videos TL;DR: Long videos support; Depth Anything V2 with…
0
30
0
RT @xwang_lk: RLHF is supervised fine-tuning. R1 is true RL. The key difference: RLHF treats language generation as the outcome, while R1 l…
0
26
0