XDWang101 Profile Banner
XuDong Wang Profile
XuDong Wang

@XDWang101

Followers
984
Following
1K
Statuses
98

PhD Candidate, Berkeley AI Research Lab @UCBerkeley; Interning @GoogleDeepMind | ex-intern at FAIR @MetaAI and GenAI team @MetaAI

Berkeley, CA
Joined March 2020
Don't wanna be here? Send us removal request.
@XDWang101
XuDong Wang
@XDWang101
1 month
Looking to save time on making slides and focus on what really matters? 🚀 Check out Jiaxin’s latest paper on AutoPresent—a model that creates presentation slides from scratch! 🎉 @aomaru_21490
@aomaru_21490
Jiaxin Ge
@aomaru_21490
1 month
Introducing "AutoPresent: Designing Structured Visuals From Scratch". We employ code generation to create structured, high-quality presentation slides from scratch! 📄 🤗 🔗 @berkeley_ai @LTIatCMU
1
0
11
@XDWang101
XuDong Wang
@XDWang101
2 months
@liliyu_lili Glad to know you enjoyed our workshop!!!! 🎉 love your talk! ❤️
0
0
0
@XDWang101
XuDong Wang
@XDWang101
2 months
🚨Join us at the NeurIPS2024 Workshop on Self-Supervised Learning - Theory and Practice! Featuring talks from leading researchers at UC Berkeley, MIT, UW, FAIR, DeepMind, MILA, AI2, NTU, JHU, Brown, and UofBonn! 🗓️ Sat, Dec 14, 2024 📍 West Meeting Room 202-204 🧭 📌 See the attached schedule for details
Tweet media one
Tweet media two
1
18
79
@XDWang101
XuDong Wang
@XDWang101
2 months
I'll be at #NeurIPS2024 to present our work "UnSAM: Segment Anything without Supervision" 🎉 Feel free to stop by and say hi! 😀 Poster: Dec 11, 4:30 - 7:30 PM PST, East Exhibit Hall A-C #4900 🔗 Code: 📷 arXiv:
@XDWang101
XuDong Wang
@XDWang101
4 months
SAM & SAM-2 are great but depend on costly annotations. Can we 'segment anything' without supervision?🤔 Yes! Check out UnSAM @NeurIPS24—an unsupervised segmenter that achieves SAM-level results! 🎉 Even better—UnSAM+ beats SAM with +6.7% AR & +3.9% AP, using just 1% labels!💪
2
14
79
@XDWang101
XuDong Wang
@XDWang101
2 months
RT @randall_balestr: The numbers are out! Very proud to share that @BrownUniversity/@BrownCSDept is where a lot of the Self Supervised Lear…
0
9
0
@XDWang101
XuDong Wang
@XDWang101
3 months
@aomaru_21490 Thank you for sharing SegLLM, jiaxin! 😃
1
0
0
@XDWang101
XuDong Wang
@XDWang101
3 months
@baifeng_shi Hhh thank you Baifeng!
0
0
1
@XDWang101
XuDong Wang
@XDWang101
3 months
@johnnys96666474 Happy to know that you love these papers! Thank you! 😊
0
0
1
@XDWang101
XuDong Wang
@XDWang101
3 months
This work is a collaboration with many amazing colleagues 🎉🎉🎉: @li78658171, Shaolun, @kk_konstantinos, Kehan, Yusuke, Kazuki, and my PhD advisor @trevordarrell n/n
0
0
0
@XDWang101
XuDong Wang
@XDWang101
4 months
Super cool open-sourced video generation model! Congratulations 🎉 @ajayj_
@genmoai
Genmo
@genmoai
4 months
Introducing Mochi 1 preview. A new SOTA in open-source video generation. Apache 2.0. magnet:?xt=urn:btih:441da1af7a16bcaa4f556964f8028d7113d21cbb&dn=weights&tr=udp://tracker.opentrackr.org:1337/announce
1
0
10
@XDWang101
XuDong Wang
@XDWang101
4 months
RT @li78658171: Glad to see our last year NeurIPS 2023 paper Hierarchical Open-vocabulary Universal Image Segmentation(HIPIE) is making rea…
0
1
0
@XDWang101
XuDong Wang
@XDWang101
4 months
RT @junyi42: Excited to share MonST3R! -- a simple way to estimate geometry from unposed video of dynamic scene We achieve competitive res…
0
135
0