Xihui Liu
@XihuiLiu
Followers
469
Following
151
Media
2
Statuses
13
Assistant Professor @ HKU. Previous Postdoc @ UC Berkeley and PhD @ CUHK MMLab
Joined August 2015
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
jungkook
• 1226456 Tweets
#خلصوا_صفقات_الهلال2
• 492713 Tweets
برشلونة
• 225005 Tweets
بلد الوليد
• 201702 Tweets
Barca
• 180285 Tweets
Rice
• 178071 Tweets
Georgia
• 138940 Tweets
Raphinha
• 117386 Tweets
Haaland
• 111911 Tweets
#WWEBash
• 102142 Tweets
Lamine
• 92794 Tweets
Hansi Flick
• 83665 Tweets
Everton
• 81976 Tweets
Olmo
• 65500 Tweets
#الاتحاد_الاحق_بالدعم1
• 57985 Tweets
West Ham
• 43962 Tweets
Clemson
• 36194 Tweets
Bournemouth
• 32668 Tweets
McLaren
• 32044 Tweets
Iowa
• 29339 Tweets
Xavi
• 23327 Tweets
Bianca
• 20647 Tweets
Penn State
• 20419 Tweets
West Virginia
• 19662 Tweets
Leverkusen
• 19434 Tweets
CM Punk
• 19045 Tweets
Will Warren
• 15142 Tweets
Mañalich
• 11408 Tweets
Kevin Owens
• 10879 Tweets
Excited to share our work, ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities, which is accepted by ECCV 2024!
Project page:
arXiv:
Code:
2
12
85
Arrived at Vienna! I am at
#ICML2024
this week. We will host the ICML workshop on Multimodal Foundation Models on Embodied Agents
@ICML2024_MFMEAI
on June 26. Looking forward to meeting old and new friends!
6
3
79
Thank
@_akhaliq
for sharing!
Welcome to check out our work DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis
We have made code and models available at
DiM
Diffusion Mamba for Efficient High-Resolution Image Synthesis
Diffusion models have achieved great success in image generation, with the backbone evolving from U-Net to Vision Transformers. However, the computational cost of Transformers is quadratic to the number of
2
30
170
0
6
26
Thank
@_akhaliq
for sharing!
Welcome to check out our work 4Diffusion
Project page
Code
4Diffusion
Multi-view Video Diffusion Model for 4D Generation
Current 4D generation methods have achieved noteworthy efficacy with the aid of advanced diffusion generative models. However, these methods lack multi-view spatial-temporal modeling and encounter challenges in
2
35
167
0
2
8
#CVPR2024
Yunhan will present this work in this afternoon 17:15-18:45 (poster
#321
). Feel free to drop by if you are interested!
DreamComposer: Controllable 3D Object Generation via Multi-View Conditions
paper page:
Utilizing pre-trained 2D large-scale generative models, recent works are capable of generating high-quality novel views from a single in-the-wild image. However, due
0
17
85
0
0
7
In this workshop, Meng Wei will introduce the Open-Vocabulary Part Segmentation Challenge (), and Yunhan Yang will present our recent work on open-vocabulary 3D part segmentation. They are both first-year Ph.D. students in my group. See you on June 18!
Look forward to meeting folks at our 4th workshop of Visual Perception and Learning in the Open World (VPLOW) @ CVPR'24! 🍻
Location: Summit 328, Seattle Convention Center
Time: 8:30am - 5:30pm Local Time (PDT), Tuesday, June 18, 2024
2
4
12
0
1
4
Excited to share our new work T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation.
Project page:
arXiv:
Code:
Hugging Face Daily Papers:
1
0
2
We propose a new task called 3D Reasoning Grounding and a new benchmark ScanReason which provides over 10K question-answer-location pairs from five reasoning types that require the synerization of reasoning and grounding. We further design our approach, ReGround3D, for this task.
0
0
1