Associate Professor at the Computer Science Department @UCLAComSci @UCLAengineering @UCLA and Chief AI Scientist at @CocoRobotics
Los Angeles
- Tweets 274
- Following 1,042
- Followers 9,030
- Likes 1,532
No accepted papers, I am still happy to announce we open-source GenForce, an efficient PyTorch library for generative modeling. StyleGAN and PG-GAN are perfectly reproduced. We also collect a zoo of 60+ pretrained StyleGAN models, with Colab to play. github.com/genforce/genforce
10
211
945
Two NeurIPS'20 rejections are accepted to CVPR'21 as Orals, including the following work of unsupervised learning of steerable dimension in GANs (genforce.github.io/sefa/). Should thank all NeurIPS adversary reviewers for making this a better work. Be more resilient and optimistic
8
158
841
I will move to UCLA Computer Science early next year to continue my academic journey. I am grateful for the enormous support from many smart and energetic people as collaborators, colleagues, and peers. Look forward to the exciting new chapter with @UCLAengineering @CS_UCLA
44
6
717
I've officially become an Associate Professor with tenure at @UCLA @UCLAengineering as we kick off the new academic year on July 1! Deepest gratitude to my mentors, my amazing students, and wonderful collaborators. Incredible journey so far—more exciting research ahead! 🚀
52
4
476
19,125
received a student’s CV where only rejections are listed in the Publication. Well, I actually like it! Going through the submission cycle and feeling the academic setback twice already makes the undergrad stand out than most of the peers
6
34
423
Our recent @CVPR 25 paper develops a Vid2Sim method that turns a video captured by mobile phone into an interactive environment represented by Gaussian Splatting to train RL agent for urban navigation. Incredible @ZiyangXie_ leaded the project.
Webpage: metadriverse.github.io/vid2s…
8
47
342
31,724
Our NeurIPS '25 Spotlight paper presents an *online* preference learning or RLHF method that enables agents to learn from human feedback in real-time — a step toward safer and more aligned AI for robots.
Led by Haoyuan Cai and Zhenghao Peng
Webpage: metadriverse.github.io/ppl/
1
32
308
31,506
We release a new urban simulator, MetaUrban, to support research on AI agents for micromobility. The work will be presented at #ICLR2025, and the demo code can run on any laptop.
Webpage: metadriverse.github.io/metau…
Code: github.com/metadriverse/meta…
Paper: arxiv.org/pdf/2407.08725
8
51
282
30,339
Our recent #ICLR2022 work develops an efficient Human-in-the-loop learning method called HACO (Human-AI CoPilot), to mentor agents interactively to act and drive while preserving their own curiosity and exploration.
Paper and code are available at decisionforce.github.io/HACO…
8
43
270
🚦 Excited introducing Urban-Sim — our new simulator presented at #CVPR2025 as a highlight paper!
⚡️ Fast training with IsaacSim backend
🏙️ Diverse 3D assets for rich urban scenes
🤖 Towards generalizable robots in dynamic urban environments.
Webpage: metadriverse.github.io/urban…
4
54
249
18,220
As many conferences are coming in the summer, here I share some of the academic posters my collaborators and I have designed as a reference, with both PDF and PPT templates available. Hope to see your awesome posters soon! github.com/zhoubolei/bolei_a…
2
55
218
25,663
#ICLR2025 My lab members, Zhizheng and Joe, will present our work on learning to generate diverse pedestrians by watching web videos this week in Singapore. Let's fill the ghost town house with people in simulations!
Webpage: genforce.github.io/PedGen/
Code: github.com/genforce/PedGen
8
35
202
15,963
Honored to be part of the big family. Go Bruins 🎉 !
We are thrilled to have Bolei Zhou @zhoubolei join our faculty @CS_UCLA in January. Welcome to @UCLA!
samueli.ucla.edu/ucla-samuel…
10
187
Our project on Reinforcement Learning for versatile exoskeleton controllers is published in Nature. I hope there is more AI assistive technology to augment humans in the physical world.
The project is led by NCSU Hao Su's group and the paper is rdcu.be/dKCZV
4
12
172
16,796
Excited to join @CocoRobotics to lead the effort of solving sidewalk autonomy! Look forward to advancing real-world physical AI through large-scale robot learning.
Today we’re launching @CocoRobotics’ new Physical AI Lab led by @zhoubolei, one of the world’s most cited AI researchers, and our new Chief AI Scientist.
Our fleet faces unpredictable environments daily. That real world data is the key to advancing physical AI.
5
7
168
21,767
Our recent work on disentangling the latent variation factors in generative models in unsupervised manner. Fun to interact with the model ;)
project page: genforce.github.io/sefa/
github: github.com/genforce/sefa
video: piped.video/OFHW2WbXXIQ
21
161
Welcome to 3rd Interpretable Machine Learning Tutorial at #CVPR2020 videos and slides are available at interpretablevision.github.i… with @ch402 ,Ruth Fong and Zeynep Akata.
46
149
The code and data of Vid2Sim are released at github.com/Vid2Sim/Vid2Sim. Great work from @ZiyangXie_
Our recent @CVPR 25 paper develops a Vid2Sim method that turns a video captured by mobile phone into an interactive environment represented by Gaussian Splatting to train RL agent for urban navigation. Incredible @ZiyangXie_ leaded the project.
Webpage: metadriverse.github.io/vid2s…
3
15
144
13,440
A computer vision conference called VALSE just ended in Hangzhou, China. Though it is more like a national-wise seminar where all the presented papers are from recent online ICCV, ICML, AAAI, it feels like the vibes of how a conference should look like... not online ICCV again..
1
3
146
Revising student's CVPR draft and LOL on this: `...deep learning-based methods have been wildly used'... yup so wildly used, let's stop abusing! *widely used*
5
3
145
Grateful 🌟 Huge thanks to my amazing colleagues, mentors, and students for their invaluable support and collaboration!
Congrats to @UCLA @UofCalifornia Asst. Prof. Bolei Zhou @zhoubolei @CS_UCLA and @CompMedUCLA on receiving an @NSF CAREER Award. The $587K grant will fund research in embodied AI — artificially intelligent systems that can interact with the physical world.
samueli.ucla.edu/ucla-comput…
24
2
139
15,745
I wonder why you said that. Many top-ranked people are not from CV, like Yang Liu you referred to, and Stefano Ermon, Jun Zhu, Bo Li, and many more. Also, CV people do not care about your work. Don't be a racist to other AI fields.
1
137
9,558
After the #NeurIPS2024 result came out yesterday, my poster repo started getting more stars😂. You are welcome to take my previous posters and pptx sources as references to create your awesome posters! github.com/zhoubolei/bolei_a…
1
3
128
11,290
We open-source a lightweight driving simulator called MetaDrive for RL research. It supports studying various RL topics in one suite, including RL generalization, safe exploration, multiagent RL, and human-in-the-loop methods.
Project Page: metadriverse.github.io/
2
17
121
Our work at CoRL'23 @corl_conf develops an adversarial training for safe driving, where diverse accident-prone scenarios are generated to train a safer and more robust driving agent in simulation.
Paper and code are available at metadriverse.github.io/cat/
1
15
103
15,532
Tame your trained RL agents!
Excited to share #NeurIPS2022 work of Policy Dissection that interprets the learned neural representations to implement human-AI shared control. Now you can play with your autonomous agent as a pet :-)
Paper and code at metadriverse.github.io/polic…
1
14
100
I have been chasing to discover the emerged knowledge in DNN for a long time. We have a recent work showing that different levels of semantics emerge in deep generative representations when trained for scene synthesis.
Paper & Webpage: ceyuan.me/SemanticHierarchyE…
1
32
102
Oh great, it is accepted by #ICLR2025 as Spotlight paper!
We release a new urban simulator, MetaUrban, to support research on AI agents for micromobility. The work will be presented at #ICLR2025, and the demo code can run on any laptop.
Webpage: metadriverse.github.io/metau…
Code: github.com/metadriverse/meta…
Paper: arxiv.org/pdf/2407.08725
1
8
97
10,627
🦾 Excited to share a blog I wrote about how we chart a path toward scaling physical AI for sidewalk autonomy at @CocoRobotics and beyond. From thousands of real-world robot hours to high-fidelity virtual worlds to continuous human feedback — we aim to build sidewalk bots 🤖 that can safely and reliably navigate the chaos of city life 🌆.
Internship and full-time ML/AI engineer positions are also available. Join us for solving the sidewalk autonomy!
cocodelivery.com/blog/scalin…
4
13
98
9,527
This is great! But will you also consider setting up an official satellite location in China, given the fact that so many great NeurIPS papers come from China and so many Chinese researchers couldn't attend the conference due to the US/Canada Visa issue?
1
7
96
7,591
gave a talk @ipam_ucla to go through our persistent multi-year effort of dissection and neural interpretation all at once. The recording is here piped.video/watch?v=i49Jk6eM…
12
84
11,426
My students and I will be at #NeurIPS2023 to present a Spotlight paper for a new Human-in-the-loop Learning method. It has extraordinary sample efficiency and AI alignment for various environments.
Paper and code: metadriverse.github.io/pvp/
8
81
9,454
Learning to drive by watching YouTube videos!
Our #ECCV2022 work develops a contrastive learning for pre-training policy representations on uncurated YouTube videos. The learned representation shows generalizability for downstream driving tasks.
Paper: metadriverse.github.io/ACO/
7
81
Excited organizing the 1st Tutorial on Human-Centered AI for Computer Vision at #CVPR2022 in person along with other three wonderful speakers @judyfhoffman @orussakovsky @ruthcfong tomorrow. Recordings and slides will be made available later at human-centeredai.github.io.
17
78
UCLA Computer Science is hiring one tenure-track faculty this year! Join us for this vibrant city of Los Angeles and incredible SoCal 🏄🌞⛰️
Application link: recruit.apo.ucla.edu/JPF0888…
11
78
13,218
FreeControl is how you get instant controllability for image generation for free!
Sicheng and Fangzhou developed this simple training-free method that allows any condition for any pre-trained diffusion models.
Paper and more results: genforce.github.io/freecontr…
1
14
74
7,601
This work continues our query into the meaning of individual units in DNNs, trained from both classification and generation tasks. Started from the object detectors emerge ICLR'15 paper, finally, the pieces are complete. congrats to the team!
What does one neuron do in a deep net? Removing units reveals structure in classifiers and generators.
Proceedings of the National Academy of Sciences
dissect.csail.mit.edu
github.com/davidbau/dissect
pnas.org/content/pnas/early/…
@junyanz @hen_str @AgataLapedriza @zhoubolei torralba
1
11
75
Many thanks to @NSF for funding our research of developing MetaDrive driving simulator into MetaDriverse, metaverse of autonomous driving, as open-source infrastructure.
News: cs.ucla.edu/ucla-cs-faculty-…
MetaDrive Github Repo: github.com/metadriverse/meta…
2
1
68
7,870
Exploring the social aspects of intelligent agents, here we develop a Multi-Agent RL (MARL) algorithm to socially coordinate the individual behaviors, with collective behaviors emerging. Work to be presented at NeurIPS'21
Project page: decisionforce.github.io/CoPO…
1
7
63
Thanks for online and in-person participation today! The slides are available at human-centeredai.github.io
Excited organizing the 1st Tutorial on Human-Centered AI for Computer Vision at #CVPR2022 in person along with other three wonderful speakers @judyfhoffman @orussakovsky @ruthcfong tomorrow. Recordings and slides will be made available later at human-centeredai.github.io.
2
4
55
We release the code of Sefa along with Colab demo in the Github (github.com/genforce/sefa). With one line of code for 1 second, you can identify the interpretable dimensions and interact with your GAN model:)
project page: genforce.github.io/sefa/
github: github.com/genforce/sefa
video: piped.video/OFHW2WbXXIQ
1
4
56
In daily life after passing the paper exam for a permit, a newbie can drive the car for real under an expert's monitoring. This guardian mechanism is crucial for exploratory but safe learning. See our #CoRL2021 work openreview.net/pdf?id=KnOYrZ…
Poster session today at Session 8
7
55
Our work on improving data-efficient GAN training with contrastive learning is accepted to #NeurIPS2021. Solid work led by @CeyuanY. Code and model are already released.
Check our work 'Data-Efficient Instance Generation from Instance Discrimination', which advances image synthesis with limited data by a clear margin.
Github: github.com/genforce/insgen
Paper: arxiv.org/pdf/2106.04566.pdf
Joint work with Yujun Shen, @YinghaoXu1, @zhoubolei
6
54
I think there should be an official satellite location in China, given the fact that a huge amount of NeurIPS works come from China, and so many great Chinese researchers couldn't attend the conference due to the US/Canada Visa issue or long travel distance.
For years, people have suggested having alternate NeurIPS locations, outside the US. 2025 is the first time it will be done, with satellite locations in Copenhagen and Mexico City.
I wonder if this will be a one-off thing, or whether the trend will continue.
1
2
55
6,673
Many great #CVPR2021 events! Here is a humble one: 4th Tutorial on Interpretable Machine Learning for Computer Vision (interpretablevision.github.i…) is online with lectures from @arimorcos @CynthiaRudin Wojciech Samek. Live panel discussion happens soon today at 2 pm EDT June 20
11
53
Code is released!
🚀URBAN-SIM is released!
A large-scale robot learning platform for urban spaces, built on NVIDIA Omniverse. Train robots at scale in rich, interactive city environments.
🔗 github.com/metadriverse/urba…
Key Features:
⚡️ High Efficiency: Thousands of FPS on a single GPU -- enabling fast robot training.
📈 Scalable Training: Add more GPUs, scale up performance (FPS) continuously.
🏙️Rich Scene Context: Infinite scene generation -- supporting tasks like visual locomotion, navigation, VLA training, and robot-human-scene interaction.
🎮 Versatile Interfaces. Collect data via VR headset, racing wheel, keyboard, or mouse for imitation learning.
🧩 Ecosystem Compatibility: Built on NVIDIA Omniverse, IsaacSim, and PhysX.
3
53
5,286
well, after attending #CVPR2022 in person and back home, started feeling COVID symptoms though still being tested negative. Hope everyone can stay well after the big party :-S
10
1
51
Flow is all you need (aka, no GAN abused), for high-fidelity video inpainting! Glad to show our recent CVPR'19 work on deep video content manipulation. First piece of work done with talented CUHK students :)
PDF: arxiv.org/pdf/1905.02884.pdf
webpage: nbei.github.io/video-inpaint…
1
18
51
Received 1 AAAI early reject email (drat), then followed by 2 CoRL accept (wow) and 1 TPAMI accept (yayyy) emails within 10 hours. Such a life.
The beauty of anonymous peer review nitter.app/Laughs_4_All/status/13…
1
46
Both PyTorch and TF codes are released for our #ECCV2020 work in-domain GAN inversion at genforce.github.io/idinvert/
10
46
Excellent book! Ordered one and will try to get signatures from three authors in person ;)
Our computer vision textbook is released!
Foundations of Computer Vision
with Antonio Torralba and Bill Freeman
mitpress.mit.edu/97802620489…
It’s been in the works for >10 years. Covers everything from linear filters and camera optics to diffusion models and radiance fields.
1/4
2
42
8,151
finally got the chance to try #dalle2, with my favorite Shiba Inu as the theme. The results are astounding!
2
4
38
Thank you for the invitation! It was a fun workshop.
And now, the magnfic @zhoubolei talks about Learning Safety-aware Agents from Human Feedback and Adversary Environments. #uncv2025 #cvpr2025
1
2
42
3,913
We propose InterFaceGAN to interpret the semantics inside the pretrained face synthesis GANs. Various facial attributes emerge spontaneously as disentangled subspaces in latent space, even for pose and synthesis quality. Paper and code are available at shenyujun.github.io/InterFac…
12
37
Here we release the source code, HiGAN, to facilitate reproducibility and further work in GAN interpretability and scene editing.
Code: github.com/ShenYujun/HiGAN
Extended paper: arxiv.org/pdf/1911.09267.pdf
I have been chasing to discover the emerged knowledge in DNN for a long time. We have a recent work showing that different levels of semantics emerge in deep generative representations when trained for scene synthesis.
Paper & Webpage: ceyuan.me/SemanticHierarchyE…
18
40
Tested positive this morning, but feel much better than yesterday. Hope everyone can have a speedy recovery
well, after attending #CVPR2022 in person and back home, started feeling COVID symptoms though still being tested negative. Hope everyone can stay well after the big party :-S
6
1
37
The source code is released for our recent CVPR'20 work, on leveraging the GAN inversion as a powerful image prior to a range of image processing tasks.
Webpage: genforce.github.io/mganprior
Github: github.com/genforce/mganprio…
1
8
38
a recent talk (three months ago) I gave at MIT vision seminar about GAN inversion. From the previous organizer of the event to a speaker (though just virtually), reminded me of so many good old days there =]
[5/11] "Inverting Latent Space of GANs for Real Image Editings", by @zhoubolei
piped.video/watch?v=zyBQ9obu…
4
37
Many thanks for the kind support. The preliminary work, MetaDrive, is already open-source and under active development here: github.com/metadriverse/meta…. More features yet to come.
Congrats to @UofCalifornia @UCLA Prof. Bolei Zhou @zhoubolei @UCLAComSci on receiving an @NSF three-year, $960K grant to lead the development of a new open-source, #AI-powered, autonomous simulation platform, MetaDriverse.
samueli.ucla.edu/ucla-comput…
4
37
8,590
Congrats to Antonio, well received. Also remembering great Thomas Huang, a pioneering researcher and an inspiring mentor in computer vision!
Big congratulations to Dr. Antonio Torralba @MIT for winning the Inaugural Thomas Huang Memorial Prize @CVPR! Look forward to seeing more researchers to be inspired by his impressive contributions to research, education and service to our community. We all need great role models!
1
37
So true. But I would think it like I pay 630K for my faculty job so I should work harder and enjoy it 😂 at least I am intellectually rich =]
Today, while talking about things with colleagues, I learned CS folks with BS degree in finance, more than 5 years younger than me, can make TC over $700K. Well... MIT gave me barely $60K in 2021 while I published like prints (and it was not even faculty job). What a life.
1
37
This CVPR'20 work on 'seriously' evaluating the weakly supervised object localization methods. One of the interesting observations is that none of the five CAM descendants since my original CAM paper in 2016 has actually beaten the CAM performance!
github.com/clovaai/wsolevalu…
1
7
36
Grateful for the kind support from @USNavyResearch ! Amazing to work with the talented students in the lab to pioneer vision and autonomy.
Congrats to @UCLA Asst. Profs. Yuzhang Li of @UclaCBE & Bolei Zhou of @UCLAComSci on each receiving a Young Investigator Program Award from @USNavyResearch to support their work on next-gen batteries & computer vision, respectively. samueli.ucla.edu/yuzhang-li-…
1
36
6,118
See our recent work on zero-shot scene generation.
Excited to share our recent attempt for #3D scene generation🪐. Given text prompt, "SceneWiz3D" can generate high-fidelty 3D scenes and support flexible object control.
Project webpage: zqh0253.github.io/SceneWiz3D…
Paper: zqh0253.github.io/SceneWiz3D…
Code: github.com/zqh0253/SceneWiz3…
1
35
5,512
Our recent work considers pretrained GAN generator as an image prior for a range of image processing tasks
Image Processing Using Multi-Code GAN Prior
deepai.org/publication/image…
by Jinjin Gu et al. including @zhoubolei
#ComputerVision #PatternRecognition
5
32
Thanks for the nice poster. Excited to engage with the lovely ML@GT community. I will talk about our series of work from genforce.github.io/ on generative models.
Next Wednesday, Jan. 27, we are excited to virtually welcome Bolei Zhou from The Chinese University of Hong Kong to discuss interpretable latent space and inverse problems in deep generative models.
Details and Registration:
ml.gatech.edu/events/mlgt-vi…
1
30
Call for submission and welcome to join us for this ICCV workshop at Hawaii!
📣 Call for Submissions - X-Sense Workshop #ICCV2025!
Let's accelerate Ego-Exo Sensing for cleaner, safer, and more efficient mobility experience! 🚀✨
📅 Deadline: August 31, 2025 09:59 AM GMT
📝 Submission Portal: lnkd.in/gyeRFYQv
1
3
27
7,066
Code is now released at github.com/nbei/Deep-Flow-Gu…
Flow is all you need (aka, no GAN abused), for high-fidelity video inpainting! Glad to show our recent CVPR'19 work on deep video content manipulation. First piece of work done with talented CUHK students :)
PDF: arxiv.org/pdf/1905.02884.pdf
webpage: nbei.github.io/video-inpaint…
1
3
27
happy to share the Competitive Pong env, used in the RL course I was teaching where students found fun to compete with each other. It was first initiated by two undergrad students I advised, which turned out winning final year undergrad project award :) github.com/cuhkrlcourse/comp…
7
28
Happy to engage with broader audience from data science area with the excitement of generative modeling.
ODSC West Virtual Conference Speaker. 50% OFF Ends Tomorrow: hubs.ly/H0tvdMb0 #ODSCVirtual #ODCSWest #DeepLearning @CUHKofficial @zhoubolei
27
Full house for our 2nd Tutorial on Intepretable Machine for Computer Vision at ICCV’19. Slide will be made available soon at interpretablevision.github.i…
1
3
25
Honored to be among MIT Tech Review's Innovators Under 35 in the Asia Pacific. Thanks for the tremendous amount of support from my mentors and collaborators innovatorsunder35.com/region…
1
24
For tomorrow morning's poster session, my student and I will present our NeurIPS paper on ScenarioNet, an open-source platform for large-scale traffic scenario simulation and modeling based on MetaDrive.
Paper, code, and data are available at metadriverse.github.io/scena…
Poster #517
1
3
26
2,541
Shared my experience of collecting all rejections from many conferences...keep calm and move on. Bless our NeurIPS submissions in a few hours😂
Wonder how to start your faculty career? grow in company? secure PhD offers? Check our #ICCV'21 workshop on Share Stories and Lessons Learned. As a warm-up, we have released some recorded talks from @dimadamen @deviparikh @xinshuoweng @zhoubolei and a few live talks upcoming!
1
1
25
many thanks to the incredible organizers @taiyasaki , Ke Li, @LingjieLiu1 and others! I have a great time!
We have had an _amazing_ week in Banff at the BIRS “3D Generative Models” workshop
Thank to @BIRS_Math for hosting us!
birs.ca/events/2023/5-day-wo…
22
4,782
Nice chatting with Marco and Peter
Peter Ludwig talked with Marco Pavone (@stanford, @nvidia) and Bolei Zhou (@ucla) about the importance of advanced simulation and scenario generation tools for the development and validation of AD systems.
#intersect24
23
3,266
It's wonderful to have @SergeyTulyakov give a guest lecture in the Deep Learning for Computer Vision course I am teaching at UCLA. He talked about the amazing research works on generative models and NeRFs from his Creative Vision Group at Snap Research: research.snap.com/team/categ…
1
22
5,045
Amazing work done by Jordan and Sicheng. Jordan is still just a rising senior undergrad at UCLA! Always proud to work with talented students.
Ctrl-X was accepted to #NeurIPS2024!
We present a guidance-free structure and appearance control method for any pre-trained diffusion model.
Paper, code, and results: genforce.github.io/ctrl-x
It was awesome collaborating with @sicheng_mo @BenKlingher Fangzhou Mu @zhoubolei :D
1
22
3,705
close to SOTA results on many video datasets with RGB modality only. Kicked my TRN's ass with large margin 😅
Check our #CVPR2020 work 'Temporal Pyramid Network for Action Recognition', a generic module to capture the visual tempos of action instances
Paper: arxiv.org/pdf/2004.03548.pdf
Github: github.com/decisionforce/TPN
Joint work with @YinghaoXu1 Jianping Shi @doubledaibo
and @zhoubolei
5
21
fun fact is that this work was done in 2018, and has been submitted for two years and rejected for three or four hours times ( I cannot count now) by so-called top conferences...until follow-up works from Berkeley and FAIR.
Our #IROS2020 work on cross-view semantic segmentation is being presented on iros2020.org/ondemand/ under the “DL for visual Perception II” session.
Project page: decisionforce.github.io/VPN/.
Thanks to my collaborators @Jack64101391, Tiga, @alexjandonian , and @zhoubolei !!!
2
21
This sounds not good:
Each accepted paper will require a 450 pound Publication Fee
It's here! You can now register for ECCV 2020 Online. Early delegate registration is available for £125 until 20 July 2020. More details at eccv2020.eu/registration #ECCV2020 #Fullyonline
1
19
piped.video/watch?v=QKy2ZDCG… My talk record at CVPR'24 WAD summarizes our effort to build the open-source platform MetaDriverse for AI research and mobility. The slide is available here too: drive.google.com/file/d/1Yir…
2
18
2,134
Welcome to the workshop at ICCV. In the afternoon session, I will give a talk of our effort towards learning physical AI for sidewalk autonomy.
📣 Join us for the ICCV’25 X-Sense Workshop at Hawai'i Convention Center @ Room 323C on Monday, Oct. 20!!
Link: x-sense-ego-exo.github.io
2
20
5,169
Thank @AmazonScience for supporting fundamental research in universities! Congrats my PhD student @sicheng_mo for winning the fellowship.
🎓 Amazon launches AI PhD Fellowship program, providing $68 million over two years to fund PhD students at 9 universities pursuing research in machine learning, computer vision, and natural-language processing. #AmazonAIFellowship amzn.to/4o6uPlu
19
4,238
Oh well, which one should be the advisor? It is complicated...
grad student and advisor nitter.app/FeelGoodPage11/status/…
1
18
Excited to know Two Min Papers Youtube channel features our recent ECCV work on GAN inversion: piped.video/watch?v=2qMw8sOs…. Here we provide a Colab live demo to play: colab.research.google.com/..…
2
2
17
My most relieved accomplishment in 2020 is getting two decent but repeatedly rejected works published somewhere😅: VPN (rej by CVPR'19, ICCV'19, CVPR'20) at IROS'20 (decisionforce.github.io/VPN/) and HiGAN (rej by NeurIPS'19, ICLR'20, two major rev) at IJCV (genforce.github.io/higan/)
1
16
Fun panel discussion, and finally having a group photo with Coco Robotics founders and UCLA alum @zac_rash and Brad!
Incredible #LATechWeek Event + Panel with Curbivore highlighting Autonomy and the Future of Delivery.
Thank you to everyone who brought the energy and excitement for this space, and to our partner Colony for providing great food!
15
3,289
I guess my former sweet home institute @MIT_CSAIL has a lot of cat lovers too 😂
Cats, meet steerable dimensions in GANs.
Steerable dimensions in GANs,
meet cats.
genforce.github.io/sefa
(v/@CUHKofficial @zhoubolei)
#GANs #machinelearning #cats #FridayFeels
1
1
15
Thanks the support from all my lovely students and collaborators!
.@zhoubolei of @CUHKERG has recently been named as one of the 20 honourees of the regional @techreview #InnovatorsUnder35. Prof. Zhou has been working on understanding #deepneuralnetworks and making #AI models more trustworthy. bit.ly/2OWawJa
#congratz #AIBlackBox
1
15
Code for FreeControl is released.
Thanks for sharing our work!@_akhaliq Our code and gradio demo has been released.
Code: github.com/genforce/freecont…
Project Page: genforce.github.io/freecontr…
1
14
4,528
just know one paper got accepted to AAAI. One of the reviewers gave us 1 score (trivial, wrong, or existing work) for the submission, then he apologized like this...Being nice works...
2
14
Great event! Thanks for hosting. Hope SoCalCV can come sooner:)
#SoCalNLP 2022 was a massive success! Thanks everyone who submitted, reviewed, presented, joined for a fantastic time!
Thank you to our speakers, @YejinChoinka @srush_nlp, @yanning_shen @swabhz @zhoubolei and William Cohen!
And congrats to our sponsored best paper winners.. 1/4
2
13
Yes I have developed and used CAM before ;)
Introducing a new paper with Jae Myung Kim, @junsukchoe, @zeynepakata @ ICCV 2021:
Keep CALM and improve your visual feature attribution.
Paper: arxiv.org/abs/2106.07861
Code: github.com/naver-ai/calm
Keep reading if you have used CAM before - worth your time! [1/13]
1
12