Jia-Bin Huang Profile
Jia-Bin Huang

@jbhuang0604

50,857
Followers
285
Following
1,361
Media
4,320
Statuses

Associate Professor @umdcs ; Part-time Research Scientist @Meta . I like pixels.

College Park, MD
Joined May 2015
Don't wanna be here? Send us removal request.
Pinned Tweet
@jbhuang0604
Jia-Bin Huang
2 months
How does OpenAI's Sora work? Like many others, I was blown away by the amazing video quality from Sora. 🤯 In this video, I summarize how Sora (might) work and put it in the context of prior work. Super excited to see what comes next!
Tweet media one
1
41
217
@jbhuang0604
Jia-Bin Huang
2 years
How to start a presentation? Most people start with all the boring info (e.g., repeating everything your host just said) and unmotivated technical details. 🥱 After a few mins, everyone starts checking their phone! 😱 How to avoid this? Here is a simple template. 🧵
75
1K
6K
@jbhuang0604
Jia-Bin Huang
4 years
Super excited to share our work on video completion at #ECCV2020 !🤩Our method seamlessly removes objects, watermarks, or expands field-of-view from casually captured videos. Paper: Project: With @gaochen315 , Ayush, and @JPKopf
71
943
4K
@jbhuang0604
Jia-Bin Huang
2 years
How to work with your advisor(s)? Working effectively with your advisor is the no doubt the key to success of your research! However, junior grad students often don't have a clear idea on how to do so. Sharing some tips that I found useful. 👇
31
763
3K
@jbhuang0604
Jia-Bin Huang
3 years
How to make steady progress in my research? I worked so damn hard but "IT JUST DOESN'T WORK!"😤 How can I unblock myself quickly and make good progress toward the goals? Below I compiled a list of tips that I found useful. 👇
17
558
2K
@jbhuang0604
Jia-Bin Huang
3 years
How to come up with research ideas? Excited about starting doing research but have no clue?🤷‍♂️🤷🏻‍♀️ Here are some simple methods that I found useful in identifying initial directions. Check out the thread below 👇
39
530
2K
@jbhuang0604
Jia-Bin Huang
3 years
How to write a paper that looks like a good one? You worked super hard and did great research, but somehow the reviewer 2 just doesn't buy it. Why? 🤔 It's probably because your paper does not look like a good paper *visually*. 🙄 How? 👇👇👇 #AcademicTwitter
26
469
2K
@jbhuang0604
Jia-Bin Huang
7 months
Research summary for the last 3 years... 2021: Replace every CNN with a Transformer 2022: Replace every GAN with diffusion models 2023: Replace every NeRF with Gaussian splatting
34
244
2K
@jbhuang0604
Jia-Bin Huang
2 years
It's time to let go
Tweet media one
24
170
2K
@jbhuang0604
Jia-Bin Huang
2 years
Reviewer: Weak Reject! This is a straightforward combination of two well-known methods. The novelty is limited.
24
143
2K
@jbhuang0604
Jia-Bin Huang
3 months
R2: While the results are impressive, this is a simple combination of diffusion transformer (ICCV 2023) and latent diffusion model (CVPR 2022). Limited novelty. Weak reject.
@OpenAI
OpenAI
3 months
Introducing Sora, our text-to-video model. Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. Prompt: “Beautiful, snowy…
10K
33K
141K
56
157
2K
@jbhuang0604
Jia-Bin Huang
25 days
Holly crap! It’s so embarrassing that I have a PhD and have been actively working in AI but my presentation does not even come close to 1/10 of the clarity of this video.
@3blue1brown
Grant Sanderson
26 days
The next chapter about transformers is up on YouTube, digging into the attention mechanism: The model works with vectors representing tokens (think words), and this is the mechanism that allows those vectors to take in meaning from context.
63
776
5K
19
122
2K
@jbhuang0604
Jia-Bin Huang
2 years
A day of an academic
Tweet media one
7
197
2K
@jbhuang0604
Jia-Bin Huang
3 years
How to do research with my mentors effectively? I get this question frequently in my open office hours. I am still learning as well but I hope sharing my ✌💰 may be helpful to some. Key idea ➡️ **Help them help you!** How? Check out the thread 🧵
18
395
1K
@jbhuang0604
Jia-Bin Huang
2 years
How to network at a conference? Many students will be attending their first-ever *in-person* conference this year. How exciting! 🤩 Some tips on making the best of attending a conference. 🧵
20
297
1K
@jbhuang0604
Jia-Bin Huang
1 year
How to write the Introduction? As a junior student, writing the introduction of a research paper is arguably the most daunting part of paper writing. 😱 Here is a simple template I find useful: 3 Figures 🖼️ + 5 Questions 🤔
17
292
1K
@jbhuang0604
Jia-Bin Huang
4 years
I always feel frustrated at taking photos through fences or windows (e.g., when taking my kids to the zoo). Check out our #CVPR2020 work on "learning to see through the obstructions" Paper: Code: Colab:
13
359
1K
@jbhuang0604
Jia-Bin Huang
2 years
Summarizing the current state of AI
Tweet media one
30
118
1K
@jbhuang0604
Jia-Bin Huang
2 years
HOLY CRAP!! I was told that I can keep my job!
Tweet media one
75
13
1K
@jbhuang0604
Jia-Bin Huang
3 years
How to keep track with the literature? Getting started with research but overwhelmed by THOUSANDS of papers each year? How could one stay sane keeping track of the literature? 😱 Here are some tricks I found useful. 🧵
19
323
1K
@jbhuang0604
Jia-Bin Huang
3 years
How to write clear and concise sentences? Getting ready to write up your very first research paper? Writing a paper could be daunting, particularly for non-native English speakers. 😬😬😬 How can we avoid common mistakes in technical writing? Check out the thread below! 🧵
13
307
1K
@jbhuang0604
Jia-Bin Huang
4 years
Sharing one idea I found useful for paper writing: Do NOT ask people to solve correspondence problems. Some Dos and Don'ts examples below: *Figures*: Don't ask people to match (a), (b), (c) ... with the descriptions in the figure caption.
Tweet media one
9
309
1K
@jbhuang0604
Jia-Bin Huang
3 years
Annoyed by shaky videos? Check out our work on stabilizing shaky handheld videos *without cropping*! Neural Re-rendering for Full-frame Video Stabilization Project:
7
161
940
@jbhuang0604
Jia-Bin Huang
3 years
Reading papers from industrial labs
Tweet media one
11
108
930
@jbhuang0604
Jia-Bin Huang
2 years
How to end a presentation? You have kicked off your talk with a fascinating story and presented an amazing body of work. 🤩 So now how do you end your talk? 🤔 Check out a simple template I like! 🧵
6
167
932
@jbhuang0604
Jia-Bin Huang
2 years
Somehow my timeline is filled with papers where the models were trained with 64 A100 GPUs for weeks. Grad students with two 2080Ti:
23
76
910
@jbhuang0604
Jia-Bin Huang
4 years
Check out our #SIGGRAPH2020 paper on Consistent Video Depth Estimation. Our geometrically consistent depth enables cool video effects to a whole new level! Video: Paper: Project page:
10
212
893
@jbhuang0604
Jia-Bin Huang
1 year
Graduate school application
Tweet media one
10
72
870
@jbhuang0604
Jia-Bin Huang
2 years
Most salient progress in AI/ML these days are driven by insanely large amount of data, model, and compute. It seems increasingly hard to do research in this space in an academic setting. 😟 What should poor academics do next? (asking for a friend)
84
74
849
@jbhuang0604
Jia-Bin Huang
2 years
How to intern? Research internships are great opportunities to do cool research in industrial labs! But it's definitely not easy to complete a solid work in 3 months. Some tips for having a successful internship ... 🧵
10
155
850
@jbhuang0604
Jia-Bin Huang
3 years
Sharing tips on preparing your presentation slides Just attend many thesis presentations and qual exams at the end of the semester. I compiled some common pitfalls here and hopefully would be helpful to some. Check out the thread 🧵below!
13
210
853
@jbhuang0604
Jia-Bin Huang
3 years
Have you ever wondered why papers from top universities/research labs often appear in the top few positions in the daily email and web announcements from arXiv? Why is that the case? Why should I care?
Tweet media one
21
159
844
@jbhuang0604
Jia-Bin Huang
2 years
Based on the twitter timeline, only the top 10 universities are accepting new PhD students.
16
26
786
@jbhuang0604
Jia-Bin Huang
1 year
How to find research opportunities? Finding opportunities to gain experience is arguably the most challenging part for students wishing to pursue grad school, particularly for those who don't have resources/connections. Some tips on approaching potential mentors. 🧵
Tweet media one
21
145
770
@jbhuang0604
Jia-Bin Huang
2 years
How to communicate clearly? Majority of our time goes into emails, slack messages, and loads of meetings. Yet, as a student, no one taught me how to communicate well. (I must have annoyed a lot of people along the way ...😬) Here is a template for organizing your message.
11
127
773
@jbhuang0604
Jia-Bin Huang
3 years
Writing Related Work I enjoy reading/writing the related work section of a paper. It helps organize prior research and put the contributions of the work in proper context. But HOW? Check the thread below👇
6
172
775
@jbhuang0604
Jia-Bin Huang
3 years
Types of Computer Vision Paper (source: @xkcd )
Tweet media one
9
159
727
@jbhuang0604
Jia-Bin Huang
3 years
Sharing ideas on how to disseminate your research. "I am THRILLED to share that our paper is accepted to ..." Congrats! So what's next? No one is going to browse through the list of thousands of accepted papers. Ain't nobody got time for that. Check out 🧵below for examples.
11
181
733
@jbhuang0604
Jia-Bin Huang
2 years
What's the differences among ... Latent space, feature space, embedding space, representation space, latent feature, feature embedding, latent representation, embedding representation, latent embedding, and feature representation? 🤔
22
69
718
@jbhuang0604
Jia-Bin Huang
2 years
How to Survive the First Year of PhD? Excited to get started your PhD study this Fall? 🤩 How to make the best out of your first year and set yourself up on the right path? Here are a few tips I wish I knew. 🧵
14
138
703
@jbhuang0604
Jia-Bin Huang
21 days
college admission in a few years...
Tweet media one
@thegautamkamath
Gautam Kamath
22 days
NeurIPS 2024 will have a track for papers from high schoolers.
Tweet media one
79
91
594
7
63
702
@jbhuang0604
Jia-Bin Huang
6 months
How to get unstuck? "It doesn't work." 🤷‍♀️🤷‍♂️ In most research projects, ~99% of the time your experiments DO NOT work. What should we do to get ourselves unstuck? 🤔 Sharing some tips I found useful. 🧵
5
135
694
@jbhuang0604
Jia-Bin Huang
1 year
How to choose a good Ph.D. advisor? Grad school application season is coming to an end. Congrats on the offers! Now, how would you choose your advisor that will help you succeed? Some tips below (that I wish I knew).
Tweet media one
4
109
681
@jbhuang0604
Jia-Bin Huang
1 year
How to meet with your advisors/mentors? If you are a grad student, having effective regular meetings with advisors or mentors is absolutely crucial for your success! Here are some tips on how to make the most of it! 🧵
Tweet media one
7
110
667
@jbhuang0604
Jia-Bin Huang
7 months
A paper's impact on your career. A good reminder from Bill Freeman.
Tweet media one
18
60
666
@jbhuang0604
Jia-Bin Huang
3 years
The privilege of having a PhD: I can always say "I didn't get what you were saying." and everybody will not assume that I am an idiot.
17
35
653
@jbhuang0604
Jia-Bin Huang
2 years
How to get your paper cited?
23
136
646
@jbhuang0604
Jia-Bin Huang
7 months
I once received advice: "If your current project will not change the field, then it's not worthwhile doing it." This was the time when I first started exploring research. Looking back, this is probably the MOST TERRIBLE advice for me.
9
55
624
@jbhuang0604
Jia-Bin Huang
3 years
Are you a student from underrepresented groups and applying for graduate school in CS this year? Check out many wonderful (student-led) pre-application programs for supporting PhD applicants!
18
226
618
@jbhuang0604
Jia-Bin Huang
1 year
How to create a good table? While in grad school, I thought my job writing the paper was done after dumping all the numerical numbers from my experiments in a table. 🤦‍♂️ Check out some tips that will help you improve the quality of your tables! 🧵
14
121
618
@jbhuang0604
Jia-Bin Huang
8 days
Tweet media one
@KLdivergence
Kristian Lum
10 days
I will never get over how AI/ML people use the word “inference”
67
35
608
4
69
637
@jbhuang0604
Jia-Bin Huang
3 years
How to share your progress with your mentors/collaborators? Throughout your research project, 99% of the time your approach DOESN'T WORK (yet). 😬 How could we share these "failed results" and have productive conversations with your mentors/collaborators? 👇
10
138
598
@jbhuang0604
Jia-Bin Huang
3 years
Excited to share that my group and I will be moving to CS dept. at University of Maryland @umdcs ! I am grateful for my mentors, students, collaborators, family, and friends for their help and support along the way. 🙏
55
10
591
@jbhuang0604
Jia-Bin Huang
2 years
How to present a line plot? Line plots are effective for describing the relationship between two variables of interests. Unfortunately, most junior students would simply copy&paste the figure from the paper in their talk and cause much confusion. 😕 Let's break it down ... 🧵
Tweet media one
6
113
578
@jbhuang0604
Jia-Bin Huang
2 years
*Hook* ❌"Hi, my name is .. I am a .. from .. My research .. I am happy to be here. Today I am going to present this title on the slide." ✅ Start your talk with a story, a picture, a surprising statistics, a quote, a question, a poll from audience, or a guessing game.
5
36
557
@jbhuang0604
Jia-Bin Huang
1 year
How to decide what to work on? So many exciting ideas, so little time! How can one narrow down to a specific idea to work on? 🤔 Sharing some strategies I found useful. 🧵
5
90
555
@jbhuang0604
Jia-Bin Huang
3 years
First Principles of Computer Vision by Shree Nayar. In the era of deep learning everything, understanding the fundamentals is more important than ever!
4
126
550
@jbhuang0604
Jia-Bin Huang
1 year
How to do experiments? Junior students often feel stressed before the weekly meeting with their advisors because their experiments do not go well. 😩😰😱 Some tips on why, what, and how to do experiments. 🧵
Tweet media one
10
146
538
@jbhuang0604
Jia-Bin Huang
3 years
So You Think You Want to Apply for a PhD The application cycle is coming up. How do I maximize my chance of getting admitted to my dream program? 🤔 Check out the thread below for resources/advices/tips!
17
130
541
@jbhuang0604
Jia-Bin Huang
3 months
TL;DR of CS graduate school application
Tweet media one
11
48
534
@jbhuang0604
Jia-Bin Huang
2 years
Grad students working on their papers while the world is on fire
6
35
520
@jbhuang0604
Jia-Bin Huang
2 years
How to work with your senior advisor(s)? Many students find it challenging to navigate grad school when working with senior professors as they are often extremely busy and hands-off in research. Check out below for some tips. 🧵
8
97
519
@jbhuang0604
Jia-Bin Huang
4 years
I still remember I marveled at how simple and elegant the Lucas-Kanade tracker is when I first learned about it as a grad student. Here is a fun story about it. "Newness itself is not a virtue, usefulness is." - Takeo Kanade
7
97
513
@jbhuang0604
Jia-Bin Huang
2 years
How to handle questions in a presentation? When I was a student, I always feel stressful during the Q&A session after my presentation. 😵‍💫 In many cases, I didn't know how to respond well and just froze up there! 🥶 Sharing some tips I learned from others. 🧵
7
96
514
@jbhuang0604
Jia-Bin Huang
4 years
The IEEE PAMI editor added "China" to my co-authors from Taiwan (without consulting with us nor our consent).
Tweet media one
22
140
478
@jbhuang0604
Jia-Bin Huang
1 year
How to write math in a paper? Math allows you to convey your idea precisely and concisely. But how to write them clearly? 🤔 Check out some high-level tips (with examples). 🧵
13
99
494
@jbhuang0604
Jia-Bin Huang
3 years
The wait is over! @gaochen315 released the video completion code in @GoogleColab . No environment setup! Just run the code directly in your browser. Try it out and have fun!
@gaochen315
Chen Gao 髙諶
3 years
The Google Colab of our video completion is up! Now you can edit the video (e.g. removing objects, FOV extrapolation) with one click!
8
42
201
5
100
484
@jbhuang0604
Jia-Bin Huang
2 years
How to improve asynchronous communication? Two years into remote work, asynchronous communication has never been this important for work efficiency and productivity. Some tips for effective async communication 🧵
7
86
484
@jbhuang0604
Jia-Bin Huang
4 months
Academics: "You should finish your PhD with three papers that you are decidedly passionate about." Job market: "Minimum requirement: 8 top-tier conference papers for research scientist roles."
@beenwrekt
Ben Recht
5 months
Since we just wrapped up an AI megaconference, it felt like a good day to plead for fewer papers.
32
162
860
15
37
472
@jbhuang0604
Jia-Bin Huang
2 years
How to present a poster at a conference? Poster presentation is a great way to disseminate your research findings, have in-depth discussions, and expand your networks! Here are some tips for presenting like a pro! 👇
5
97
472
@jbhuang0604
Jia-Bin Huang
2 years
How to get a tenure-track faculty job? Interested in pursuing an academic career? Summer is the best time to kick off your search! Here are some tips that I learned. 🧵
4
85
472
@jbhuang0604
Jia-Bin Huang
2 years
Me: Reviewing CS PhD/internship applications... Also me: Yep, I am absolutely sure that I will not get into any graduate programs and would get zero internship offers if I were the applicant now. Sooooo many talented candidates!
13
13
463
@jbhuang0604
Jia-Bin Huang
2 years
Meeting senior PhD students in grad student visit days
Tweet media one
1
38
458
@jbhuang0604
Jia-Bin Huang
2 years
It's that time of year.
Tweet media one
3
27
449
@jbhuang0604
Jia-Bin Huang
1 year
Excited to share our #CVPR2023 on synthesizing new views along a camera trajectory from a **single image**! How? 💡 The good old epipolar constraints in a pose-guided diffusion model! Paper: Project:
8
63
436
@jbhuang0604
Jia-Bin Huang
2 years
Somehow google scholar is really concerned about a robot reading too many papers
Tweet media one
11
12
435
@jbhuang0604
Jia-Bin Huang
2 years
Glad to learn that my silly Twitter threads are helpful! ☺️
Tweet media one
10
4
432
@jbhuang0604
Jia-Bin Huang
1 year
Student: I want to pursue an academic career. Do I have to do a PhD at a top university? Me: Of course not! You will be evaluated based on the quality of your work, NOT the university prestige. Student: But all the faculty candidates we interviewed are from top places. Me:
Tweet media one
14
27
422
@jbhuang0604
Jia-Bin Huang
3 years
Making pretrained models cool again!
Tweet media one
4
26
407
@jbhuang0604
Jia-Bin Huang
2 years
How to organize your talk? Qual/prelim/defense/conference season is coming up! 😱 How should we organize the talk so that your committee members won't fall asleep? Some simple tips I found useful ...👇
13
85
406
@jbhuang0604
Jia-Bin Huang
4 months
New YouTube video! Diffusion models are awesome! But how do they actually work? 🤔 Check out the video and learn with me!
Tweet media one
4
73
406
@jbhuang0604
Jia-Bin Huang
3 years
For the first time in five years, I have a full-time work schedule. I thought I will trivially be 3-4 times more productive, but it turns out managing time well is so damn challenging. 😬 After watching productivity videos to procrastinate, here are what I found useful. 🧵
2
67
403
@jbhuang0604
Jia-Bin Huang
3 years
Understanding ML/CV papers 📰 • Ground truth label: Some guy says so. • Learning from unlabeled data: Learning from carefully curated ImageNet and pretend that we don't know the labels. • Parameter empirically determined: Tried many paras and this has the best number.
7
40
400
@jbhuang0604
Jia-Bin Huang
3 years
Writing Cold Emails Writing emails to a stranger could be daunting, but it's a great way to build connections, explore opportunities, and even advance your career. How do we write an effective cold email? Check out 🧵 below for some ideas.
12
90
401
@jbhuang0604
Jia-Bin Huang
2 years
CVPR: We welcome new students! Students: Cool! I just submitted my very first paper! CVPR: You now also need to review papers. Students: Not sure how to do that. Here is my attempt. CVPR: Your reviews are too unprofessional. You are now banned for two years. Students: ...
@wjscheirer
Walter Scheirer
2 years
Voting is now closed for the motions proposed at the #CVPR2022 PAMI-TC meeting. All motions have passed: Motion 1: Withdrawn Submissions Will No Longer Be Made Inaccessible to Reviewers Yes: 867 No: 354 Motion 2: Making Authors Responsible for Reviewing Yes: 677 No: 553
2
12
36
15
46
394
@jbhuang0604
Jia-Bin Huang
3 years
Finished my ML course syllabus this Spring! Am I doing this right?
Tweet media one
16
21
384
@jbhuang0604
Jia-Bin Huang
3 years
Trying to cover a lecture on “open/unsolved problems in deep learning” next week. Any suggestions?
37
30
370
@jbhuang0604
Jia-Bin Huang
3 years
Thrilled to share that all my grant proposals submitted last year have been rejected!! It’s time to update and beef up my CV of failures.
12
7
375
@jbhuang0604
Jia-Bin Huang
3 years
It seems that everyone wants to publish many papers but no one wants to read others’ papers… (thoughts after attending a poorly attended poster session)
15
12
372
@jbhuang0604
Jia-Bin Huang
10 months
Excited to turn all the memes into an actual course @umdcs . Looking forward to developing this course! 🤩
Tweet media one
15
31
368
@jbhuang0604
Jia-Bin Huang
4 years
@hardmaru @CVPRConf Thanks @hardmaru for sharing our work! For people who would like to try this out, please check out the code on GitHub and Colab. Thanks!🙏 Paper: Code: Colab:
2
104
360
@jbhuang0604
Jia-Bin Huang
3 years
How to cope with paper rejection? Rejection SUCKS! It feels awful that months of hard work did not pay off. 😭 How do we hold a positive outlook when dealing with rejection? A thread of lessons (learned from many rejections) 🧵
6
79
363
@jbhuang0604
Jia-Bin Huang
1 year
How to email faculty as a prospective student? Emailing faculty whom you would like to work with is a great way to get you on the radar of the faculty. But writing these emails could be daunting 😱 and stressful 😩. Some tips below 👇
4
69
360
@jbhuang0604
Jia-Bin Huang
3 years
How to find a research internship? Doing an internship helps • expand your network 🕸️, • explore new topics 💡, • learn new research skills 🔬, and • earn more money 💰! But how can we find good internship opportunities? 🤔 A thread 👇👇👇
3
55
357
@jbhuang0604
Jia-Bin Huang
2 years
How to develop a productive routine? When transiting from structured learning environments (e.g., courses) to unstructured ones (e.g., research), developing a productive routine and managing their time well are critical for productivity. Sharing some hacks I found useful! 👇
2
45
355
@jbhuang0604
Jia-Bin Huang
3 years
How to prepare your Curriculum Vitae? Your curriculum vitae (Latin for "course of life") is the most important document 📜 for all sorts of career opportunities. But not all students have access to resources for learning to write a good CV. Check out the thread 🧵below!
5
69
352
@jbhuang0604
Jia-Bin Huang
2 years
Student: I want to work with you. I am a big fan Me: Thanks! We can chat … Student: … of your memes! They are hilarious. Me: …
10
10
350
@jbhuang0604
Jia-Bin Huang
3 years
Publications in AI/ML these days
2
25
340