Igor Gilitschenski @igilitschenski Twitter profile

Last Seen Profiles

@cruelgetaway_

@seolbiyy

@pivotalventures

@davidrliu

@potelongtabetai

@senaka_admin

@coco_kitsune

@jackcorrbit

@pt_token

@stevie_mckenna

@officiallyali

@TheRealKirstyG

@MasAllaDelGolYT

@FerryhillDynam1

@Quantectum_Euro

@UOPX

@MurrayLedger

@schnirosaurier

@marie_keates

@GinaValis

@khwampa

@Coach_Kowalski

@ParadigmSports

@TylerManionTV

@Nadatuw

@BlackBone_io

@mariabuxton2gm1

@DG_Reformed

@choiyewonq

@psjbutler

@nycreaders

@youneedselfhelp

@faiqairudin

@FieldGulls

@byunbear_

@JeffConawayTFA

Igor Gilitschenski

@igilitschenski

2 years

Young PI trying to outline the direction of their new lab.

4

47

481

Igor Gilitschenski

@igilitschenski

3 years

Doing research is no less challenging than professional sports.🏃🧑‍🔬 But PhD students get nowhere near as much life support as top athletes do. In a talk for my first group of grad students, I presented a brief PhD survival guide. It focuses on three main points... 1/5

3

63

373

Igor Gilitschenski

@igilitschenski

4 years

I'm thrilled to announce that I will be joining the University of Toronto as an Assistant Professor in 2021. All of this feels like a dream coming true as I have been admiring the research at @UofT since I first learned about Neural Networks in high school. 1/4

25

7

326

Igor Gilitschenski

@igilitschenski

11 months

Creating 3d reconstructions from very few images is a challenging task. In our #cvpr2023 work SparsePose, led by @_sam_sinha_ , we address one of the underlying challenges, the estimation of camera poses. 📄 Paper: 1/n

4

53

246

Igor Gilitschenski

@igilitschenski

6 months

I plan to take on graduate students 🎓 working on Computer Vision 📷, AI 🧠, & Robotics 🤖 in @UofTCompSci . Interested in joining and becoming part of the broader @UofTRobotics and @VectorInst communities? Learn more at 1/2

6

41

191

Igor Gilitschenski

@igilitschenski

2 years

Excited to now officially announce the launch of my group, the Toronto Intelligent Systems Lab at @UofT . We are looking for people at all levels to join us. Check out our website and learn more about our work and how to get involved:

Toronto Intelligent Systems Lab

tisl.cs.toronto.edu

4

26

168

Igor Gilitschenski

@igilitschenski

3 years

New year, new job! 💼 Excited to join @ToyotaResearch 🚘🦾💻 as a Research Scientist (visiting). Looking forward to new amazing colleagues many of whom are past collaborators and friends. My time at @MIT_CSAIL has been amazing and I'm excited to continue working together.

0

108

Igor Gilitschenski

@igilitschenski

11 months

Excited to share that I have joined @VectorInst as a faculty affiliate. 🎉 Looking forward to being part of an exciting community with brilliant colleagues in ML & AI.

11

3

107

Igor Gilitschenski

@igilitschenski

3 years

Passionate about Math 🧮, CS 💻, AI 🧠, and Robots 🦾? This season, I am looking for my first cohort of graduate students 🎓 at the fantastic @UofTCompSci 🇨🇦 ❤️💻. Find out more at and apply by Dec 1st.

Our Programs - Graduate — Department of Computer Science, University of Toronto

With over 250 top graduate students, we are one of the largest computer science graduate programs in the country.

web.cs.toronto.edu

4

19

103

Igor Gilitschenski

@igilitschenski

3 years

Handed over the @MIT_CSAIL Distributed Robotics Lab's PostDoc bike to Xiao Li ( @xli417 ). Proud to have been in the company of its great owners: Mac Schwager ( @Stanford ), Javier Alonso-Mora ( @tudelft ), and Cristian-Ioan Vasile ( @LehighU ). Hope it brings you luck as it did for us.

3

100

Igor Gilitschenski

@igilitschenski

7 months

Excited to share that @nanditav17 (PI) and I have received the Sony Focused Research Award to support our work on neutral rendering within @UofTCompSci , @UofTRobotics , and @VectorInst

Nandita Vijaykumar and Igor Gilitschenski win 2022 Sony Focused Research Award

Assistant professors Nandita Vijaykumar and Igor Gilitschenski are joint winners of a 2022 Sony Focused Research Award.

web.cs.toronto.edu

12

4

98

Igor Gilitschenski

@igilitschenski

2 years

We have released the code for VISTA, our data-driven simulator used for some of our recent work at ICRA and RA-L. Check it out at Big Kudos to @xanamini and @johnsonwang0810 for leading the underlying projects and the code release.

MIT CSAIL

@MIT_CSAIL

2 years

MIT has released a photorealistic, open-source simulator for autonomous vehicles:

3

154

611

0

18

93

Igor Gilitschenski

@igilitschenski

3 years

Check out our #NeurIPS2021 paper "Is 💥Bang-Bang💥Control All You Need? Solving Continuous Control with Bernoulli Policies" (with @timseyde , @WilkoSchwarting , @b_stellato , Martin Riedmiller, @markus_with_k , and Daniela Rus). We analyze a surprising phenomenon in RL... 1/5

3

9

83

Igor Gilitschenski

@igilitschenski

2 years

Grateful for having received the Robotics and Automation Letters Outstanding Associate Editor award! Congrats to all awardees at today's #ICRA2022 award ceremony. Happy to see so many friends and former colleagues among them. I'm very impressed by your work and creativity!

2

1

80

Igor Gilitschenski

@igilitschenski

6 months

Check out our work "Geometry Matching for Multi-Embodiment Grasping" (led by @JMarakiii ) that will be presented at #CoRL2023 today! 1/n 🏠 📄 🎥

1

12

81

Igor Gilitschenski

@igilitschenski

7 months

My grad student @JMarakiii rocking her first invited talk in front of full room at the #ICCV2023 Workshop on Big Model Adaptation for Computer Vision! 🎉🎙️

1

6

78

Igor Gilitschenski

@igilitschenski

5 months

Feels like #NeurIPS2023 is a gathering of a very fast growing family. What started as a family ski trip to the Canadian mountains… 1/2

2

3

72

Igor Gilitschenski

@igilitschenski

4 years

Happy to invite submissions for our @NeurIPSConf Workshop on Robot Learning. Our fantastic speakers involve: @DorsaSadigh ( @StanfordAILab ), @RaquelUrtasun ( @UofTCompSci & @UberATG ), @peteflorence ( @GoogleAI ), @HwangboJemin ( @kaistpr ) & Fabio Ramos ( @NVIDIAAI & @sydney_uni ) 1/2

1

10

67

Igor Gilitschenski

@igilitschenski

1 year

Excited to be starting as Associate Editor for the International Journal of Robotics Research. 🤖🧑‍💻📰 IJRR has played an important role in advancing robotics and connecting an interdisciplinary audience since before I was born. Looking forward to being part of this journey. 🚀

1

69

Igor Gilitschenski

@igilitschenski

7 months

Reconnecting with friends and colleagues is one of the best parts of a conference. #ICCV2023

1

3

67

Igor Gilitschenski

@igilitschenski

4 years

Very excited to have received a Robotics and Automation Letters Best Paper Award with Teddy Ort, Krishna Murthy, @rohanbbanerjee , @saikrishna_gvs , @dhaivat1729 , @duckietown_coo , and Daniela Rus for MapLite (). Huge shout out to Teddy for leading that work!

4

2

64

Igor Gilitschenski

@igilitschenski

3 years

My slides (available at ) are an ad-hoc material collection from several different books and sources I found here. It is impossible to master all of this at once. Working on one aspect in each of these areas is a good start. 5/5

20211015_Grad School Survival Guide.pdf

drive.google.com

0

5

58

Igor Gilitschenski

@igilitschenski

11 months

As @CVPR is rapidly approaching, I am excited to share our lab's work that you can check out at the conference starting with SPIn-NeRF led by @ashmrz10 . 🏠 Web: 📄 Paper: 1/n

2

10

58

Igor Gilitschenski

@igilitschenski

4 years

Yay! Our proposal for the "3rd Robot Learning Workshop" was accepted at NeurIPS. It is jointly organized with @ItkinaMasha , @AlexBewleyAI , @RCalandra , @perezjln , @Ransalu , @markus_with_k , and Vincent Vanhoucke. More info coming soon.

2

57

Igor Gilitschenski

@igilitschenski

2 years

In today's afternoon session at @ieee_ras_icra , @xanamini will be presenting our work "VISTA 2.0: An Open, Data-driven Simulator for Multimodal Sensing and Policy Learning for Autonomous Vehicles" Paper: 1/n

2

9

53

Igor Gilitschenski

@igilitschenski

4 years

Interested in working with cool robots at @UofT / @UofTRobotics ? We are looking for a Robotics Laboratory Technician to join @BurgnerKahrs , @animesh_garg , @florian_shkurti , and myself at the beautiful @UTM campus. See for job posting.

Robotics Laboratory Technician

jobs.utoronto.ca

0

8

49

Igor Gilitschenski

@igilitschenski

2 years

On my way to @ieee_ras_icra ! My first in-person attendance in 2.5 years. It’s off to a good start. Entire row in the airplane consists of ICRA attendants.

0

48

Igor Gilitschenski

@igilitschenski

6 months

MIT Distributed Robotics Lab reunion at @corl_conf !

1

0

46

Igor Gilitschenski

@igilitschenski

3 years

Easy way to tell that the @NeurIPSConf deadline⌛️has just passed: Numerous friends and colleagues working in ML simultaneously started responding to emails & messages from the last 1.5 weeks.

1

46

Igor Gilitschenski

@igilitschenski

2 years

Can't wait for the #NeurIPS2022 Workshop on Robot Learning? 🤖👨‍🏫 We got you! In the upcoming weeks, we will post talks of our panelists starting with @andyzengtweets & @jackyliang42 who have cool insights on "Language as Robot Middleware" 🤖💬🚀

Language as robot middleware

Andy Zeng & Jacky Liang will join us during the workshop (December 9), where we bring together experts with diverse perspectives to highlight the ways curren...

www.youtube.com

0

18

45

Igor Gilitschenski

@igilitschenski

7 months

Thanks for featuring our work @_akhaliq !

AK

@_akhaliq

7 months

Reconstructive Latent-Space Neural Radiance Fields for Efficient 3D Scene Representations paper page: Neural Radiance Fields (NeRFs) have proven to be powerful 3D representations, capable of high quality novel view synthesis of complex scenes. While…

4

57

218

0

9

43

Igor Gilitschenski

@igilitschenski

7 months

On the academic CS job market this season? 🎓💼 We are looking for multiple new faculty to join us in @UofTCompSci . 🧑‍💻❤️🇨🇦 Find out more at or simply reach out to me if you are interested!

2

11

44

Igor Gilitschenski

@igilitschenski

10 months

Thanks @_akhaliq for featuring our work. Huge kudos to @iamborisi from @drmapavone 's AV group at NVIDIA for leading the project and to my undergrad research student @songguanyu0316 for his first contribution as part of our group.

AK

@_akhaliq

10 months

trajdata: A Unified Interface to Multiple Human Trajectory Datasets paper page: The field of trajectory forecasting has grown significantly in recent years, partially owing to the release of numerous large-scale, real-world human trajectory datasets for…

0

13

58

0

5

44

Igor Gilitschenski

@igilitschenski

5 months

Check out our @SIGGRAPHAsia work "iNVS : Repurposing Diffusion Inpainters for Novel View Synthesis". This paper, led by @yash2kant , leverages monocular depth in combination with diffusion inpainters for single-image novel view synthesis. 1/n

1

10

44

Igor Gilitschenski

@igilitschenski

1 year

Having worked mainly in robotics and estimation, I'll be attending #CVPR for the first time this year. Largely thanks to my brilliant grad students @ashmrz10 , @_sam_sinha_ , and @yash2kant (plus many collaborators). Congrats on getting your papers accepted! 🎉 Details coming soon.

1

43

Igor Gilitschenski

@igilitschenski

3 years

Join us for the 3rd Workshop on Robot 🦾🦿Learning 👩‍🏫👨‍🏫 at this year's @NeurIPSConf . Our program features invited and contributed talks📢, a panel discussion💬🗯, and a virtual poster session 💡 in @gather_town with over 30 contributed posters. 1/🧵

1

4

42

Igor Gilitschenski

@igilitschenski

6 months

Somehow, @florian_shkurti and I must have scared away our own students. Fortunately, @RaquelUrtasun ’s team volunteered to take a @UofTRobotics at #CoRL2023 picture with us.

1

0

42

Igor Gilitschenski

@igilitschenski

9 months

Great having @GlenBerseth visit @UofTRobotics today. Thank you for the inspiring talk on your work in robot learning.

1

41

Igor Gilitschenski

@igilitschenski

5 months

About to depart to New Orleans for #NeurIPS2023 . 🛫 Reach out if you’re interested in chatting about neural representations and world models as well as their role in robotics. 🦾 Or simply to have a debate over coffee ☕️ on when AI will take over the world. 🌎

3

2

40

Igor Gilitschenski

@igilitschenski

1 year

Maplab 2.0 paper seems out on ArXiV. Congrats Andrei, Lukas, and everyone at @ASL_ETHZ ! preprint: code:

0

10

37

Igor Gilitschenski

@igilitschenski

11 months

In our #CVPR2023 work Invertible Neural Skinning, led by @yash2kant , we focus on the task of reposing clothed humans for animation. 🏠 Web: 📄 Paper:

1

3

38

Igor Gilitschenski

@igilitschenski

3 years

Interested in robotics? We're hiring a lab technician at @UofTCompSci / @UofTRobotics / @UTM_MCS . Join @BurgnerKahrs , @animesh_garg , Lueder Kahrs, @florian_shkurti , and myself to help building a new robotics program in CS. Many cool robots guaranteed. 🦾🦿

Robotics Laboratory Technician

jobs.utoronto.ca

1

9

35

Igor Gilitschenski

@igilitschenski

1 year

This year, CVPR has 5‼️ workshops on autonomous driving. 💻🚙 Just in case anyone was wondering whether there is still enough work to do for academic researchers in that space. 😉

2

3

36

Igor Gilitschenski

@igilitschenski

1 year

Our work "Towards Zero-Shot Multi-Team Racing: Competitive Driving via Learning in Simulation" (led by Peter Werner & @timseyde ) has won the Best Workshop Paper Award 🏆 at the #ICRA2023 Workshop on Multi-Robot Learning. 🎉 1/n

1

3

36

Igor Gilitschenski

@igilitschenski

4 years

Excited to share our #CoRL2020 work "Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space". We propose a novel Multi-Agent RL method for learning competitive behavior from images. Paper: Site: 1/5

1

10

36

Igor Gilitschenski

@igilitschenski

1 year

Continuing the @NeurIPSConf Robot Learning Workshop talk series, I am excited to share "A Vision for Certifiable Perception: from Outlier-Robust Estimation to Self-Supervised Learning" by @MIT 's amazing @lucacarlone1 & @TalakRajat 1/2

A Vision for Certifiable Perception: from Outlier-Robust Estimation...

Luca Carlone & Rajat Talak will join us during the workshop (December 9), where we bring together experts with diverse perspectives to highlight the ways cur...

www.youtube.com

1

11

36

Igor Gilitschenski

@igilitschenski

2 years

Together with @yash2kant , we were representing the Toronto Intelligent Systems Lab at #ECCV2022 .We've had a wonderful time presenting our two works Housekeep and LaTeRF. 1/3

1

2

34

Igor Gilitschenski

@igilitschenski

2 years

📢 Toronto 🇨🇦 AI 🧠 Robotics 🦾 Seminar 📢 Our seminar series is back featuring local and international speakers from mid-career grad students to early career assistant professors. The seminars are usually on Mondays at 10:30am ET. More info at 1/n

1

3

35

Igor Gilitschenski

@igilitschenski

2 years

Still shocked and angry about the illegal attack on Ukraine. It is a humanitarian tragedy. Are you (or do you know) a Ukrainian Robotics/CV/ML scientist or grad student who is trying to find refuge? Please reach out. I might be able to host you as a visitor in my group at @UofT .

0

9

35

Igor Gilitschenski

@igilitschenski

1 year

Excited about last season's inspiring speakers 📢 at the Toronto AI Robotics Seminar. Huge kudos to @Dazitu_616 & @WeiChengTseng1 for organizing. Missed a talk? 😱 Need to procrastinate on your CoRL paper? 🤯 We got you! 1/3 🏠 🎥

1

4

34

Igor Gilitschenski

@igilitschenski

1 year

Super cool to have @MetaAI ‘s @mhmukadam visit @UofTRobotics today and talk about their differentiable optimization library Theseus.

0

34

Igor Gilitschenski

@igilitschenski

5 months

The first paper we will be presenting at #NeurIPS2023 is "SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models" led by my amazing student @Dazitu_616 . Object-centric learning aims to represent visual data with a set of object entities ("Slots"). 1/n

1

4

34

Igor Gilitschenski

@igilitschenski

3 years

First, organizing your life.📆 This sounds trivial but can be surprisingly hard when coming from undergrad where the school structures the schedule and the dorm offers three meals a day. A PhD is often the first time students have to think about these things for themselves. 2/5

1

33

Igor Gilitschenski

@igilitschenski

9 months

Processing contradictory reviews for NeurIPS and CoRL? I noticed an interesting pattern with mixed reviews in competitive venues: When it comes to clarity, the most critical reviewer is often correct. When it comes to novelty, it's the other way around.🤔Here is why... 1/🧵

1

34

Igor Gilitschenski

@igilitschenski

1 year

Besides developing new technology, I have always also been passionate about its societal impact and broader public policy. Thus, I am excited to have joined @TorontoSRI as a faculty affiliate and very much look forward to interdisciplinary exchange opportunities beyond CS.

2

0

32

Igor Gilitschenski

@igilitschenski

10 months

Paris, here we come…. 🎉 #ICCV2023

1

0

32

Igor Gilitschenski

@igilitschenski

8 months

Excited to share that our work on Object-centric learning with Diffusion Models has been accepted as a spotlight at NeurIPS! 💡🎉 Huge kudos to my student @Dazitu_616 for leading that work. It's been a great collaboration involving @JingyuHu16 , @WuyueLu_Ivy , and @animesh_garg .

Ziyi Wu

@Dazitu_616

8 months

1/ Excited to share our NeurIPS’23 Spotlight paper SlotDiffusion! Our work on diffusion-based object-centric learning enables unsupervised segmentation, visual generation, and downstream video prediction & VQA, all with one model! Project, paper, code:

3

19

124

2

6

32

Igor Gilitschenski

@igilitschenski

2 years

A @CVPR deadline wouldn't be the same without an @overleaf outage. Maybe a secret measure for enforcing work-life balance. Perfect timing for a coffee break. ☕️

2

0

32

Igor Gilitschenski

@igilitschenski

1 year

Congratulations to @rsiegwart and Daniela Rus for winning the "ICRA Most Influential Paper Award" and the "IEEE Robotics and Automation Award" respectively. 🎉 It is a privilege to have been part of your labs and I am excited to see your hard work rewarded.

1

0

32

Igor Gilitschenski

@igilitschenski

4 years

Join us today for our #RSS2020 Workshop on Interaction and Decision Making in Autonomous Driving. Looking forward to a fantastic set of speakers: @DorsaSadigh , @ancadianadragan , Alyssa Pierson, Changliu Liu, Maxim Dolgov, Yichuan Tang, @adnothing , and Shengbo Li. 1/2

1

4

29

Igor Gilitschenski

@igilitschenski

1 year

Preparing for #ICCV2023 the @CSProfKGD way. Picture obviously staged: No tablet display in use ever looks that clean.

1

31

Igor Gilitschenski

@igilitschenski

1 year

Starting the holiday season with hundreds of grad applications to review. With so many brilliant applicants, this feels every time like an almost impossible task.

0

30

Igor Gilitschenski

@igilitschenski

1 year

So cool to see multiple fellow roboticists and two @UofTCompSci colleagues among the @SloanFoundation Fellowship winners. Congrats @jimmybajimmyba , @sushnt , @lucacarlone1 , @Majumdar_Ani , @chelseabfinn , and @leto__jean . 🎉 Your work has been and continues to be inspiring.

4

0

29

Igor Gilitschenski

@igilitschenski

9 months

Together with @BurgnerKahrs , Lüder Kahrs, and @florian_shkurti , we enjoyed hosting a delegation from @BW__i , my home state in Germany. Great meeting the Minister of Science, Research, and Arts @OlschowskiPetra , @UniKonstanz ’s Katharina Holzinger, and the @GermanyinTO team.

0

1

29

Igor Gilitschenski

@igilitschenski

9 months

Huge congrats to @JMarakiii and @__wernerpe for getting your papers on geometry matching for grasping and multi-team racing accepted into @corl_conf ! 🎉 Shoutout to many collaborators at @UofTCompSci , @MIT_CSAIL , @GoogleDeepMind , and @ToyotaResearch ! Details coming soon!

0

1

29

Igor Gilitschenski

@igilitschenski

2 years

Today, I was asked to review a paper titled „Long-term couple relationships Stress, problems and coping processes in couple counselling.“ Robotics researchers are generalists and all that but still trying to figure out how to use my expertise here… 🤔

0

29

Igor Gilitschenski

@igilitschenski

2 years

Our collaborator @sanderryanm had no luck. @FrontierCare canceled flights and @FedEx didn’t deliver the poster on time. We still did it and he joined virtually to present our @l4dc2022 work. Shoutout to @yel_esen for all the help and to @CopyFactory for fast-tracked printing.

0

29

Igor Gilitschenski

@igilitschenski

3 years

Excited to share the CfP for the 4th Workshop on Robot Learning to be held at #NeurIPS2021 . 🦾🧠 Our focus this year is Self-Supervised and Lifelong learning. However, all contributions within the scope of robot learning are welcome. Instructions: 1/🧵

4th Robot Learning Workshop:Self-Supervised and Lifelong Learning

@NeurIPS 2021 14 December 2021

www.robot-learning.ml

1

4

28

Igor Gilitschenski

@igilitschenski

3 years

Second, knowing what and how to learn.📚 Having the right skillset can make all the difference between impossible and obvious. It's easy to waste time on learning something you don't need or being inefficient by not properly knowing regularly used tools. 3/5

1

2

26

Igor Gilitschenski

@igilitschenski

6 months

Amazing paper. IMO, creating dynamic learned scene representations is one of the key challenges for robust robot learning and validation.

Yue Wang

@yuewang314

6 months

Introducing EmerNeRF, our answer to the challenging dynamic NeRF in-the-wild problem. EmerNeRF is the best-ever project I've got involved in, led by our only @JiaweiYang118 (stay tuned for his even more impressive works), in collaboration with @NVIDIAAI colleagues @iamborisi …

5

30

215

1

0

27

Igor Gilitschenski

@igilitschenski

2 years

Imagine the Fast and the Furious without anyone actually being Furious.

Toyota Research Institute (TRI)

@ToyotaResearch

2 years

What if every driver could control their vehicle under the most extreme circumstances - just like a pro? For the first time ever, @ToyotaResearch has successfully programmed a vehicle to autonomously drift around obstacles on a closed track. 📺⤵️

53

525

974

1

2

27

Igor Gilitschenski

@igilitschenski

3 years

Excited to share our paper "GROUNDED: The Localizing Ground Penetrating Radar Evaluation Dataset" to be presented today at #RSS2021 . Paper: Website: 1/2

2

3

27

Igor Gilitschenski

@igilitschenski

1 year

Excited to share our work on building scalable Video Understanding benchmarks 📹📈 led by @agarwalaniket11 and @a1zhang . When joining my group @yash2kant told me about an idea he and @VishvakM were working on. To follow this idea, I had to learn about cricket first... 🏏 1/n

1

4

27

Igor Gilitschenski

@igilitschenski

2 years

📢📢📢 @UofTCompSci is hiring!📢📢📢 On the faculty job market? We are looking for 7(‼️) new colleagues 🧑‍🏫🧑‍🔬 in multiple areas of computer science 🧑‍💻❤️🇨🇦 including two open area calls 🔭. Reach out for a chat if you are at #ECCV2022 and check out:

Employment Opportunities — Department of Computer Science, University of Toronto

Are you looking for a thought-provoking and inventive career at a leading institution?

web.cs.toronto.edu

0

6

26

Igor Gilitschenski

@igilitschenski

7 months

That’s huge! Congrats @Sotiris_No , @IanWithanM , @rahul_gulve , @DaveLindell , and Kyros Kutulakos for bringing the #ICCV2023 Best Paper Award to @UofTCompSci !

Sotiris Nousias

@Sotiris_No

7 months

Excited to present passive ultra-wideband single-photon imaging at #ICCV2023 this week! We demonstrate imaging across timescales spanning 9+ orders of magnitude—for example, in one acquisition we can capture both a spinning fan and a propagating light pulse. (1/n)

6

35

211

0

2

27

Igor Gilitschenski

@igilitschenski

2 years

Dear airline and weather gods, first conference after pandemic is already exciting enough. Canceling my flight was not necessary. #ICRA2022

1

0

26

Igor Gilitschenski

@igilitschenski

2 years

Congrats @ashmrz10 ! I am very excited about this work. In some sense, this is also the first paper coming out of my lab.

Ashkan Mirzaei

@ashmrz10

2 years

Thanks @_akhaliq for sharing our #ECCV2022 work. We propose LaTeRF to extract 3D object representations from 2D input images with a minimal set of supervision; User clicks are used to remove the background/foreground, while a text prompt is utilized to resolve the occlusions.

1

16

78

1

2

25

Igor Gilitschenski

@igilitschenski

3 years

Today is election day in Germany. Probably the most remote election party: Fabian Parsch and I are celebrating @spdde and @OlafScholz in Toronto. We've met over 15 years ago while being active at @jusos . Now we are both colleagues at @UofT .

1

0

24

Igor Gilitschenski

@igilitschenski

1 year

Happy to share the third talk 📢 in preparation for the Scaling & Models Panel at the #NeurIPS2022 Workshop on Robot Learning. 🦾 @GoogleAI 's @hausman_k and @brian_ichter sharing their perspective on "Language as a Connective Tissue for Robotics"

Language as a Connective Tissue for Robotics

Karol Hausman and Brian Ichter will join us during the workshop (December 9), where we bring together experts with diverse perspectives to highlight the ways...

www.youtube.com

0

7

25

Igor Gilitschenski

@igilitschenski

2 years

„When will robots clean my house?“ 🧹is one of the most common questions for robotics researchers. 🦾🧑‍💻This task is hard and requires commonsense reasoning. In our #ECCV2022 work led by @yash2kant , we propose to use housekeeping as a new embodied AI 🧠 benchmark. Check it out!

Yash Kant

@yash2kant

2 years

🏠🧹Introducing Housekeep, a benchmark to evaluate commonsense reasoning in embodied AI agents. Appearing at #ECCV2022 ! Website: Paper: Data in colab: 🧵

3

22

84

0

4

25

Igor Gilitschenski

@igilitschenski

3 years

Third, creating an effective research process. 🧑‍💻💡🔥Research is stressful and there is usually no recipe for doing it well. But there are many aspects that can be easily influenced such as staying on top of literature, writing great papers, and creating synergies. 4/5

3

1

23

Igor Gilitschenski

@igilitschenski

4 years

Looking forward to an exciting new chapter in life. If you are interested in being part of my future group as a graduate student, please consider applying to @UofTCompSci 's CS graduate program: 4/4

Our Programs - Graduate — Department of Computer Science, University of Toronto

With over 250 top graduate students, we are one of the largest computer science graduate programs in the country.

web.cs.toronto.edu

1

2

21

Igor Gilitschenski

@igilitschenski

2 years

The talk by @NikolaiMatni addresses one of the most important questions in ML research “🤯🤯🤯 Why isn’t it working?🤯🤯🤯“

0

1

24

Igor Gilitschenski

@igilitschenski

6 months

Excited to share our paper "Dynamic Multi-Team Racing: Competitive Driving on 1/10-th Scale Vehicles via Learning in Simulation" (led by @__wernerpe & @timseyde ) that we will be presenting today at #CoRL2023 today. 1/n

1

6

23

Igor Gilitschenski

@igilitschenski

2 years

In today's morning sessions at @ieee_ras_icra , @xli417 will be presenting our work "Learning An Explainable Trajectory Generator Using The Automaton Generative Network (AGN)" Paper: 1/n

1

22

Igor Gilitschenski

@igilitschenski

3 years

LOL. I guess we all were involved in some of those.

Robot Operating System (ROS)

@rosorg

3 years

Types of robotics papers.

11

263

890

0

1

22

Igor Gilitschenski

@igilitschenski

2 years

With my timeline being filled with #CVPR2022 tweets, I feel almost like a rebel for going to @l4dc2022 this week. Looking forward to meeting fellow rebels at Stanford.

1

0

22

Igor Gilitschenski

@igilitschenski

4 years

Similarly, the work by @UofTRobotics has been a constant source of inspiration. Together with the amazing @animesh_garg , @BurgnerKahrs , and @florian_shkurti , I will be part of the young robotics cluster on the @UTM campus. 2/4

1

0

20

Igor Gilitschenski

@igilitschenski

2 years

Can we incorporate rules as priors in learning trajectory planners while also learning the rule structure? Check out "Learning An Explainable Trajectory Generator Using The Automaton Generative Network (AGN)" (accepted at ICRA/RA-L, led by @xli417 ) 1/

Learning An Explainable Trajectory Generator Using The Automaton Generative Network (AGN) | Toronto...

Symbolic reasoning is a key component for enabling practical use of data-driven planners in autonomous driving. In that context, deterministic finite state automata (DFA) are often used to formalize...

tisl.cs.toronto.edu

1

3

21

Igor Gilitschenski

@igilitschenski

1 year

Two of my grad students told me this week that they already feel the impact of aging. I don't even know what to say.

2

0

21

Igor Gilitschenski

@igilitschenski

2 years

Get ready for @NeurIPSConf with the #RobotLearning Workshop talk countdown starting with Jeannette Bohg ( @leto__jean ) and Rika Antonova ( @contactrika ) on "The Challenge of Robot Learning for Manipulation of Deformables" 1/2

Jeannette Bohg (Stanford) -- The Challenge of Robot Learning for...

Jeannette will join us during the workshop (14 December), where we bring together experts with diverse perspectives to highlight the ways current successes i...

www.youtube.com

1

6

21

Igor Gilitschenski

@igilitschenski

4 years

Super excited about having our workshop on "Interaction and Decision-Making in Autonomous-Driving" accepted at RSS 2020. We have a fantastic lineup of speakers including @ancadianadragan , @mayban , Changliu Liu, Alyssa Pierson, @adnothing , @DorsaSadigh , and Shengbo Li.

Rowan McAllister

@rowantmc

4 years

We're excited to announce the RSS 2020 Workshop on Interaction and Decision-Making in Autonomous-Driving! Organizers: @rowantmc , @panpan_1988 , @igilitschenski , and Daniela Rus. Call for papers:

1

3

11

1

0

19

Igor Gilitschenski

@igilitschenski

2 years

Enjoying @BurgnerKahrs ’ inspiring talk at @TEDxToronto about her path into Continuum Robotics.

1

2

19

Igor Gilitschenski

@igilitschenski

4 years

My amazing colleagues Lucas and Cenk (who stubbornly refuse to use Twitter) are presenting their fantastic work on sensitivity-based filter pruning at @iclr_conf today. Paper: Code:

1

2

17

Igor Gilitschenski

@igilitschenski

2 years

Join us once again for the Robot Learning Workshop at NeurIPS and show off what your robots have recently learned. This year, our focus is Trustworthy Robotics. However, contributions from all areas of robot learning are welcome.

Nathan Lambert

@natolambert

2 years

Who's working on the most exciting interdisciplinary work on robotics, AI, safety, fairness, robustness? Come to our workshop on Trustworthy Robotics at @NeurIPSConf Call for papers here: We have financial support for under-represented groups. 🧶/

3

5

21

0

2

20

Igor Gilitschenski

@igilitschenski

8 months

Heading to ICCV? 🛫Check out our work on "Reference-guided Controllable Inpainting". 🎮🧑‍🎨 Excited about editing reconstructions? Let's have a chat! @TristanAA97 , @CSProfKGD , and myself will be around. Our poster is in the 10:30am session next Friday.

Ashkan Mirzaei

@ashmrz10

8 months

🧵If you are attending ICCV🇫🇷🥐, make sure to check Tristan ( @TristanAA97 ) presenting our work, "Reference-guided Controllable Inpainting of Neural Radiance Fields". website: abs: Paper summary in the thread🧵.

1

6

47

0

2

20

Igor Gilitschenski

@igilitschenski

3 years

Although not yet started, my experience "at" @UofTCompSci 🇨🇦 has already been fantastic having (virtually) met many hugely supportive and brilliant colleagues. If you are on the cs job market 💼, consider applying to one of our faculty positions! 🎓🚀👩‍🏫👨‍🏫

U of T Department of Computer Science

@UofTCompSci

3 years

Join us at #UofT ! We are currently accepting applications for multiple tenure-stream #facultyjobs starting July 1, 2021. Learn more ➡️

0

19

26

0

20

Igor Gilitschenski

@igilitschenski

2 years

Boosted 💉💪

0

18

Igor Gilitschenski

@igilitschenski

4 years

Congrats @valentinp ! I really enjoyed reading your guys' paper.

Robotics: Science and Systems

@RoboticsSciSys

4 years

Best Student Paper Award was given to V. Peretroukhin, M. Giamou, D. M. Rosen, W. N. Greene, N. Roy, J. Kelly for “A Continuous Representation of Belief over SO(3) for Robust Rotation Learning with Uncertainty” - Congratulations!

1

2

24

1

3

19

Igor Gilitschenski

@igilitschenski

2 years

After a long break from debating, I am excited to be co-hosting the #RobotLearningDebate tonight jointly with @Ransalu at the @NeurIPSConf #RobotLearning Workshop. Join us for the second half of the workshop at 3:15pm PST and the debate at 6pm PST. More at

0

18