Anand Bhattad (@anand_bhattad)

Pinned

A

Anand Bhattad@anand_bhattad · Jun 2

I’m thrilled to share that I will be joining Johns Hopkins University’s Department of Computer Science (@JHUCompSci, @HopkinsDSAI) as an Assistant Professor this fall.

anand_bhattad's tweet image. I’m thrilled to share that I will be joining Johns Hopkins University’s Department of Computer Science (@JHUCompSci, @HopkinsDSAI) as an Assistant Professor this fall.

81

35

1.0K

72

85.0K

Pinned

Anand Bhattad Retweeted

S

Shivansh Patel@shivanshpatel35 · Jul 1

🚀 Introducing RIGVid: Robots Imitating Generated Videos! Robots can now perform complex tasks—pouring, wiping, mixing—just by imitating generated videos, purely zero-shot! No teleop. No OpenX/DROID/Ego4D. No videos of human demonstrations. Only AI generated video demos 🧵👇

3

32

143

76

39.0K

Pinned

A

Anand Bhattad@anand_bhattad · Jul 2

Research arc: ⏪ 2 yrs ago, we introduced VRB: learning from hours of human videos to cut down teleop (Gibson🙏) ▶️ Today, we explore a wilder path: robots deployed with no teleop, no human demos, no affordances. Just raw video generation magic 🙏 Day 1 of faculty life done! 😉…

SShivansh Patel@shivanshpatel35 · Jul 1

🚀 Introducing RIGVid: Robots Imitating Generated Videos! Robots can now perform complex tasks—pouring, wiping, mixing—just by imitating generated videos, purely zero-shot! No teleop. No OpenX/DROID/Ego4D. No videos of human demonstrations. Only AI generated video demos 🧵👇

3

29

133

32

23.0K

A

Anand Bhattad@anand_bhattad · Jul 14

Welcome to JHU CS! 💙

AAnand Bhattad@anand_bhattad · Jun 2

I’m thrilled to share that I will be joining Johns Hopkins University’s Department of Computer Science (@JHUCompSci, @HopkinsDSAI) as an Assistant Professor this fall.

0

2

7

1

1.0K

Anand Bhattad Retweeted

J

Jason Ren@RenZhongzheng · Jun 30

🥳 Excited to share that I’ll be joining the CS Department at UNC-Chapel Hill (@unccs @unc_ai_group) as an Assistant Professor starting Fall 2026! Before that, I’ll be working at Ai2 Prior (@allen_ai @Ai2Prior) and UW (@uwcse) on multimodal understanding and generation.

16

15

113

17

9.0K

Anand Bhattad Retweeted

K

Kostas Daniilidis@KostasPenn · Jun 29

Excellent material for a computer vision class (compute optical flow, human pose, focuse of expansion, ...) @CSProfKGD @anand_bhattad. All videos are downloadable. nytimes.com/interactive/20…

1

6

38

26

4.0K

A

Anand Bhattad@anand_bhattad · Jun 30

All slides from the #cvpr2025 (@CVPR) workshop "How to Stand Out in the Crowd?" are now available on our website: sites.google.com/view/standoutc…

AAnand Bhattad@anand_bhattad · Jun 10

In this #CVPR2025 edition of our community-building workshop series, we focus on supporting the growth of early-career researchers. Join us tomorrow (Jun 11) at 12:45 PM in Room 209 Schedule: sites.google.com/view/standoutc… We have an exciting lineup of invited talks and candid…

1

13

147

109

17.0K

Anand Bhattad Retweeted

R

Rishubh Parihar@RishubhParihar · Jun 29

🌟Excited to share our paper - “Zero Shot Depth-Aware Image Editing with Diffusion Models” is accepted at #ICCV2025!! paper - rishubhpar.github.io/DAEdit/main_pa… 🙌🏻 Kudos to amazing collaborators - @sachidanand8036, @rvbabuiisc Stay tuned for more details!

3

5

25

2

1.0K

Anand Bhattad Retweeted

T

TTIC@TTIC_Connect · Jun 27

We’re proud to announce three new tenure-track assistant professors joining TTIC in Fall 2026: Yossi Gandelsman (@YGandelsman), Will Merrill (@lambdaviking), and Nick Tomlin (@NickATomlin). Meet them here: buff.ly/JH1DFtT

3

9

137

10

23.0K

Anand Bhattad Retweeted

Y

Yutong Bai@YutongBAI1002 · Jun 27

What would a World Model look like if we start from a real embodied agent acting in the real world? It has to have: 1) A real, physically grounded and complex action space—not just abstract control signals. 2) Diverse, real-life scenarios and activities. Or in short: It has to…

32

123

502

323

150.0K

Anand Bhattad Retweeted

J

Jia-Bin Huang@jbhuang0604 · Jun 24

Why More Researchers Should be Content Creators Just trying something new! I recorded one of my recent talks, sharing what I learned from starting as a small content creator. youtu.be/0W_7tJtGcMI We all benefit when there are more content creators!

8

29

196

88

22.0K

Anand Bhattad Retweeted

U

UniLight Workshop @ICCV25@unilightws · Jun 17

#CVPR2025 is a wrap! Amazing contributions on lighting-related tasks this year. Now it’s time to look ahead to #ICCV2025 in beautiful Hawai’i. Let’s keep the momentum going and join us to explore and discuss how to evaluate lighting across diverse tasks!

0

8

13

0

8.0K

A

Anand Bhattad@anand_bhattad · Jun 17

Lighting hasn’t received as much attention as 3D geometry in the vision community, but that’s changing. A wave of exciting papers in recent venues (#ICLR2025, #SIGGRAPH2025 and #CVPR2025) reflects growing momentum, and the rise is just beginning. But before the field scales…

UUniLight Workshop @ICCV25@unilightws · Jun 17

#CVPR2025 is a wrap! Amazing contributions on lighting-related tasks this year. Now it’s time to look ahead to #ICCV2025 in beautiful Hawai’i. Let’s keep the momentum going and join us to explore and discuss how to evaluate lighting across diverse tasks!

1

7

35

3

6.0K

Anand Bhattad Retweeted

T

Tianmin Shu@tianminshu · Jun 14

🚀 Excited to introduce SimWorld: an embodied simulator for infinite photorealistic world generation 🏙️ populated with diverse agents 🤖 If you are at #CVPR2025, come check out the live demo 👇 Jun 14, 12:00-1:00 pm at JHU booth, ExHall B Jun 15, 10:30 am-12:30 pm, #7, ExHall B

6

42

208

71

27.0K

A

Anand Bhattad@anand_bhattad · Jun 14

Highly recommend checking out the Parthenon if you’re in Nashville for #CVPR2025. It’s an exact 1:1 replica of the original in Athens.

anand_bhattad's tweet image. Highly recommend checking out the Parthenon if you’re in Nashville for #CVPR2025. It’s an exact 1:1 replica of the original in Athens.

3

17

2

5.0K

A

Anand Bhattad@anand_bhattad · Jun 13

Ready to go!! Poster #26 at #CVPR2025 Sadly, @RealXiaoyanXing’s visitor visa was canceled last minute, and he couldn’t make it. This work is a result of his hard work and effort. Code: github.com/xyxingx/LumiNet Project: luminet-relight.github.io Paper: arxiv.org/abs/2412.00177

AAnand Bhattad@anand_bhattad · Dec 5

[1/7] I'm super stoked to share LumiNet! 🎉 💡LumiNet combines our latent intrinsic image representations with a powerful generative image model. It lets us relight complex indoor images by transferring lighting from one image to another! Most importantly, it is completely…

1

3

10

1

1.0K

A

Anand Bhattad@anand_bhattad · Jun 13

Latent Intrinsics are powerful representations. When smartly combined with diffusion-based generators, they enable compelling image relighting without any labeled data or semantics. Catch our LumiNet poster tomorrow (Jun 13) at #CVPR2025 in the first poster session at 10:30 AM.

AAnand Bhattad@anand_bhattad · Dec 5

[1/7] I'm super stoked to share LumiNet! 🎉 💡LumiNet combines our latent intrinsic image representations with a powerful generative image model. It lets us relight complex indoor images by transferring lighting from one image to another! Most importantly, it is completely…

0

2

14

2

1.0K

A

Anand Bhattad@anand_bhattad · Jun 13

Celebrating @jon_barron’s birthday at #CVPR2025 🎉🎉🥳

T@ ·

0

40

6

3.0K

A

Anand Bhattad@anand_bhattad · Jun 12

My amazing PhD advisor kicked things off with a roaring “Generators are DUMB!” Talking about some of Vaibhav’s exciting PhD work, and a project we’ve been quietly working on for over two years now! #CVPR2025

CCongyue Deng@CongyueD · Jun 12

And finally, talk by the great David Forsyth!

0

11

1

1.0K

A

Anand Bhattad@anand_bhattad · Jun 12

Talk by @KostasPenn happening now!

HHanwen Jiang@hanwenjiang1 · May 8

🔍 3D is not just pixels—we care about geometry, physics, topology, and functions. But how to balance these inductive biases with scalable learning? 👀 Join us at Ind3D workshop @CVPR (June 12, afternoon) for discussions on the future of 3D models! 🌐 ind3dworkshop.github.io/cvpr2025

0

4

28

2

3.0K