Kunal Gupta

Ph.D. student @ucsd_cse @ViLabUCSD working on 3D Vision & Inverse Rendering.

[Jon Barron @jon_barron]

One of the more interesting and thought provoking research papers I've seen in a while. A system for reading and reimplementing NeRF papers, and it seems to work very well. Pretty easy to extrapolate out from here to what CVPR 2027 papers will look like. https://t.co/gokzG27mIT

[Bing Xu @_bingxu]

What a pleasant big surprise. Free to share a $1M secret to get a best paper award: to get Iliyan presenting the paper. @EGSympRendering @iliyang. Congrats to @tzumaoli, Trevor and Ravi.

[AK @_akhaliq]

OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation

abs: https://t.co/FxvbuvS5Le
project page: https://t.co/KLtI3wVDwr

[Sanjay Subramanian @sanjayssub]

New paper at #acl2023nlp!
"Modular Visual Question Answering via Code Generation"
With @medhini_n @kushaltk1248 @KevinYa33964384 @NagraniArsha @CordeliaSchmid @andyzengtweets @trevordarrell Dan Klein (@berkeley_ai/@GoogleAI)!
📜 https://t.co/O4jJDc4prj
💻https://t.co/kwGyYMJ8le

[Kunal Gupta @KunalMGupta]

@AryaArshia @ucsd_cse @MSFTResearch Welcome to the program!

[Kevin Lin @linkevin0]

Large language models (LLMs) can readily convert language instructions into high-level plans.

However, should we trust robots to execute these plans without verifying that they actually satisfy the instructions and are feasible in the real world?
https://t.co/2lv5NtkXsC

[Danish Pruthi @danish037]

I am looking for a few PhD/MTech (research) students for my lab at IISc Bangalore.

The institute-wide applications for these programs are now open (deadline: March, 23). Please email me if you have any questions.

https://t.co/Y4vSoU7FLI

[Kunal Gupta @KunalMGupta]

@danish037 Heartiest Congratulations!!! Eager to see all the great work from your upcoming lab at IISc :)

[Morteza Mardani @MardaniMorteza]

We are looking for highly motivated #ML #AI Ph.D. students to work with us at NVIDIA Research as summer #interns next year. We encourage applicants with experience in generative modeling in one of these domains:

[Berkeley Faculty Association @FacultyBerkeley]

Long thread on why @UniCalifornia Senate faculty should join the @uc_faculty #UCFacultySolidarity rallies on their campus at noon tomorrow to support #UAWonStrike #FairUCNow @uaw2865 @sruuaw @UAW5810

[Student Researchers United-UAW @sruuaw]

UC wants to limit and control our earnings by calling some of it “student support,” which would block part of our pay from being covered by our union contract. Watch this video and read 🧵 for more about why our total earnings must be included in our contract! (1/3) #UAWonStrike

[Matthias Niessner @MattNiessner]

(1/n)
Key to successful projects in Deep Learning are fast turnaround times of experiments.

For large models, training often takes several days or even weeks, and it might need countless runs to find hyperparameters that yield good results.

How to get things fast? A thread🧵

[Simon LC @simonlc_]

We're excited to present a differentiable physics engine for NeRF-represented objects! We augment object-centric NeRFs with dynamical properties (e.g. friction properties).
paper: https://t.co/j25HRsSwvk
video: https://t.co/h1tg9JVMpD

[Manmohan Chandraker @manu_chandraker]

Delighted to receive the Best Paper Honorable Mention @eccvconf #ECCV2022 for Neural Implicit Evolution, together with @ishit_mehta and Ravi Ramamoorthi @ucsd_cse @UCSanDiego @ViLabUCSD

Code and webpage: https://t.co/Oeptywueon

[Neural Fields @neural_fields]

Neural Shape Deformation Priors (NeurIPS 2022)

Authors: Jiapeng Tang, Lev Markhasin, Bi Wang, Justus Thies, Matthias Nießner

https://t.co/tNHcCKJ19E

#neuralfieldsoftheday

[Sergey Tulyakov @SergeyTulyakov]

We have started accepting Snap Research 2022 Fellowship applications! We will award up to 10 fellowships. If you're doing highly impactful research relevant to Snap, we encourage you to apply. The deadline is Oct 10. Apply here:
https://t.co/jIMySVzqYi

[AK @_akhaliq]

Immersive Real World through Deep Billboards
abs: https://t.co/Am57HW8Y5c
project page: https://t.co/N05rwRWVDx

[Sergey Tulyakov @SergeyTulyakov]

How to build relightable neural models of objects from internet images? Check our #SIGGRAPH2022 NeROIC paper. It does high quality material decomposition, making it possible to insert such objects into new scenes from internet images!

[Kunal Gupta @KunalMGupta]

Check out our recent work at #SIGGRAPH2022

[Neural Fields @neural_fields]

Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes (SIGGRAPH 2022)

Authors: Noam Aigerman, Kunal Gupta, Vladimir G. Kim, Siddhartha Chaudhuri, Jun Saito, Thibault Groueix

https://t.co/kdPGF8SXcS

#neuralfieldsoftheday

[Neural Fields @neural_fields]

Neural Density-Distance Fields (ECCV 2022)

Authors: Itsuki Ueda, Yoshihiro Fukuhara, Hirokatsu Kataoka, Hiroaki Aizawa, Hidehiko Shishido, Itaru Kitahara

https://t.co/YiicWmOvNd

#neuralfieldsoftheday