Agrim Gupta @agrimgupta92 Twitter profile

Pinned Tweet

Agrim Gupta

5 months

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

55

267

1K

Last Seen Profiles

@techpolicyinst

@starsowing

@thomazing

@wolfyxoxobieber

@TheRealDarryl_

@ikatukhuingonga

@iamjordanlive

@ShopeePH

@ItzUntaa

@zuppu11

@dbkappel

@DmansJNJ

@hunter_hi12

@CBruswan

@Jakelan00578004

@Aldonie_

@MehdMends

@atjotho

@diva_seto

@JuggieDevilz7

@fowler_aisling

@hyukacentral

@winrinawinning

@timbhealey

@golightly1308

@LKALOSIS

@GoberNorte

@alyshia_2001

@MyCreativeOwls

@Boltksa

@all300_

@KhionYohann

@eto_cp

@FeministGreens

@fxta09

@mo8167312

Agrim Gupta

@agrimgupta92

1 year

How should we leverage internet videos for learning visual correspondence? In our latest work we introduce SiamMAE: Siamese Masked Autoencoders for self-supervised representation learning from videos. web: paper: 👇🧵

16

122

484

Agrim Gupta

@agrimgupta92

5 years

We have released LVIS v0.5 dataset for long tail object detection with 1200+ categories and 700k+ high quality instance segmentation masks Paper: Website: API: with Ross Girshick and Piotr Dollar @facebookai

GitHub - lvis-dataset/lvis-api: Python API for LVIS Dataset

Python API for LVIS Dataset. Contribute to lvis-dataset/lvis-api development by creating an account on GitHub.

github.com

2

91

287

Agrim Gupta

@agrimgupta92

2 years

1/ Can we replicate the success of large scale pre-training --> task specific fine tuning for robotics? This is hard as robots have different act/obs space, morphology and learning speed! We introduce MetaMorph🧵👇 Paper: Code:

3

46

262

Agrim Gupta

@agrimgupta92

3 years

Excited to share our work on understanding the relationship between environmental complexity, evolved morphology, and the learnability of intelligent control. Paper: Video: w/ @silviocinguetta @SuryaGanguli @drfeifei

8

44

208

Agrim Gupta

@agrimgupta92

2 years

1/ Can we build video prediction models by masked visual pretraining via Transformer? We present MaskViT: a simple & parameter efficient method to generate high res. videos in real time. Paper: Web: 🧵👇

7

34

171

Agrim Gupta

@agrimgupta92

3 years

1/ Excited to share that our work on Deep Evolutionary Reinforcement Learning (DERL): a framework for large scale evolution of embodied agents in physically realistic environments is now published in @NatureComms Paper Video

Stanford researchers evolve embodied AI agents

A team of researchers at Stanford wondered: Does embodiment matter for the evolution of intelligence? And if so, how might computer scientists make use of em...

www.youtube.com

3

25

109

Agrim Gupta

@agrimgupta92

5 months

6/ Finally, our model can be used to generate videos with consistent 3D camera motion.

3

16

96

Agrim Gupta

@agrimgupta92

5 months

2/ website: Our approach has two key design decisions. First, we use a causal encoder to compress images and videos in a shared latent space.

2

14

72

Agrim Gupta

@agrimgupta92

5 months

7/ This work was done at @StanfordAILab , @StanfordSVL , @GoogleAI , @Google with amazing collaborators @LijunYu0 , @kihyuk_sohn , @laoreja001 , @MeeraHahn , @drfeifei , @irrfaan , @roadjiang , @jlezama

4

3

50

Agrim Gupta

@agrimgupta92

5 months

5/ We can also use our model to animate any image.

1

5

47

Agrim Gupta

@agrimgupta92

5 months

4/ Our model can generate photorealistic, temporally consistent motion from natural language prompts.

1

4

46

Agrim Gupta

@agrimgupta92

5 years

First LVIS Challenge @ ICCV 2019 is now live. We have updated the paper to include baselines and analysis. Paper: Challenge: with Ross Girshick and Piotr Dollar @facebookai

LVIS: A Dataset for Large Vocabulary Instance Segmentation

Progress on object detection is enabled by datasets that focus the research community's attention on open challenges. This process led us from simple images to complex scenes and from bounding...

arxiv.org

0

19

43

Agrim Gupta

@agrimgupta92

11 months

Foundation models can dexterously manipulate the world of bits but what about the world of atoms? Excited to introduce 🤖RoboCat🐈, the first foundation agent: ✅ multi-embodiment ✅ self-improves ✅ vision to action ✅ dexterous & generalist: 100s of tasks + objects How? 👇🧵

Google DeepMind

@GoogleDeepMind

11 months

Introducing RoboCat, a new AI model designed to operate multiple robots. 🤖 It learns to solve new tasks on different robotic arms with as few as 100 demonstrations - and improves skills from self-generated training data. Find out more:

45

281

1K

2

12

42

Agrim Gupta

@agrimgupta92

5 years

Dataset are extremely hard to get right and often under appreciated. I can only try to imagine the tremendous foresight and hard-work which went into making ImageNet. It's mind boggling that @drfeifei was able to envision where the community should go as early as 2006-07! #CVPR19

1

2

41

Agrim Gupta

@agrimgupta92

6 years

We have released the code our #CVPR2018 paper on predicting socially acceptable trajectories using GANs with @jcjohnss @drfeifei @silviocinguetta @AlexAlahi . Paper: Code:

GitHub - agrimgupta92/sgan: Code for "Social GAN: Socially Acceptable Trajectories with Generative...

Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018 - agrimgupta92/sgan

github.com

0

14

38

Agrim Gupta

@agrimgupta92

4 months

A great thread summarizing the state of video generation in 2023. 2024 looks promising!

Justine Moore

@venturetwins

4 months

2023 was a breakout year for AI video. In January, there were no public text-to-video models. Now, there are dozens of video gen products and millions of users. A recap of the biggest developments + companies to watch 👇

25

173

647

0

6

39

Agrim Gupta

@agrimgupta92

5 months

3/ Second, for memory and training efficiency, we use a window attention based transformer architecture for joint spatial and temporal generative modeling in latent space.

2

5

32

Agrim Gupta

@agrimgupta92

5 months

Thanks @_akhaliq for sharing!

AK

@_akhaliq

5 months

Photorealistic Video Generation with Diffusion Models paper: present W.A.L.T, a transformer-based approach for photorealistic video generation via diffusion modeling. Our approach has two key design decisions. First, we use a causal encoder to jointly…

11

186

776

1

27

Agrim Gupta

@agrimgupta92

3 years

We are excited to announce the LVIS 2021 challenge @ICCV_2021 . This year we introduce new metrics to better measure progress made by our algorithms in the challenging regime of long tail object recognition. Checkout the challenge hosted @eval_ai

AI at Meta

@AIatMeta

3 years

The LVIS 2021 challenge is live! It uses our #dataset that contains 1203 object categories, 160k images, and 2M instance annotations. The deadline to submit your challenge entry is September 27. Learn more about LVIS and the challenge here:

3

34

142

0

3

27

Agrim Gupta

@agrimgupta92

10 months

LLMs are extremely powerful and are very good at writing code. However, they lack visual grounding. Exciting work led by @wenlong_huang shows how we can combine LLMs + VLMs for robotic manipulation.

Wenlong Huang

@wenlong_huang

10 months

How to harness foundation models for *generalization in the wild* in robot manipulation? Introducing VoxPoser: use LLM+VLM to label affordances and constraints directly in 3D perceptual space for zero-shot robot manipulation in the real world! 🌐 🧵👇

10

141

582

0

10

25

Agrim Gupta

@agrimgupta92

1 year

Latest project from friends at @NVIDIAAI : Voyager. An AI agent based on GPT-4 that plays Minecraft and keeps learning new skills. Congrats @guanzhi_wang , @DrJimFan and the whole team!

Jim Fan

@DrJimFan

1 year

What if we set GPT-4 free in Minecraft? ⛏️ I’m excited to announce Voyager, the first lifelong learning agent that plays Minecraft purely in-context. Voyager continuously improves itself by writing, refining, committing, and retrieving *code* from a skill library. GPT-4 unlocks…

365

2K

9K

2

4

22

Agrim Gupta

@agrimgupta92

3 years

Great use of AI for video editing. Dynamic ad creation using @Rephrase_AI + hyper local targeting based on pincodes of users = Having one of the most popular Bollywood star @iamsrk being a brand ambassador for your local business! Video:

0

6

18

Agrim Gupta

@agrimgupta92

5 years

Congratulations @ai_habitat for best paper nomination @ICCV19 . Work led by FAIR habitat team @facebookai

0

18

Agrim Gupta

@agrimgupta92

2 years

Thanks a lot @techreview and @strwbilly for inviting me to share our latest work on evolving agent morphologies and learning universal controllers! Joint work with my wonderful collaborators @drfeifei @SuryaGanguli @silviocinguetta @DrJimFan

MIT Technology Review

@techreview

2 years

First up: @agrimgupta92 from Stanford is interested in how the form of a machine changes its ability to learn, shifting the focus away from learning algorithms operating by themselves and onto learning combined with a kind of bodily evolution. #EmTechDigital

1

2

9

0

6

13

Agrim Gupta

@agrimgupta92

5 years

ICCV 2019 by numbers: 10k authors, 59 countries, 7.5k attendees and 1k accepted papers. @ICCV19

0

14

Agrim Gupta

@agrimgupta92

2 years

2/ MetaMorph is based on the insight that robot morphology is just another modality on which we can condition the output of a Transformer. We process an arbitrary robot by creating a 1D sequence of tokens corresponding to depth first traversal of its kinematic tree.

1

11

Agrim Gupta

@agrimgupta92

5 years

People say datasets are opium for AI researchers. I like the original analogy better. Data is Oil. Both are unsustainable in the long run but nothing else works right now.

1

0

12

Agrim Gupta

@agrimgupta92

5 years

Came across this discussion from 1984: More than 35 years have passed but it still is reads the same if you just replace expert systems by deep learning.

0

11

Agrim Gupta

@agrimgupta92

5 years

VQA (V+L) was subject to much debate after Alyosha's talk in #CVPR2019 . Even though I agree with the sentiment that vision is just not there yet I don't think discarding an entire field is wise. The progress VQA benchmark has enabled is undeniable.

Devi Parikh

@deviparikh

5 years

VQA performance on a standard benchmark (VQA v2 dataset) has gone up 20% (absolute) in the last ~4 years. You can really tell the difference when interacting with these models! Check the VQA demo out here: .

2

16

49

0

1

11

Agrim Gupta

@agrimgupta92

1 year

5/ By predicting a majority fraction of the future frame, SiamMAE learns the notion of object boundaries. This emergent ability is unique and surprising as no loss function operates on the [CLS] token in SiamMAE. We're excited to explore this further!

1

11

Agrim Gupta

@agrimgupta92

3 years

3/ Large scale simulations allow us to ask interesting scientific questions like what is the relationship between morphological intelligence and environmental complexity. We find that agents evolved in more complex environments are able to learn new tasks faster and better.

1

11

Agrim Gupta

@agrimgupta92

1 year

2/ First, we note that images are (approximately) isotropic. However, the temporal dimension is special and not all spatio-temporal orientations are equally likely. Hence, symmetric masking across temporal dimension might be sub-optimal!

1

10

Agrim Gupta

@agrimgupta92

5 years

pycls is a high-quality, high-performance codebase for image classification research. It can also serve as a great starting point for projects not necessarily on image classification. Code: by @facebookai

0

2

10

Agrim Gupta

@agrimgupta92

3 years

Very accessible and fun conversation about our work on evolving embodied intelligence. Thanks @a16z @lr_bio @vijaypande for hosting. Joint work with @silviocinguetta @SuryaGanguli @drfeifei

Surya Ganguli

@SuryaGanguli

3 years

Was fun doing a podcast at @a16z with @drfeifei @vijaypande and @lr_bio on evolving embodied intelligence!

1

22

75

0

2

10

Agrim Gupta

@agrimgupta92

4 years

1/2 We released LVIS v1.0 dataset for long tail object detection with 1200+ categories and 2M+ high quality instance seg masks on 160k images Paper: API: Website: with Ross and Piotr #CVPR2020 @facebookai

GitHub - lvis-dataset/lvis-api: Python API for LVIS Dataset

Python API for LVIS Dataset. Contribute to lvis-dataset/lvis-api development by creating an account on GitHub.

github.com

1

0

10

Agrim Gupta

@agrimgupta92

2 years

Task specification is a challenging problem in robotics. We introduce VIMA: A transformer based model which can perform *any* task as specified by multimodal prompts. Intuitive & multimodal task interface is going to be essential for useful embodied agents.

Jim Fan

@DrJimFan

2 years

We trained a transformer called VIMA that ingests *multimodal* prompt and outputs controls for a robot arm. A single agent is able to solve visual goal, one-shot imitation from video, novel concept grounding, visual constraint, etc. Strong scaling with model capacity and data!🧵

18

147

870

0

3

10

Agrim Gupta

@agrimgupta92

8 months

Great work showcasing the power of sim2real and dexterous manipulation! Congrats @chenwang_j and team.

Chen Wang

@chenwang_j

8 months

How to chain multiple dexterous skills to tackle complex long-horizon manipulation tasks? Imagine retrieving a LEGO block from a pile, rotating it in-hand, and inserting it at the desired location to build a structure. Introducing our new work - Sequential Dexterity 🧵👇

27

92

473

1

9

Agrim Gupta

@agrimgupta92

2 years

@ilyasut “It is slothful not to compress your thoughts.” Winston Churchill

0

1

8

Agrim Gupta

@agrimgupta92

6 months

Evaluation of modern generative models is challenging. Check out HEIM: amazing work led by @tonyh_lee @michiyasunaga @chenlin_meng . A new benchmark for evaluating text to image generation models 🧵👇

Michi Yasunaga

@michiyasunaga

6 months

Text-to-image models like DALL-E create stunning images. Their widespread use urges transparent evaluation of their capabilities and risks. 📣 We introduce HEIM: a benchmark for holistic evaluation of text-to-image models (in #NeurIPS2023 Datasets) [1/n]

3

57

177

0

2

9

Agrim Gupta

@agrimgupta92

3 years

6/ ecological niche but also enable efficient multi task learning. This is joint work with @drfeifei @SuryaGanguli , @silviocinguetta at @StanfordBrain , @StanfordSVL , @StanfordHAI and published in @NaturePortfolio , @NatureComms

1

7

Agrim Gupta

@agrimgupta92

3 years

7/ Summary of our research can be found here: Code:

GitHub - agrimgupta92/derl: Code for "Embodied Intelligence via Learning and Evolution", Gupta et...

Code for "Embodied Intelligence via Learning and Evolution", Gupta et al, Nature Communications - agrimgupta92/derl

github.com

0

1

7

Agrim Gupta

@agrimgupta92

1 year

3/ We randomly select a pair of frames from videos and use an asymmetric masking strategy: mask a high portion of the future frame (95%) and keep the past frame intact (0%). Frames are processed independently via an encoder and future masked patches are predicted via a decoder.

1

7

Agrim Gupta

@agrimgupta92

3 years

4/ Moreover, we observe a morphological Baldwin effect, where morphologies rapidly evolve over a few generations to reduce the sample complexity of reinforcement learning, cutting learning times in half in just 10 generations!

1

2

7

Agrim Gupta

@agrimgupta92

5 months

Amazing results on real world humanoid locomotion using RL! Congrats @ir413

Ilija Radosavovic

@ir413

5 months

we have trained a humanoid transformer with large-scale reinforcement learning in simulation and deployed it to the real world zero-shot

95

259

2K

0

6

Agrim Gupta

@agrimgupta92

3 years

5/ We find a mechanistic underpinning for both the morphological Baldwin effect and the emergence of embodied intelligence. DERL finds morphologies which are energy efficient and highly stable which affords the agents the ability to not only survive in their...

1

6

Agrim Gupta

@agrimgupta92

5 years

People often want to work with the best people in a field. I think if life is like a race then it make sense to work with people who are just ahead of you, splitstream only happens when you are just behind.

0

1

6

Agrim Gupta

@agrimgupta92

1 year

6/6 This is joint work with @jiajunwu_cs , @jiadeng and @drfeifei . Work done at @StanfordAILab , @StanfordSVL and supported by @StanfordHAI .

1

6

Agrim Gupta

@agrimgupta92

1 year

4/ MAE features generally require finetuning and perform poorly in zero-shot settings. Asymmetric masking, siamese encoder and our decoder design fixes this. SiamMAE features can be used zero-shot and outperform state-of-the-art self-supervised methods in multiple tasks.

1

6

Agrim Gupta

@agrimgupta92

2 years

4/ Thanks to iterative decoding, we can now use MaskViT for planning on real robots. In fact our video prediction is up to 512x faster than autoregressive video prediction.

1

0

6

Agrim Gupta

@agrimgupta92

5 years

Came across the YouTube channel of @Lux_Capital . Some really cool startups are being backed by them. A key difference I noticed in their portfolio was absence of Uber for X or Amazon for Y type startups. Really refreshing.

1

0

6

Agrim Gupta

@agrimgupta92

5 years

This is great! Almost all computer vision dataset depend on flicker. This trend which started with PASCAL was later followed by ImageNet, COCO etc. Finally we will have some thing which is not only a different type of image distribution but hopefully not too North America focused

Michelle Greene

@MGreenePhD

5 years

Big news! With help from the @NSF , some terrific colleagues ( @neuroMDL @bjbalas and Paul MacNeilage) and I are about to start a journey creating the Visual Experience Database: a first-person video database that will characterize how the world actually looks. 1/

21

39

223

1

0

6

Agrim Gupta

@agrimgupta92

3 years

1/ How do current advances in transformer architectures and representation learning transfer to the challenging setting of long tail instance segmentation? Are we close to detecting 1200+ categories? Checkout LVIS Challenge Workshop video:

1

6

Agrim Gupta

@agrimgupta92

4 years

My pior on what AGI stands for has been updated from Artificial General Intelligence --> Adjusted Gross Income. #tax2020

0

4

Agrim Gupta

@agrimgupta92

6 months

Amazing work! Congratulations.

Sumith Kulal

@sumith1896

6 months

Super excited to announce the release of Stable Video Diffusion (SVD) -- the first set of video models in the Stable Diffusion series. To start with, we release 14-frame (SVD) and 25-frame image-to-video (SVD-XT) models. The code/weights are already out! SVD:…

7

43

307

1

0

5

Agrim Gupta

@agrimgupta92

2 years

2/ Our approach is based on two simple design decisions. First, for memory and training efficiency, we use two types of window attention: spatial and spatiotemporal. We find that this simple de-coupling greatly improves the training speed without sacrificing quality.

1

0

5

Agrim Gupta

@agrimgupta92

1 year

@johnowhitaker Non-autoregressive decoding has shown great results with mask-predict in NLP, MaskGIT in images , and MaskViT in videos . The key idea is iterative refinement!

1

0

5

Agrim Gupta

@agrimgupta92

3 years

2/ DERL closely mimics the intertwined processes of evolution and learning and creates embodied agents exploit the passive physical dynamics of agent-environment interactions to survive in their evolutionary environment

1

5

Agrim Gupta

@agrimgupta92

2 years

5/ Finally, we provide a mechanistic explanation of how MetaMorph is able to control 1000s of morphologies. MetaMorph simplifies the control problem by learning to activate different motor synergies depending on the input morphology!

1

4

Agrim Gupta

@agrimgupta92

2 years

4/ Pre-trained controller can zero shot generalize to novel task and morphology combinations. Fine tuning our pre-trained controller is upto 3x more sample efficient than training from scratch on novel tasks.

1

0

4

Agrim Gupta

@agrimgupta92

3 months

compute + data + transformer + details = magic! congratulations @_tim_brooks & @billpeeb on sora!

1

0

6

Agrim Gupta

@agrimgupta92

3 years

Are you looking for more realistic and challenging environments to train your robots? Would you one day like a robot which can free you from household chores? Wondering how current RL algorithms perform in this challenging setting? Come join us at #ICCV2021

Roberto @ICRA24

@RobobertoMM

3 years

#ICCV2021 Join us this Sunday Oct 17 13-18 EDT @ BEHAVIOR Workshop: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments. We feature 7 world-renowned speakers in CV, embodied AI, and robotics: @leto__jean @chelseabfinn @hyogweon & more

1

14

36

1

5

Agrim Gupta

@agrimgupta92

5 years

1/ You don't need if you are interested in ML engeering roles. If you care about doing independent research it is almost impossible now to get that freedom at a company without a PhD. @chipro

Chip Huyen

@chipro

5 years

Can we say once and for all that you DON'T need MS/PhD to do machine learning? If you're interested in a company, build up your portfolio and apply (or get people to refer you)! No tech company would pass up someone who has won Kaggle competitions or amazing GitHub repos.

20

49

255

1

0

5

Agrim Gupta

@agrimgupta92

4 years

I have a joke about human behaviour prediction but it's anti-social.

0

4

Agrim Gupta

@agrimgupta92

1 year

What should we learn from videos to accelerate robot learning? Key idea: learn high level planning from in domain human videos and low level skills from robot demonstrations. Really impressive results. Congrats @chenwang_j and team!

Chen Wang

@chenwang_j

1 year

How to teach robots to perform long-horizon tasks efficiently and robustly🦾? Introducing MimicPlay - an imitation learning algorithm that uses "cheap human play data". Our approach unlocks both real-time planning through raw perception and strong robustness to disturbances!🧵👇

20

144

742

0

4

Agrim Gupta

@agrimgupta92

2 years

This is joint work with @stephentian_ , @zhang_yunzhi , @jiajunwu_cs , @RobobertoMM and @drfeifei .

0

4

Agrim Gupta

@agrimgupta92

2 years

3/ Second, during training, we mask a variable percentage of tokens instead of a fixed mask ratio. For inference, MaskViT generates all tokens via iterative refinement where we incrementally decrease the masking ratio following a mask scheduling function.

1

0

4

Agrim Gupta

@agrimgupta92

5 years

2/ It was a bit better in the early days when you had less people and the companies were still trying to figure out the right structure of the research labs.

0

1

4

Agrim Gupta

@agrimgupta92

5 years

When we were working on modelling human behavior for social navigation in early 2017 we were not satisfied with the available datasets. Check the new datset from @StanfordSVL

Silvio Savarese

@silviocinguetta

5 years

New benchmark for social robot navigation in crowed environments is available at . This is the largest dataset up-to-date!

0

5

12

0

1

3

Agrim Gupta

@agrimgupta92

2 years

This is joint work with @DrJimFan , @SuryaGanguli and @drfeifei @StanfordAILab @StanfordSVL

0

3

Agrim Gupta

@agrimgupta92

5 years

Of course it would not have been possible without an amazing group of people who shared the vision Jia Deng @RichardSocher @lijiali_vision Kai Li and made it possible.

0

3

Agrim Gupta

@agrimgupta92

2 years

Every day we have a new LLM paper but web search still sucks! Having trouble answering simple questions in 2022. Interestingly 4th link does have the correct age highlighted 🤷‍♂️. Also checked @YouSearchEngine same failure mode :/ Hopefully LLMs disrupt search soon!

0

3

Agrim Gupta

@agrimgupta92

5 years

@ai_habitat @facebookai @apsdehal

0

3

Agrim Gupta

@agrimgupta92

3 months

@jeffclune Flipbook animation of images on the bottom right?

1

0

2

Agrim Gupta

@agrimgupta92

2 years

3/ Our pre-trained policy zero-shot generalizes to 1000s of variations in dynamics and kinematic parameters and even completely unseen morphologies. This graph below shows zero shot performance 👇

1

0

2

Agrim Gupta

@agrimgupta92

5 years

@deviparikh @DhruvBatraDB @ICatGT @gtcomputing @mlatgt Congratulations!

1

0

3

Agrim Gupta

@agrimgupta92

2 years

🤯🤯

Jonathan Ho

@hojonathanho

2 years

Excited to announce Imagen Video, our new text-conditioned video diffusion model that generates 1280x768 24fps HD videos! #ImagenVideo Work w/ @wchan212 @Chitwan_Saharia @jaywhang_ @RuiqiGao @agritsenko @dpkingma @poolio @mo_norouzi @fleet_dj @TimSalimans

58

734

3K

0

3

Agrim Gupta

@agrimgupta92

6 years

@dog_feelings Would be great when you retweet something twitter could show: Thoughts of Dog woofed :)

0

2

Agrim Gupta

@agrimgupta92

3 years

@animesh_garg @RoboticsSciSys Congratulations @animesh_garg and to the team!

0

2

Agrim Gupta

@agrimgupta92

5 years

So true!

Lego Grad Student

@legogradstudent

5 years

Any time I feel smart, I remember that I am hesitant to watch new movies because they take too much time yet I gleefully chain-watch videos on YouTube.

9

114

1K

1

0

2

Agrim Gupta

@agrimgupta92

5 years

A recent work shows how object-recognition systems perform on a geographically diverse dataset.

Does Object Recognition Work for Everyone?

The paper analyzes the accuracy of publicly available object-recognition systems on a geographically diverse dataset. This dataset contains household items and was designed to have a more...

arxiv.org

0

2

Agrim Gupta

@agrimgupta92

2 years

Amazing results!

Ben Poole

@poolio

2 years

Happy to announce DreamFusion, our new method for Text-to-3D! We optimize a NeRF from scratch using a pretrained text-to-image diffusion model. No 3D data needed! Joint work w/ the incredible team of @BenMildenhall @ajayj_ @jon_barron #dreamfusion

136

1K

6K

0

2

Agrim Gupta

@agrimgupta92

3 years

Congratulations @DeepMind @demishassabis . In 2014 people thought the mission statement of Deepmind was absolutely crazy "solving intelligence" and using it to solve other challenges. It's amazing what we can achieve with current capabilities. Future looks promising!

Demis Hassabis

@demishassabis

3 years

The #AlphaFold 2 papers on the methods and human proteome predictions are out today in hard copy in @Nature ! A really proud moment to see our work featured with a fantastic image on the front cover of the issue:

35

534

3K

0

2

Agrim Gupta

@agrimgupta92

4 months

Sim to SF

Ilija Radosavovic

@ir413

4 months

hello san francisco

47

42

496

0

3

Agrim Gupta

@agrimgupta92

3 years

Woke up to two exciting pieces of news! Thanks @HennessyReports for the amazing article featuring our work in @TheEconomist , which was also featured in @NatureComms editor highlights.

A novel way to optimise robots

It harks back to a 19th-century idea about evolution

www.economist.com

0

2

Agrim Gupta

@agrimgupta92

1 year

This is perhaps as mainstream as it gets for #ChatGPT @OpenAI usage! Only @VancityReynolds can get you to watch ads on @YouTube

ChatGPT Writes a Mint Mobile Ad

You knew it was just a matter of time until we did this (extend the @MintMobile savings with @OpenAI, that is). https://www.mintmobile.com/#MintMobile offers...

www.youtube.com

0

2

Agrim Gupta

@agrimgupta92

3 years

Workshop organized by: @ChengshuEricLi @sanjana__z @mjlbach @xf1280 @sultanskyman @silviocinguetta @hyogweon @jiajunwu_cs @drfeifei S. Buch & K. Liu

0

2

Agrim Gupta

@agrimgupta92

6 years

Today we are open-sourcing code and pretrained models for our paper Image Generation from Scene Graphs. #CVPR2018

Justin Johnson

@jcjohnss

6 years

Code and pretrained models for our #CVPR2018 paper on generating images from scene graphs is now available! A step toward creating images with fine-grained control over visual content. With @agrimgupta92 and @drfeifei

1

101

316

0

2

Agrim Gupta

@agrimgupta92

4 months

@RobertTLange @hardmaru @SakanaAILabs @yujin_tang Congratulations @RobertTLange !

0

1

Agrim Gupta

@agrimgupta92

4 years

2/2 LVIS v1.0 will be used for the Joint COCO and LVIS Workshop in ECCV 2020. Please see the section about best practices if you use LVIS in your research.

0

1

Agrim Gupta

@agrimgupta92

3 years

@maxjaderberg Congratulations on the release! Both the environment and the learnt behaviors are fascinating. Really like the procedural generation of environments which encompasses both cooperative and competitive games!

0

Agrim Gupta

@agrimgupta92

3 years

"Biology is far too complex and messy to ever be encapsulated as a simple set of neat mathematical equations. But just as mathematics turned out to be the right description language for physics, biology may turn out to be the perfect type of regime for the application of AI"

Demis Hassabis

@demishassabis

3 years

Thrilled to announce the launch of a new Alphabet company @IsomorphicLabs . Our mission is to reimagine the drug discovery process from first principles with an AI-first approach, to accelerate biomedical breakthroughs and find cures for diseases. Details:

69

618

3K

0

Agrim Gupta

@agrimgupta92

6 months

@adityagrover_ Congrats @adityagrover_ !

1

0

1

Agrim Gupta

@agrimgupta92

3 months

@ashrewards Congratulations @ashrewards !

1

0

Agrim Gupta

@agrimgupta92

1 year

Feature request for prompt: Interesting follow ideas on X. The model should do more than extracting future work snippets. Can potentially be really helpful with the paper as context combined with huge database of papers --> brainstorming parter!

Papers with Code

@paperswithcode

1 year

🪐 Introducing Galactica. A large language model for science. Can summarize academic literature, solve math problems, generate Wiki articles, write scientific code, annotate molecules and proteins, and more. Explore and get weights:

283

2K

8K

0

1

Agrim Gupta

@agrimgupta92

5 months

@chenwang_j Thank you @chenwang_j

0

1

Agrim Gupta

@agrimgupta92

3 months

@jparkerholder Congratulations @jparkerholder !

1

0

1

Agrim Gupta

@agrimgupta92

9 months

@KuanFang @Cornell @CornellCIS @Cornell_CS Congrats, Kuan!

0

1

Agrim Gupta

@agrimgupta92

3 years

Check out the video and the blog post describing our work.

Stanford University

@Stanford

3 years

. @StanfordHAI researchers created a computer-simulated playground where arthropod-like agents dubbed "unimals" (short for universal animals) learn and are subjected to mutations and natural selection.

3

21

59

0

1

Agrim Gupta

@agrimgupta92

6 months

@DrJimFan @sama @gdb What if they join Anthropic?

2

0

1