Ajay Jain
Time 2022-09-15 03:43:20Web Name: Ajay Jain
WebSite: http://www.ajayjain.net
ID:315446
Keywords:
Ajay,JainDescription:
Ajay Jain
Doctoral student (Ph.D.), UC Berkeley
NSF Graduate Research Fellow
NVIDIA Research
Previous: Google Brain, Uber ATG, Meta AI, MIT
Biography
I'm a PhD student at UC Berkeley. At Berkeley, I'm affiliated with Berkeley Artificial Intelligence Research and a recipient of the NSF Graduate Research Fellowship. My research studies the problem of unsupervised machine learning: How can machines automatically recognize, reconstruct, and generate the structure within raw data? I'm particularly excited by creative applications of AI, such as supercharging design and editing with generative models.
Previously, I was a visiting researcher at Google Brain and Uber ATG, and worked on ML at Meta (Facebook) AI, Kensho, and Juniper Networks. I graduated from MIT with an S.B. in Computer Science, was a director of Machine Intelligence Community, and organized the HackMIT hackathon. I also enjoy the outdoors, board games, and cooking.
I've been fortunate to be advised by really great people along the way, including Pieter Abbeel, Ben Poole, Jon Barron, Joseph Gonzalez, Ion Stoica, Deepak Pathak, Saman Amarasinghe, and Raquel Urtasun.
Email: ajayj at berkeley dot edu
News
New! July 2022: Dream Fields wins the Best Poster award at AI4CC
New! May 2022: AdaCat accepted to UAI 2022
March 2022: Dream Fields accepted to CVPR 2022
Aug 2021: ContraCode accepted to EMNLP 2021
July 2021: DietNeRF accepted to ICCV 2021
Publications * indicates equal contribution
Adaptive Categorical Discretization for Autoregressive Models
Colin Li, Ajay Jain, Pieter Abbeel
UAI 2022 Conference on Uncertainty in Artificial Intelligence
AdaCat learns expressive autoregressive models by capturing fine-grained variation in continuous distributions with discrete density estimators.
[Paper] [Website] [Code] [Poster]"a sculpture of a rooster"
Zero-Shot Text-Guided Object Generation with Dream Fields
Ajay Jain, Ben Mildenhall, Jon Barron, Pieter Abbeel, Ben Poole
CVPR 2022 Conference on Computer Vision and Pattern Recognition
We combine neural rendering with multi-modal image and text representations to synthesize diverse 3D objects solely from natural language descriptions.
[Website] [arXiv] [Overview video] [Code] [Colab demo] [Poster]Contrastive Code Representation Learning
Paras Jain*, Ajay Jain*, Tianjun Zhang, Pieter Abbeel, Joseph E. Gonzalez, Ion Stoica
EMNLP 2021 Empirical Methods in Natural Language Processing
Learn to represent software functionality for automated software engineering tasks like type inference, clone detection and summarization. Improving robustness of ML4Code.
[Website] [ACL] [arXiv] [Poster] [Slides] [Talk] [Code]Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis
Ajay Jain, Matthew Tancik, Pieter Abbeel
ICCV 2021 International Conference on Computer Vision
CLIP + NeRF: Given only a few images of an object or scene, we reconstruct its 3D structure & render novel views using prior knowledge contained in large image encoders.
[Website] [arXiv] [Code] [Overview video]Denoising Diffusion Probabilistic Models
Jonathan Ho, Ajay Jain, Pieter Abbeel
NeurIPS 2020 34th Conference on Neural Information Processing Systems
High-quality likelihood-based image generation; connect diffusion models to denoising score matching and Langevin dynamics; compression, reconstruction and interpolation
[Website] [arXiv] [Talk] [Sample video] [Code]Sparse Graphical Memory for Robust Planning
Scott Emmons*, Ajay Jain*, Michael Laskin*, Thanard Kurutach, Pieter Abbeel, Deepak Pathak
NeurIPS 2020 34th Conference on Neural Information Processing Systems
Provably robust+efficient long-horizon monocular navigation combining sparse graph planning and RL. Propose two-way consistency to find landmark memories and create a topological map.
[Website] [arXiv] [NeurIPS] [Talk] [Video] [Poster] [Code]Locally Masked Convolution for Autoregressive Models
Ajay Jain, Pieter Abbeel, Deepak Pathak
UAI 2020 36th Conference on Uncertainty in Artificial Intelligence
Efficent op allows PixelCNNs to generate images in arbitrary orders
[Website] [arXiv] [PMLR] [Talk] [Code]Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization
Paras Jain*, Ajay Jain*, Aniruddha Nrusimha, Amir Gholami, Pieter Abbeel, Kurt Keutzer, Ion Stoica, Joseph E. Gonzalez
MLSys 2020 3rd Conference on Machine Learning and Systems
Use up to 5x less memory when training DNNs by recomputing activations
[Website] [arXiv] [Slides] [PPTX] [Code]Discrete Residual Flow for Probabilistic Pedestrian Behavior Prediction
Ajay Jain*, Sergio Casas Romero*, Renjie Liao*, Yuwen Xiong*, Song Feng, Sean Segal, Raquel Urtasun
CoRL 2019 3rd Conference on Robot Learning, Spotlight talk
Multimodal, long-range behavior forecasts by predicting state marginals
[arXiv] [Poster] [Talk] [Slides]Revec: Program Rejuvenation through Revectorization
Charith Mendis*, Ajay Jain*, Paras Jain, Saman Amarasinghe
CC 2019 28th International Conference on Compiler Construction
Achieve performance portability for hand-vectorized programs, with up to 1.88x speedup
[Website] [Paper] [arXiv] [Talk] [Slides] [Code]Autonomy for Surface Ship Interception
C. Mirabito, D.N. Subramani, T. Lolla, J. P.J. Haley, A. Jain, P.F.J. Lermusiaux, C. Li, D. Yue, Y. Liu, F. Hover, N. Pulsone, J. Edwards, K. Railey, and G. Shaw OCEANS 2017 60th OCEANS Conference, MTS/IEEE Aberdeen
OCEANS 2017 60th OCEANS Conference, MTS/IEEE Aberdeen
Time-optimal path planning for underwater robots
[Paper] [Open access]Short papers
Learning Automatic Schedulers with Projective Reparameterization
Ajay Jain, Saman Amarasinghe
ISCA 2019 46th International Symposium on Computer Architecture
Workshop on Machine Learning for Systems, Jun 2019, Talk
Supervised learning of schedulers, with correctness constraints
[Paper] [Slides] [PPTX]Using effective dimension to analyze feature transformations in deep neural networks
Kavya Ravichandran, Ajay Jain, Alexander Rakhlin
ICML 2019 36th International Conference on Machine Learning
Workshop on Identifying and Understanding Deep Learning Phenomena, Jun 2019
[Paper]The Case for GPU Multitenancy
Paras Jain, Xiangxi Mo, Ajay Jain, Alexey Tumanov, Joseph E. Gonzalez, Ion Stoica
arXiv 2019 arXiv:1910.02653, Jan 2019
[arXiv]Dynamic Space-Time scheduling for GPU inference
Paras Jain, Xiangxi Mo, Ajay Jain, Harikaran Subbaraj, Rehan Sohail Durrani, Alexey Tumanov, Joseph E. Gonzalez, and Ion Stoica
NeurIPS 2018 32nd Annual Conference on Neural Information Processing Systems
Workshop on Systems for Machine Learning, Dec 2018
Demonstrate 2.5x-4.9x speedups for deep learning inference workloads via GPU multitenancy
[arXiv] [Poster] [Follow-up paper]Invited talks
Service and teaching
Machine Learning Software
More Software
<<< Thank you for your visit >>>
Websites to related : VERTIC - Putoamissuojainjärjest
+358 50 579 0301info@vertic-finland.fi : KotisivuTuotteetVaakasuorat putoamissuojajärjestelmätTurvavaijerit ja
Heti szaunaprogramjaink - Székehu enSearch Toggle navigation
YogaJaya Tokyo - Baseworks Pract keywords:
description:Bespoke movement studio serving the Tokyo community for 18 years. Our signature practice method: Baseworks, is designed to get r
keywords:
description:
Skip to main content Sunday November 14 2021
keywords:Hindu Temple Architects, Jain Temple Architects, Temple Architect, Temple Architects.
description:Shubash Bhoite and Associates Architect spe
keywords:
description:
Home Hinduism Buddhism Spirituality Self-Help Quotations Web Resources Reference Shopping Scriptures
1 Spacious Master Bedroom (17 x20 , 2nd Floor) with:-LED TV CD/DVD/USB Player(DVD movies ), attached bathroom, Laptop/Work Table, 2 seater sofa, 2 que
Ready-to-Eat RTE Vegetable SupplAbout Us Ready-to-EatIQF Vegetables Dehydrated Onion Garlic, Spices, Herbs Fruit Products Leave this world better than you found it. Started
Hindu Website, Hinduism, BuddhisWelcome to Hinduwebsite PortalHinduwebsite.com is the real Hindu Website in the original sense, providing information on all the Santana Dharmas that
Hindu Website, Hinduism, BuddhisWelcome to Hinduwebsite PortalHinduwebsite.com is the real Hindu Website in the original sense, providing information on all the Santana Dharmas that
adsHot Websites