The computer vision and reasoning lab in the Allen School at the University of Washington, led by Ali Farhadi and Ranjay Krishna.
Seattle, WA
Joined April 2020
- Tweets166
- Following144
- Followers882
- Likes294
UW RAIVN Lab retweeted
📢Applications are open for summer'25 internships at the PRIOR (computer vision) team
@allen_ai:
Come join us in building large-scale models for:
📸 Open-source Vision-Language Models
💻 Multimodal Web Agents
🤖 Embodied AI + Robotics
🌎 Planet Monitoring
Apply by December 11, 2024!
UW RAIVN Lab retweeted
🎉 Very Excited to present our recent work on “Selective🔍 Visual Representations for Embodied-AI🤖” next week at ICLR in Vienna🇦🇹!!
📣📣Important update! Our code and pretrained models are now available through our project website 🌐: embodied-codebook.github.io/🚀
👋Come to my poster, say hi, and learn more about our findings! (Poster #111, Session 8, on Friday, May 10th at 4:30 PM)
Embodied-AI 🤖 models employ general-purpose vision backbones such as CLIP to encode the observation. How can we have a more task-driven visual perception for embodied-AI?
We introduce a parameter-efficient approach that selectively filters visual representations for Embodied-AI tasks.
Project page: embodied-codebook.github.io
🧵👇
UW RAIVN Lab retweeted
Introducing💃AdANNS: A Framework for Adaptive Semantic Search🕺
TL;DR: Up to 90× faster nearest neighbor retrieval and 2× lower memory cost for web-scale search.
Applies to vector search at scale & improves all "retrieval" augmented models!
arxiv.org/abs/2305.19435
[1/8]
UW RAIVN Lab retweeted
1/9 I am excited to announce that our workshop "Towards the Next Generation of Computer Vision Datasets" will be happening at ICCV 2023 in Paris. We will feature DataComp submissions, other data-centric papers, and invited talks by experts. datacomp.ai/workshop
UW RAIVN Lab retweeted
Introducing DataComp, a new benchmark for multimodal datasets!
We release 12.8B image-text pairs, 300+ experiments and a 1.4B subset that outcompetes compute-matched CLIP runs from OpenAI & LAION
📜 arxiv.org/abs/2304.14108
🖥️ github.com/mlfoundations/dat…
🌐 datacomp.ai
UW RAIVN Lab retweeted
Instead of prompting CLIP w/ "A photo of a {class}", why not ask GPT-3 to describe {class} instead?
The result is customized prompts for each {class}!
Less human effort, higher zero-shot accuracy
Work w/ Rosanne Liu (@savvyRL) + Ali Farhadi
arxiv.org/abs/2209.03320
(1/4)
UW RAIVN Lab retweeted
Introducting🪆Matryoshka Representations for Adaptive Deployment🪆
TL;DR: up to 14× lower real-world classification & retrival costs at web-scale at no loss in accuracy & w/o any overhead across setups.
Paper: arxiv.org/abs/2205.13147
Code: github.com/RAIVNLab/MRL
[1/11]
UW RAIVN Lab retweeted
Matryoshka Representations for Adaptive Deployment
abs: arxiv.org/abs/2205.13147
flexibility within the learned Matryoshka Representations offer: (a) up to 14× smaller embedding size for ImageNet-1K classification at the same level of accuracy
UW RAIVN Lab retweeted
Our latest work!! I will share a tweet thread soon🪆
Work co-led w/ @BhattGantavya @wregss
Collab between @uwcse/@RAIVNLab & @GoogleAI
Co-authors: Matt Wallingford, @adityaasinha,@RamanujanVivek, William, Kaifeng, @ShamKakade6, @jainprateek_ and Ali Farhadi.
Matryoshka Representations for Adaptive Deployment
abs: arxiv.org/abs/2205.13147
flexibility within the learned Matryoshka Representations offer: (a) up to 14× smaller embedding size for ImageNet-1K classification at the same level of accuracy
UW RAIVN Lab retweeted
A bit of outdated news: I am spending more time at AI2 @allen_ai now, co-leading @ai2_allennlp with @nlpnoah
At @ai2_allennlp, we are hiring postdocs and research scientists with strong foundation in NLP.
Links to apply: boards.greenhouse.io/thealle…
boards.greenhouse.io/thealle…
UW RAIVN Lab retweeted
On #GivingTuesday, we’re excited to share the story behind a new professorship honoring #UWAllen’s own “force of nature” (and resident steamroller) @lazowska—a fierce champion for our school, @UW, and expanding access to computing education & careers: news.cs.washington.edu/2021/… 1/3
ALT Portrait of Ed Lazowska in light-filled Gates Center atrium with stairwell in the background
UW RAIVN Lab retweeted
‼️Announcement‼️I'm on the academic job market!
I focus on building grounded AI models🤖, capable of understanding humans and the complex world we live in🌍. I combine #NLProc & vision, with insights from developmental psych.
Reach out if your university might be a good fit😀
UW RAIVN Lab retweeted
I feel awful working on the CVPR deadline and having first-world problems (like OMG my learning curves are ugly!), while my parents, who are both healthcare workers in Iran, keep getting re-infected and getting hospitalized over and over again!
UW RAIVN Lab retweeted
Excited to share our new method, "Learning Compressible Subspaces (LCS)", for adaptive model compression in real-time: (arxiv.org/abs/2110.04252).
UW RAIVN Lab retweeted
Multi-class classification of *L* classes traditionally need *L* classifiers.
1st thought in 2016: Can we do this w/ *log L* bits?
I finally acted on it, we propose LLC that solves 1000 class ImageNet classification with **20-bits**.
A thread🧵(1/8)
arxiv.org/abs/2106.01487
UW RAIVN Lab retweeted
Amazing collaborators (@RAIVNLab & @uw_wail): Matt, @RamanujanVivek, @SomaniRaghav, @jae_sung_park96 & Krishna
My advisors (@uwcse & @GoogleAI) Ali Farhadi, @ShamKakade6 & @jainprateek_. They were the best with all that's going on around & supported all my crazy thoughts. 8/8
UW RAIVN Lab retweeted
Congrats to @UW @uw_ece Ph.D. student Vikram Iyer on winning the @GeekWire Innovation of the Year Award 🏆 for his work with #UWAllen's @ShyamGollakota & @ME_at_UW's @blinkminster on low-power sensing and insect-scale robotics🪲— and thanks to the voters!🙌geekwire.com/2021/2021-geekw…
UW RAIVN Lab retweeted
Exciting life update: I'll be joining Carnegie Mellon University's LTI department as an assistant prof 👨🏼🏫 in Fall '22, before which I'll spend a year as a postdoc at AI2 Mosaic 👨🏼🔬...
That is, once I finish and defend my thesis first👨🏼🎓
@SCSatCMU @LTIatCMU @ai2_mosaic @allen_ai
