Ranjay Krishna
2,093 posts
Ranjay Krishna
@RanjayKrishna
Assistant Professor @ University of Washington, Co-Director of RAIVN lab (raivn.cs.washington.edu), Director of PRIOR team (prior.allenai.org)
A hearty congratulations to my student @RanjayKrishna (co-advised by @msbernst ) for a successful PhD thesis defense! Great pioneering work in combining human cognition, human-computer interaction and #AI! Thank you PhD committee members @chrmanning @syeung10 @magrawala 🌹
- 🎓 I'm on the faculty job market this year! Please send me a message if your department (or one you know) is interested in a Computer Vision / HCI researcher who designs models inspired by human perception and social interaction! My application materials: ranjaykrishna.com
- Our submission received my first ever 10/10 review from NeurIPS. Check out our #NeurIPS2023 Oral. We release the largest vision-language dataset for histopathology and train a SOTA model for classifying histopathology images across 13 benchmarks across 8 sub-pathologies.Quilt-1M has been accepted for an oral presentation at @NeurIPSConf. As promised, we have also released our data and our model: quilt1m.github.io See you all in New Orleans!
- We are happy to introduce Action Genome: a new representation, new dataset, and new model for decomposing actions into spatio-temporal scene graphs. Action Genome has 1.7M relationships between 0.4M object instances and enables few-shot action prediction. arxiv.org/pdf/1912.06992…
GIF - My latest #CVPR2018 paper with Ines, @msbernst and @drfeifei is now live with fully documented open source training/testing code. We treat visual relationships as shifts in attention and perform attention saccades around scene graphs. goo.gl/mqSTrA
- I expect a future where ML agents will dynamically learn through real-world interactions with people. My #CVPR2019 paper with @msbernst and @drfeifei pushes us towards that goal by learning to pose directed questions to learn about the visual world. bit.ly/2CKLdDu
- Our new paper finds something quite neat: We easily scale up how many tools LLMs can use to over 200 tools (APIs, models, python functions, etc.) ...without any training, without a single tool-use demonstration!!Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models paper page: huggingface.co/papers/2308.00… Today, large language models (LLMs) are taught to use new tools by providing a few demonstrations of the tool's usage. Unfortunately, demonstrations are hard to
- Announcing the first 𝗜𝗖𝗖𝗩 𝘄𝗼𝗿𝗸𝘀𝗵𝗼𝗽 𝗼𝗻 𝗦𝗰𝗲𝗻𝗲 𝗚𝗿𝗮𝗽𝗵 𝗥𝗲𝗽𝗿𝗲𝘀𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴. If your research involves structured data or graph-based learning, consider submitting to us by August 15, 2019: sgrl.stanford.edu
- On my way to Seoul for #ICCV2019. If you’re at the conference on October 28th, come check out a full day workshop I am organizing on Scene Graph Representation and Learning (sgrl.stanford.edu). We have a great lineup of speakers and posters.
- Academic quarter recap: here's a staff photo after the last lecture of @cs231n. It's crazy that we were the largest course at Stanford this quarter. This year, we added new lectures and assignments (open sourced) on attention, transformers, and self-supervised learning.
- Thank you all for coming to my talk yesterday at #ECCV2024 where we discussed the lessons learned from evaluating VLMs and designing Molmo. In today's talk, I will discuss limitations still left with VLMs and what we can do about it: **Suite 9 at 2pm** green-fomo.github.io/ECCV2024/
- Someone made an in-depth video of our recent work at #CVPR2018 on Referring Relationships. If you are interested in how we train models to disambiguate between different people or objects in images, go check it out. #ComputerVision #MachineLearning youtube.com/watch?v=G7Ti_S…
- Deploying LLMs continues to be a challenge as they grow in model size and consume more data. We introduce a simple distillation mechanism to make even 770M T5 models outperform 540B PaLM. Led by my PhD student @cydhsieh and with collaborators @chunliang_tw @ajratnerDistilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes reduce both the model size and the amount of data required to outperform LLMs; our 770M T5 model outperforms the 540B PaLM model using only 80% of available data on a
