
Scientist @amazon, photographer, substandard musician but a linguistic genius
Melbourne, Victoria
Joined July 2013
- Tweets46
- Following61
- Followers91
- Likes275
Frederic Zhang retweeted
In our first Researcher Spotlight, Dr. Frederic Zhang, AIML Postdoctoral Fellow, shares insights into his work on 'task vectors'—a method for improving multitasking in machine learning. Learn more and watch his interview: youtu.be/Rhe7AV2MPUg #AI #machinelearning
Frederic Zhang retweeted
I just posted the first of what will be several chapters about transformers, which in the last year has been the most requested topic for the channel.
youtu.be/wjZofJX0v4M
Frederic Zhang retweeted
#ICCV2023 Awards 🏆 – at Paris, France
Frederic Zhang retweeted
My mind is blown 🤯🤯🤯
go to any github repo but use github.dev instead of github.com
it's now VS code IN BROWSER
Frederic Zhang retweeted
This is a baby GPT with two tokens 0/1 and context length of 3, viewing it as a finite state markov chain. It was trained on the sequence "111101111011110" for 50 iterations. The parameters and the architecture of the Transformer modifies the probabilities on the arrows.
E.g. we can see that:
- state 101 deterministically transitions to 011 in the training data, so the probability of that transition becomes higher (79%). Not near 100% because we only did 50 steps of optimization.
- state 111 goes to 111 and 110 with 50% probability each, which the model almost learns (45%, 55%).
- states like 000 are never encountered during training, but have relatively sharp transition probabilities, e.g. 73% of going to 001. This is a consequence of inductive biases in the Transformer. One might imagine wanting this to be 50%, except in a real deployment almost every input sequence is unique, not present in the training data verbatim.
Not really sure where I was going with this :D, I think it's interesting to train/study tiny GPTs because it becomes tractable to visualize and get an intuitive sense of the entire dynamical system. Play with here: colab.research.google.com/dr…
Frederic Zhang retweeted
Announcing GPT-4, a large multimodal model, with our best-ever results on capabilities and alignment: openai.com/product/gpt-4
Frederic Zhang retweeted
What if you actually could build Rome in a day? Prof Richard Hartley is one of the founders of Multiview Geometry, which establishes the construction of 3D models from sets of images or videos. He receives the Hannan Medal for his pioneering work.
Revolution in 3D reconstruction – #Honorifics23
Prof Hartley is one of the founders of Multiview Geometry, which establishes the construction of 3D models from sets of images or videos. He receives the Hannan Medal for his work in Computer Vision.
Frederic Zhang retweeted
Thrilled that our workshop on "Generative Models for Computer Vision" got accepted to #CVPR2023!
We have a fantastic speaker lineup with whom we will discuss how image synthesis can benefit image analysis.
Stay tuned! :-)
Frederic Zhang retweeted
I'm recruiting for a 1-year postdoc to work at the intersection of object tracking and NeRF models. @ANUComputing
jobs.anu.edu.au/cw/en/job/54…
Applications close 23 October 2022. Ideal candidate will preferably be able to commence by January 2023. Contact me if you're interested.
Frederic Zhang retweeted
Short video summaries for some papers that @ANUComputing researchers and colleagues will be presenting at #CVPR2022 can be viewed here:
youtube.com/watch?v=VneKesTm…
Frederic Zhang retweeted
a @Gradio Demo for DALL·E mini by @borisdayma is now on @huggingface Spaces using the new Blocks API, demo by @evilpingwin , @abidlabs and Ali Abid from the Gradio team
demo: huggingface.co/spaces/dalle-…
Frederic Zhang retweeted
Short on GPUs/time/data/$, but still want to train a GAN?
In "Ensembling Off-the-shelf Models for GAN Training", we show GANs can be "Vision-Aided" with pre-trained nets as discriminators.
A #CVPR2022 (oral) by @nupurkmr9, @elishechtman, @junyanz89
Web: cs.cmu.edu/~vision-aided-gan…
Frederic Zhang retweeted
How Do Vision Transformers Work?
abs: arxiv.org/abs/2202.06709
Frederic Zhang retweeted
Collapse by Conditioning: Training Class-conditional GANs with Limited Data
abs: arxiv.org/abs/2201.06578
github: github.com/mshahbazi72/trans…
























