Frederic Zhang (@fredzzhang) header
Frederic Zhang (@fredzzhang) profile picture

Scientist @amazon, photographer, substandard musician but a linguistic genius

Melbourne, Victoria
Joined July 2013
Photo by Frederic Zhang (@fredzzhang)Photo by Frederic Zhang (@fredzzhang)Photo by Frederic Zhang (@fredzzhang)Photo by Frederic Zhang (@fredzzhang)Photo by Frederic Zhang (@fredzzhang)Photo by Frederic Zhang (@fredzzhang)Photo by Frederic Zhang (@fredzzhang)Photo by Frederic Zhang (@fredzzhang)Photo by Frederic Zhang (@fredzzhang)Photo by Frederic Zhang (@fredzzhang)
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
1
7
333
Frederic Zhang retweeted
This is wild 🤯 AI imagines stars with young self together
991
2,946
761
16,407
3,604,760
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
21
169
65
807
63,498
Frederic Zhang retweeted
#ICCV2023 Awards 🏆 – at Paris, France
2
41
5
226
31,448
My mind is blown 🤯🤯🤯 go to any github repo but use github.dev instead of github.com it's now VS code IN BROWSER
33
419
73
3,607
1,408,143
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…
206
1,052
183
8,180
1,952,393
Frederic Zhang retweeted
Announcing GPT-4, a large multimodal model, with our best-ever results on capabilities and alignment: openai.com/product/gpt-4
2,003
15,919
5,348
59,541
12,484,160
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.
3
57
15
252
60,326
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! :-)
3
43
4
293
75,591
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.
8
1
16
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-…
16
66
16
264
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…
16
3
112
Frederic Zhang retweeted
How Do Vision Transformers Work? abs: arxiv.org/abs/2202.06709
4
71
3
377
Frederic Zhang retweeted
Collapse by Conditioning: Training Class-conditional GANs with Limited Data abs: arxiv.org/abs/2201.06578 github: github.com/mshahbazi72/trans…
10
81
Frederic Zhang retweeted
The shaded square covers half the larger square. What’s the angle?
60
85
9
403