Imtiaz Humayun
@imtiazprio
Followers
482
Following
886
Media
20
Statuses
212
Research Scientist at Google. PhD @RiceUniversity with @rbaraniuk. Co-founded @bengali_ai. DL theory, interpretability and generative models 🇧🇩
Houston, Texas
Joined August 2018
How are Deep Neural Networks black-boxes if you can visualize them in an 'exact' manner?. Our new #CVPR23 paper, presents a fast and scalable PyTorch toolbox to visualize the linear regions, aka partition+decision boundary, of any DNN (red🔻)!. 🧵 1/N
6
56
270
RT @agrimgupta92: Introducing Genie 3, our state-of-the-art world model that generates interactive worlds from text, enabling real-time int….
0
180
0
RT @thomas_M_walker: GrokAlign: A method to accelerate grokking motivated by a geometric characterisation of the phenomenon. - The grokked….
0
1
0
RT @Google: Say goodbye to the silent era of video generation: Introducing Veo 3 — with native audio generation. 🗣️. Quality is up from Veo….
0
3K
0
RT @tjingrant: 📣 The Journey Matters: Our #ICLR2025 paper shows how to pretrain sparse LLMs with half the size of dense LLMs while maintain….
0
5
0
RT @andrewgwils: My new paper "Deep Learning is Not So Mysterious or Different": Generalization behaviours in deep….
0
317
0
Indeed, it is that simple! The wiggliness induced by each layer allows NNs to approximate non-linear functions. More layers -> more possible wiggle -> more non-linearity. A nice way of thinking about this is imagining NNs doing origami on an elastic piece of paper!
14
105
928
RT @bneyshabur: In 2021, when I decided to let go of deep learning theory and focus on improving math and reasoning in LLMs, I was inspired….
0
9
0
Checkout buddy @randall_balestr discussing our work and more, why thinking of NNs as splines can provide strong intuitions of how they learn, generalize and grok! Also features a small cameo from yours truly!!.
Professor @randall_balestr discussing some exciting research he has been working on recently, in particular around spline-based interpretability. • Why reconstruction learning can fail for perception.• How deep nets partition space like a crystal.• Spline theory new insights
0
1
19
RT @mbeisen: Here's the thing. We have **NO IDEA** how to pick good graduate students. I served on admission committees for 10+ years, and….
0
435
0
RT @fchollet: I kinda miss when "AI Twitter" was folks doing AI research or app development, posting under their own identities. Slightly m….
0
236
0
RT @YukeWang1: I will be hiring 2~3 PhD students at Rice CS in the Fall of 2025 in the system for deep learning. Feel free to reach out and….
csweb.rice.edu
Graduate Program Application Thank you for your interest in computer science graduate studies at Rice University.
0
179
0
RT @ShayneRedford: Interested in how LLMs are really used?. We are starting a research project to find out! In collaboration w/ @sarahookr….
docs.google.com
This is an interest form to contribute/collaborate on a community research project. What? The research project, targeting the following questions: How are general-purpose AI systems *really* being...
0
38
0
0
2
0
RT @pcastr: We've been rehearsing for over two months and we're ready to rock opening night tomorrow. If you're in Ottawa, don't miss out!….
0
1
0
We have already achieved self-improvement in diffusion models, via its own synthetic data! Not that far away definitely!
Mustafa Suleyman, CEO of Microsoft AI, says in an interview surprisingly openly that self-improving AI will be achieved in 3-5 years at the latest, but certainly before 2030. That would be the point in time when we would slowly enter the singularity. The consequences after that
0
2
16
RT @micahgoldblum: 📢I’ll be admitting multiple PhD students this winter to Columbia University 🏙️ in the most exciting city in the world!….
0
146
0
RT @MihaelaVDS: Interested in a #PhD that let‘s you transform what is possible with #AI & #MachineLearning? That gives you the chance to pu….
vanderschaar-lab.com
Do you want to meet Prof van der Schaar, the current PhD students, and our researchers? Join us for our online PhD Open Day on 14 November!
0
24
0
RT @JaronMink: The Happy Lab is hiring multiple PhD students for Fall 2025! RT appreciated :-). We discover how human factors can 1) mitiga….
happyresearchlab.com
Human Aspects in cyber Protection & PrivacY Who are we? We are a group of researchers discovering how to better pro...
0
46
0