ᴘᴇᴛᴇʀ ɢ. ᴄʜᴀɴɢ
@petergchang
Followers
243
Following
2K
Media
1
Statuses
33
PhD Student | @MIT EECS | with @m_sendhil | AI for Scientific Understanding
Cambridge, MA
Joined May 2022
RT @andrewgwils: A common takeaway from "the bitter lesson" is we don't need to put effort into encoding inductive biases, we just need com….
0
36
0
If you’re at ICML, please come check out the World Models workshop I am co-organizing tomorrow!.
Join us for the Workshop on Assessing World Models at ICML tomorrow!. When: Friday July 17, 8:45am-5:15pm.Where: West Ballroom B (same floor as registration)
0
1
7
RT @Alber_RomGar: Researchers from Harvard, Keyon Vafa (@keyonV) and MIT, Peter Chang (@petergchang), Ashesh Rambachan (@asheshrambachan),….
0
27
0
The first paper I’ve worked on as a PhD student is out! Very proud of this work.
Can an AI model predict perfectly and still have a terrible world model?. What would that even mean?. Our new ICML paper formalizes these questions. One result tells the story: A transformer trained on 10M solar systems nails planetary orbits. But it botches gravitational laws 🧵
1
3
22
RT @brandondamos: & here are some of my favorite papers on the unification of flows and diffusion. What a decade!!. (From my presentation h….
0
42
0
RT @antferrui: Excited to share our latest story! We found disentangled memory representations in the hippocampus that generalized across t….
0
161
0
RT @ArturAGalstyan: Worked on a little project which helps converting PyTorch models to JAX PyTrees (e.g. for usage in Equinox). You can al….
0
20
0
RT @R_Thaler: I was so lucky to be able to have Danny Kahneman as a best friend and collaborator for decades. He usually ended our conversa….
0
1K
0
RT @tdietterich: This looks cool: Mathieu Blondel (@mblondel_ml) and Vincent Roulet have posted a first draft of their book on arXiv: https….
arxiv.org
Artificial intelligence has recently experienced remarkable advances, fueled by large models, vast datasets, accelerated hardware, and, last but not least, the transformative power of...
0
79
0
RT @srush_nlp: If you know Torch, I think you can code for GPU now with OpenAI's Triton language. We made some puzzles to help you rewire….
0
197
0
RT @stephen_wolfram: Can AI Solve Science? (podcast version with Q&A) now available on YouTube:..
0
52
0
RT @PreetumNakkiran: My friend Chenyang (twitterless) has written a nice tutorial on diffusion models, from the "projection onto manifold"….
0
139
0
RT @jeremyphoward: If you watched my "Getting Started with CUDA for Python Programmers", and are ready to go even faster, then this new vid….
0
158
0
RT @TheGradient: (0/17) Grab your🍿 for a thread on some mysteries and explanations connecting flat minima, second order optimization, weigh….
0
72
0
RT @kostaspitas_: Interested in working on Bayesian neural networks/ deep ensembles? Here's a reading list to get you started! I've taken a….
github.com
A primer on Bayesian Neural Networks. The aim of this reading list is to facilitate the entry of new researchers into the field of Bayesian Deep Learning, by providing an overview of key papers. Mo...
0
8
0
RT @PatrickKidger: Announcing a new #JAX and #Equinox nonlinear optimisation library:. ⭐️ Optimistix ⭐️. (GitHub: ….
0
36
0
RT @sirbayes: The trilogy is complete! My "Advanced Topics" book is officially released today. Buy it on Amazon, or get it for free at http….
0
755
0
RT @mjsMLP: Come help us build the next generation of numerical computing and machine learning software! Join the JAX team at Nvidia to inv….
linkedin.com
Today’s top 14,000+ Senior System Software Engineer jobs in United States. Leverage your professional network, and get hired. New Senior System Software Engineer jobs added daily.
0
3
0
RT @sirbayes: I am pleased to announce the release of which is a library for structural time series forecasting in….
github.com
Structural Time Series in JAX. Contribute to probml/sts-jax development by creating an account on GitHub.
0
62
0