Gautam Reddy
@Gautam_Reddy_N
Followers
551
Following
155
Media
0
Statuses
73
Assistant Professor, Princeton Physics.
Princeton, NJ
Joined December 2021
RT @danielwurgaft: 🚨New paper! We know models learn distinct in-context learning strategies, but *why*? Why generalize instead of memorize….
0
15
0
RT @EkdeepL: Thank you to amazing collaborators! @danielwurgaft, @corefpark, @Gautam_Reddy_N, @Hidenori8Tanaka, and @noahdgoodman. Check ou….
0
1
0
RT @martinmbauer: Even if you don't care one bit about scientific research, it's important to recognise the value of publicly funding peopl….
0
113
0
RT @MichaelMDesai: Just got news that all of my NIH and NSF grants were officially terminated today. Have been expecting this for some time….
0
339
0
RT @paul_masset: I am recruiting graduate students for my lab @mcgillu for admission in Fall 2025! Get in touch if you're interested in ho….
0
35
0
RT @HopfieldJohn: This award is very hard to respond to. I have received many hundred congratulatory notes, from former students, post-docs….
0
176
0
Happy to see this point being articulated so well :).
Earlier this year I tried writing a doc to encourage the MIT Department of Physics to create a new PhD specialization in ML. The doc ended up being a little vague and so I didn't push it. But in light of the Physics Nobel this week, I thought I'd share it here:
1
1
9
Our hope is to build new physics-style theory that lets us develop a more precise intuitive picture of how learning works in high-dimensional, over-parameterized systems. But this is very much a community effort. Hope to see you next March!.
0
0
3
Complexity in biology and ML arises from heavily parameterized systems tuned by rather simple "learning rules". Learning matters -- what's learnable is not necessarily what's optimal. The interaction between learning rules, task structure and system architecture is non-trivial.
1
0
3
I believe this will be a really exciting space going forward. At its core, biological physics is driven by the belief that the tremendously complex systems we find in biology can be broken down into intuitive bits and described in quantitative terms.
1
0
3
Sarah Marzen and I are hosting a session on "The Physics of Learning and Adaptation" at the APS March Meeting in 2025. Abstract submissions due Oct 25th (. We hope to have a solid list of speakers from both biological physics and machine learning.
1
3
18
RT @DimaKrotov: Huge congratulations to John Hopfield for the 2024 Physics Nobel Prize! #NobelPrize2024 @HopfieldJohn .
0
39
0
Please share with anyone who may be interested!.
@Gautam_Reddy_N and I are hiring a predoc/postbach researcher! Paid, in-person at Princeton. Topic: self-supervised ML + physics. Requirements: Docker/Singularity, PyTorch/Jax, US work authorization (OPT is OK). Apply by emailing me a resume and transcript.
0
5
8
RT @Hidenori8Tanaka: Exciting news🎉 We're now accepting applications for CBS-NTT postdoc fellows in the Physics of Intelligence at Harvard….
0
41
0
RT @phybiofunc: Finishing your PhD and interested in the Physics of Life? We are in the midst of our annual search for new Fellows. We are….
0
16
0
RT @ApsDbio: Want to run your own session at the 2025 APS March Meeting? Help build the DBIO program by (i) leading an existing session or….
0
7
0
RT @phybiofunc: Our next symposium will focus on large language models. Longer talks and plenty of discussion time should help making thes….
0
2
0
RT @JosephDZak: Our recent work on representations of olfactory stimuli in sensory neurons and cortical projections to the OB is now formal….
0
12
0
RT @ben_eysenbach: 1/ Given high-dim time series data (e.g., video, text), we'd like to know "what happens in the future?" and "what happen….
0
98
0