BCS PhD @ MIT | Auditory perception + deep learning | Turning noise into signal
Cambridge, MA
Joined April 2018
- Tweets22
- Following327
- Followers261
- Likes387
Pinned Tweet
Just published my first ever blog post about @ianmgriffith @JoshHMcDermott and I's recent paper on the cocktail party problem and brain-inspired auditory attention models.
Would love any feedback if you check it out!
(link in replies)
Preston Hess retweeted
There is a new kind of robotics called "Vibe Robotics"
It's when you ask agents for fully functioning embodied agents (both hardware and software) that must solve a given task in physically grounded environments.
We build an evaluation to test how good agents (frontier models) are at "Vibe Robotics".
Website: artifactarena.ai/
Preston Hess retweeted
Leading AI models appeared to predict brain activity equally well…
…until we asked them to synthesize images that precisely control neural firing, like these 👇
Across 25 neural sites, closed-loop experiments revealed striking hidden differences in model-brain alignment.
🧵
Preston Hess retweeted
Is this machine playing? 🏀🪁🛝
We left Eko, an embodied coding agent, on an island for 30 hours with no task or goal, studying it like ethologists study a new species
Eko explored, built, climbed, made games, and learned completely new techniques (1/9)
machineplaying.org
Preston Hess retweeted
What happens when a former MIT football captain who majored in computation and cognition + minored in design and music comes to McGovern @mitbrainandcog for his PhD? He builds a speaker room that solves the "cocktail party" problem, of course. 💥
ALT A smiling man stands with arms folded in front of a wall of speakers.
ALT A man in a blue striped shirt inspects a speaker.
Preston Hess retweeted
We never really knew how to train nonlinear RNNs well… BPTT struggled with vanishing grads (no long-range memory) and sequential rollout (hard to parallelizable).
What if instead an oracle told us the optimal memory state m_t at each step? Then the RNN could do one-step supervised learning on (m_t, x_{t+1}) → m_{t+1} labels.
We call this Supervised Memory Training (SMT): a replacement for BPTT that trains RNNs without unrolling them. SMT is time-parallelizable and solves vanishing gradients.
Website: akarshkumar.com/smt/
arXiv: arxiv.org/abs/2606.06479
Preston Hess retweeted
"The Truth Lies Somewhere in the Middle (of the Generated Tokens)"
In autoregressive language models, mean pooling hidden states across generation yields better representations than any token alone.
project page: sophielwang.com/tokens
w/ @phillip_isola and @thisismyhat
Can a simple architectural bias produce human-like selective attention?
We trained a network with multiplicative feature gains from an attention cue and found it reproduces many cocktail party effects, and even predicts new ones!
Loved on working on this with @ianmgriffith
Excited to announce a new paper from our lab, by Ian Griffith @ianmgriffith with help from Preston Hess @phess2, introducing a model of attentional selection. nature.com/articles/s41562-0…
@mitbcs @ScienceMIT @mcgovernmit @SHBTHarvard
Here is a summary. (1/n)
Preston Hess retweeted
New pre-print from our lab, by Lakshmi Govindarajan @lakshming92 with help from Sagarika Alavilli, introducing a new type of model for studying sensory uncertainty. biorxiv.org/content/10.1101/…
Here is a summary. (1/n)
Preston Hess retweeted
Our next paper on comparing dynamical systems (with special interest to artificial and biological neural networks) is out!! Joint work with @AnnHuang42 , as well as @tweetsatpreet , @Leokoz8 , @FieteGroup , and @KanakaRajanPhD : arxiv.org/pdf/2510.25943
Preston Hess retweeted
Over the past year, my lab has been working on fleshing out theory/applications of the Platonic Representation Hypothesis.
Today I want to share two new works on this topic:
Eliciting higher alignment: arxiv.org/abs/2510.02425
Unpaired rep learning: arxiv.org/abs/2510.08492
1/9
Had a ton of fun working on this with @LakerNewhouse @leloykun @anzahorodnii @jxbz @phillip_isola. Check out the paper linked on the second tweet in the thread!
Let’s get it #RollTech
The Engineers welcome another Chicagoland baller to the party -@phess002 from @LoyolaAcademy!
#RollTech🏆🏆🎉
@LAFootballAC @LAGoRamblers
As of this Wednesday I am officially signed! I’m so blessed to have the support and love of everyone who helped me along the way. I want to especially thank my Coaches, Family, and Teammates. Go Engineers! @LAFootballAC @Coach_Brennan @bbubna @MITFootball
Preston Hess retweeted
.@LAGoRamblers celebrated Signing Day Wednesday by honoring 15 student-athletes who signed their National Letters of Intent to the colleges they'll be playing at next year.
wilmettebeacon.com/p/sports-…
