_jacobprince_ Profile Banner
Jacob Prince Profile
Jacob Prince

@_jacobprince_

Followers
453
Following
2K
Media
17
Statuses
188

4th-year PhD candidate studying neuroAI @ Harvard with @talia_konkle and @grez72. Vision, DNNs, fMRI, behavior. Previously @TarrLab, CMU. Avid musician 🎹

Cambridge, MA
Joined May 2019
Don't wanna be here? Send us removal request.
@Napoolar
Thomas Fel
28 days
Synthesizing these observations, we propose a refined view, motivated by Gärdenfors' theory and attention geometry. Activations = multiple convex hulls simultaneously: a rabbit among animals, brown among colors, fluffy among textures. The Minkowski Representation Hypothesis.
1
2
21
@Napoolar
Thomas Fel
28 days
🕳️🐇Into the Rabbit Hull – Part II Continuing our interpretation of DINOv2, the second part of our study concerns the geometry of concepts and the synthesis of our findings toward a new representational phenomenology: the Minkowski Representation Hypothesis
5
68
381
@isabelpapad
Isabel Papadimitriou
29 days
I shared an office with Thomas for a year and saw it with my own eyes: truly never have I seen so much work and original thought go into one interpretability paper
@Napoolar
Thomas Fel
29 days
🕳️🐇Into the Rabbit Hull – Part I (Part II tomorrow) An interpretability deep dive into DINOv2, one of vision’s most important foundation models. And today is Part I, buckle up, we're exploring some of its most charming features.
1
15
170
@Napoolar
Thomas Fel
29 days
🕳️🐇Into the Rabbit Hull – Part I (Part II tomorrow) An interpretability deep dive into DINOv2, one of vision’s most important foundation models. And today is Part I, buckle up, we're exploring some of its most charming features.
10
120
642
@GretaTuckute
Greta Tuckute
1 month
Why are some words and sentences easier to remember than others? Two of our papers covered by @MIT News today: we found that unambiguous words with few or no synonyms ("Pineapple") and sentences with distinctive meanings (“Every cloud has a blue lining”) are most memorable!
@mcgovernmit
McGovern Institute
1 month
Words and sentences that are highly dissimilar from anything we’ve seen before are more likely to be remembered accurately, according to research from @ev_fedorenko @GretaTuckute @bj_mdn @thomashikaru @LanguageMIT. https://t.co/8KyOqv9LEA @mitbrainandcog @ScienceMIT
1
5
30
@hsteven9
Steven scholte
2 months
🧠 New preprint: Why do deep neural networks predict brain responses so well? We find a striking dissociation: it’s not shared object recognition. Alignment is driven by sensitivity to texture-like local statistics. 📊 Study: n=57, 624k trials, 5 models https://t.co/GSowf8JYUA
3
19
47
@Napoolar
Thomas Fel
3 months
Check out @fenildoshi009's work! Love the 20° tuning finding: models finetuned at this curvature generalize to unseen curvatures, rediscovering the old Geisler results from visual neuroscience! 👀
@fenildoshi009
Fenil Doshi
3 months
🧵 Can a purely feedforward network — with no recurrence or lateral connections — capture human-like perceptual organization? 🤯 Yes! Especially for contour integration, and we pinpoint the key inductive biases. New paper in @PLOSCompBiol with @talia_konkle & @grez72! 1/24
0
4
20
@fenildoshi009
Fenil Doshi
3 months
🧵 Can a purely feedforward network — with no recurrence or lateral connections — capture human-like perceptual organization? 🤯 Yes! Especially for contour integration, and we pinpoint the key inductive biases. New paper in @PLOSCompBiol with @talia_konkle & @grez72! 1/24
2
20
117
@GretaTuckute
Greta Tuckute
3 months
Humans largely learn language through speech. In contrast, most LLMs learn from pre-tokenized text. In our #Interspeech2025 paper, we introduce AuriStream: a simple, causal model that learns phoneme, word & semantic information from speech. Poster P6, Aug 19 at 13:30, Foyer 2.2!
8
32
193
@GretaTuckute
Greta Tuckute
3 months
0
14
78
@Napoolar
Thomas Fel
4 months
Chatted with Le Monde about interpretability and sparse autoencoders. (Yes, SAE made it into mainstream news 😅) https://t.co/ondoORjzlW Merci à Nicolas Six pour l’échange !
Tweet card summary image
lemonde.fr
Les rouages des robots conversationnels demeurent très opaques, mais des chercheurs commencent à localiser les « neurones » qui stockent les informations et prennent des décisions-clés.
4
9
57
@t_andy_keller
Andy Keller
4 months
Why do video models handle motion so poorly? It might be lack of motion equivariance. Very excited to introduce: Flow Equivariant RNNs (FERNNs), the first sequence models to respect symmetries over time. Paper: https://t.co/dkk43PyQe3 Blog: https://t.co/I1gpam1OL8 1/🧵
8
72
396
@GretaTuckute
Greta Tuckute
4 months
Very excited to be joining the Kempner Institute this fall—and to be part of this amazing cohort and the broader Kempner/Harvard community! Please don’t hesitate to get in touch!
@KempnerInst
Kempner Institute at Harvard University
4 months
Thrilled to announce the 2025 recipients of #KempnerInstitute Research Fellowships: Elom Amemastro, Ruojin Cai, David Clark, Alexandru Damian, William Dorrell, Mark Goldstein, Richard Hakim, Hadas Orgad, Gizem Ozdil, Gabriel Poesia, & Greta Tuckute! https://t.co/mbFOsLFdNw
7
5
100
@Napoolar
Thomas Fel
4 months
🧠 Submit to CogInterp @ NeurIPS 2025! Bridging AI & cognitive science to understand how models think, reason & represent. CFP + details 👉
@CogInterp
CogInterp Workshop @ NeurIPS 2025
4 months
We’re excited to announce the first workshop on CogInterp: Interpreting Cognition in Deep Learning Models @ NeurIPS 2025! 📣 How can we interpret the algorithms and representations underlying complex behavior in deep learning models? 🌐 https://t.co/sKn7LYWtR7 1/
0
8
32
@unireps
UniReps
4 months
📢 We're thrilled to announce that the UniReps workshop will return to @NeurIPSConf 25 for its 3rd edition! 🔵Check our new Call for Papers at: https://t.co/i0lGs0DQXm 🔴Submit your work (Proceedings or Extended Abstracts) at: https://t.co/9fZzZvgi9M See you in San Diego!🌴🇺🇸
1
14
42
@Napoolar
Thomas Fel
4 months
Check out this amazing work by @fenildoshi009 on shape holistic processing in vision models! 🍀
@fenildoshi009
Fenil Doshi
4 months
🧵 What if two images have the same local parts but represent different global shapes purely through part arrangement? Humans can spot the difference instantly! The question is can vision models do the same? 1/15
1
6
36
@fenildoshi009
Fenil Doshi
4 months
🧵 What if two images have the same local parts but represent different global shapes purely through part arrangement? Humans can spot the difference instantly! The question is can vision models do the same? 1/15
5
123
606
@KempnerInst
Kempner Institute at Harvard University
5 months
The Kempner Institute congratulates its research fellows Isabel Papadimitriou (@isabelpapad) and Jenn Hu (@_jennhu) for their faculty appointments (@UBCLinguistics & @JHUCogSci) and celebrates their innovative research. Read more here: https://t.co/Uw0mU42ZUS #AI #LLMs
Tweet card summary image
kempnerinstitute.harvard.edu
As members of the first two cohorts of research fellows at the Kempner Institute, Jennifer Hu and Isabel Papadimitriou both arrived at Harvard to pursue research that advances the field […]
0
6
28
@nmblauch
Nick Blauch
5 months
What shapes the topography of high-level visual cortex? Excited to share a new pre-print addressing this question with connectivity-constrained interactive topographic networks, titled "Retinotopic scaffolding of high-level vision", w/ Marlene Behrmann & David Plaut. 🧵 ↓ 1/n
4
30
87
@nmblauch
Nick Blauch
6 months
This workshop is going to be properly epic...very honored to be included among the speakers
@dyamins
Daniel Yamins
6 months
Come to our CCN workshop! Blending iophysical constraints and neural networks. Topographical ANNs + and much more. @meenakshik93 @talia_konkle @PouyaBashivan @nmblauch @TimKietzmann @GwilliamsL @apurvaratan @jakhmack @Pieters_Tweet @martin_schrimpf Andrew Miri Nabil Imam
0
4
14