Ehsan Pajouheshgar
@Esychology
Followers
152
Following
1K
Media
23
Statuses
97
Postdoc researcher. Working on Neural Cellular Automata and Self-Organizing Systems. PhD from EPFL
Switzerland
Joined February 2022
✨ I'm excited to share our joint work with Google Research titled “Mesh Neural Cellular Automata” appearing in SIGGRAPH 2024. MeshNCA can directly synthesize dynamic textures on 3D meshes in real time, without UV maps. https://t.co/8lNDCniDOE (1/n) @xuyitao5 @zzznah @eyvindn
5
27
167
Sharing an interesting recent conversation on AI's impact on the economy. AI has been compared to various historical precedents: electricity, industrial revolution, etc., I think the strongest analogy is that of AI as a new computing paradigm (Software 2.0) because both are
555
2K
13K
Andrew Wiles on the morning he discovered how to fix his proof of Fermat's Last Theorem
475
2K
13K
Your base model is kind of a secret genius, but in a *much stronger* sense than this paper suggests... this is the whole idea of the implicit knowledge in our paper
arxiv.org
Large Language Models (LLMs) define probability measures on text. By considering the implicit knowledge question of what it means for an LLM to know such a measure and what it entails...
Holy shit… Harvard just proved your base model might secretly be a genius. 🤯 Their new paper “Reasoning with Sampling” shows that you don’t need reinforcement learning to make LLMs reason better. They used a 'Markov chain sampling trick' that simply re-samples from the
0
9
41
hey look, an AI artist got hurt because somebody stole his prompt
Never do this: Passing off someone else’s work as your own. This Grok Imagine effect with the day-to-night transition was created by me — and I’m pretty sure that person knows it. To make things worse, their copy has more impressions than my original post. Not cool 👎
1K
24K
314K
Self-replication and Computational Universality.
arxiv.org
Self-replication is central to all life, and yet how it dynamically emerges in physical, non-equilibrium systems remains poorly understood. Von Neumann's pioneering work in the 1940s and...
1
15
78
Exploring the Landscape of Non-Equilibrium Memories with Neural Cellular Automata.
arxiv.org
We investigate the landscape of many-body memories: families of local non-equilibrium dynamics that retain information about their initial conditions for thermodynamically long time scales, even...
0
3
6
This 1998 paper is, without question, one of the most beautiful in the history of biology. It answers two questions: First, how does a potassium channel let in K+ ions while excluding Na+ ions? And second, how does it funnel 100 million of those ions through each second? These
27
251
1K
In 2023, a few of my @Google Paradigms of Intelligence colleagues and I set out to explore how often life will emerge in a universe capable of computation.
2
10
58
🚀 New preprint! ARC-NCA shows how Neural Cellular Automata —incl. memory-rich EngramNCA—crack tasks from the ARC-AGI benchmark, hitting GPT-4.5-level accuracy at a fraction of the cost. 🌱🤖 Web: https://t.co/e5iWq1jf16 Preprint: https://t.co/ltm4RPM9Zy
#NeuroAI #AGI #CA #ALIFE
24
47
194
@stevelauda_ I'm not making the effort to understand what's going on here but I see my work without me being mentioned (and the other one is by me too) https://t.co/6TMskqilRe
1
8
108
fascinating how everyday we come closer to this.🦾🦾
104
422
4K
The good idea comes when one person feels comfortable enough to say something that might make them look stupid and their friend is open enough to recognize its potential.
17
417
2K
It has not been reported much, but I believe ETH Zurich has, as of last week, banned new Master and PhD students who attended a long list of universities in China, Russia, and Iran. 🧵
25
73
452
🚨 PhD Opportunity! 🚨 I'm accepting PhD students for Spring and Autumn 2025! International applicants welcome—funding available! Work on computer vision and optimization. Interested? Reach out! 👇 🔗 https://t.co/wIO4IqKPxZ
#PhDPosition #ComputerVision #ResearchOpportunity
researchportal.bath.ac.uk
2
5
15
I've seen claims online that tardigrades can live for 30 years without food or water. A Nat Geo article says this, without attribution. My initial reaction was that this must be an estimate. Why would anyone wait 30 years to figure this out? But Japanese scientists actually did.
36
264
2K
Very interesting and unintuitive things happen at low Reynolds numbers. Strongly suggest this read.
30 Essays to Make You Love Biology Day 4. "Life at low Reynolds number," by E.M. Purcell. This essay taught me about the weirdness of life at the microscale, where "inertia plays no role whatsoever." "We know that F = ma, but [microbes] could scarcely care less."
0
0
2