Ndea (@ndea) / X

Ndea

111 posts

Ndea

@ndea

A new intelligence science lab founded by @fchollet & @mikeknoop. Deep Learning-guided Program Synthesis. We're hiring.

Joined October 2024

Ndea
@ndea
Jun 18
On the pod: "Inductive Logic Programming" with Stephen Muggleton, Emeritus Professor at @imperialcollege. What does it take to invent an entirely new field of AI? From Turing to Michie to McCarthy - the journey to creating ILP, combining logic programming with machine learning.
00:00
1.6K
Ndea
@ndea
Jun 18
Watch the full interview:
923
Ndea
@ndea
May 27
On the pod: "Recursive Program Synthesis" with @awsTO, Associate Professor at @WisconsinCS. How cold-emailing @SumitGulwani at Microsoft Research led to a novel research paper and inside Aws' vision to automatically synthesize the software stack for future quantum computers.
00:00
3.4K
Ndea
@ndea
May 27
Watch the full interview:
2K
Ndea
@ndea
Apr 7
On the pod: our most-requested guest! @ellisk_kellis from @Cornell shares the origins of his influential neurosymbolic paper "DreamCoder". Plus: program synthesis, wake-sleep library learning, world models, running an AI research lab, and more.
00:00
27K
Ndea
@ndea
Apr 7
Watch the full interview:
5.8K
Ndea reposted
ARC Prize
@arcprize
Apr 6
Francois Chollet + Sam Altman Fireside @fchollet and @sama fireside during ARC-AGI-3 Launch Party moderated by @deedydas They discuss: - Social contracts evolving - AGI views as a parent - When will labs score >85% on ARC-AGI-3?
00:00
33K
Ndea
@ndea
Apr 3
"We are trying to build a new branch of machine learning. An alternative to Deep Learning itself...building something that we call Symbolic Descent." @fchollet joins the @ycombinator Lightcone podcast to share about our research at Ndea and the launch of ARC-AGI-3.
00:00
65K
Ndea
@ndea
Apr 3
Watch the full episode:
3.6K
Ndea reposted
Y Combinator
@ycombinator
Mar 27
François Chollet (@fchollet) has spent years asking a different question than most of the AI world. Instead of scaling what already works, he’s trying to understand what intelligence actually is and how to build it from first principles. In this episode of the @LightconePod, he
00:00
151K
Ndea
@ndea
Mar 3
AI researcher @pidgeyusedgust of @ProseMsft joins us on the pod to discuss his favorite paper, "Semantic Programming by Example with Pre-trained Models" - a neurosymbolic framework where Flash Fill meets GPT-3. Symbolic for structure (syntactic), LLMs for meaning (semantic).
00:00
5.8K
Ndea
@ndea
Mar 3
Watch the full interview: youtu.be/UyWSvLgQMDE
4.4K
Ndea
@ndea
Feb 10
New open role: Technical Staff - Search Guidance Accelerate science & innovation. Join our small, talent-dense, globally remote team. Apply your RL/DL search expertise to the most advanced program synthesis system. Also: $10k referral bonus Details:
Join Ndea - Technical Staff - Search Guidance
From ndea.com
16K
Ndea
@ndea
Feb 9
In the past 8 episodes of the Abstract Synthesis podcast, we've covered grammar filtering, temporal synthesis, inductive logic programming, vision-language programs, and symbolic world models. This week, we step back to reflect on 3 emergent themes.
3.8K
Ndea
@ndea
Feb 9
Watch the mini-recap episode: youtu.be/t_RgBe2CVms Subscribe + share your feedback!
3.4K
Ndea
@ndea
Feb 2
"...simply looking at a problem differently can greatly improve learning performance." New pod: Ndea researcher & ILP expert @CelineHocquette on "Relational Decomposition for Program Synthesis" - making symbolic learning systems more efficient without domain-specific knowledge.
00:00
3.4K
Ndea
@ndea
Feb 2
Watch the full episode:
3.3K
Ndea
@ndea
Jan 26
On the pod: @topwasu from @ellisk_kellis' lab at @Cornell discusses his paper PoE-World. We explore how symbolic world models can achieve strong generalization and sample efficiency by composing many small causal programs instead of learning a single monolithic model.
00:00
3K
Ndea
@ndea
Jan 26
Watch the full episode:
2.7K
Ndea
@ndea
Jan 19
Vision-language models (VLMs) can see well, but they struggle to reason. In this episode, @toniwuest (PhD researcher, @TUDarmstadt) explains how combining VLMs with program synthesis yields more reliable visual reasoning, with fewer tokens than chain-of-thought.
00:00
22K
Ndea
@ndea
Jan 19
Dive into the paper, "Synthesizing Visual Concepts as Vision-Language Programs". A neuro-symbolic approach to visual concept induction that treats VLMs as perceptual tools inside symbolic programs. Watch the full episode: youtu.be/uefqvsButp8
3.3K