Ndea

@ndea • 11,382 subscribers

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

Shorts

Deep Learning architectures usually aren't trained to perform search at test time, leading to sample inefficiency + poor generalization. Latent Program Network (LPN) builds in test-time adaption by learning a latent space that can be searched. Clem Bonnet matt

Deep Learning architectures usually aren't trained to perform search at test time, leading to sample inefficiency + poor generalization. Latent Program Network (LPN) builds in test-time adaption by learning a latent space that can be searched. Clem Bonnet matt

30,803 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

"We are trying to build a new branch of machine learning. An alternative to Deep Learning itself...building something that we call Symbolic Descent." François Chollet joins the Y Combinator Lightcone podcast to share about our research at Ndea and the launch of ARC-AGI-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." François Chollet joins the Y Combinator Lightcone podcast to share about our research at Ndea and the launch of ARC-AGI-3.

65,196 views • 5 months ago

On the pod: "Constrained Adaptive Rejection Sampling" with UCSD CSE professor Loris D'Antoni. Hear how symbolic AI experts have navigated the LLM era and why the future of AI code generation depends on program synthesis and formal methods.

On the pod: "Constrained Adaptive Rejection Sampling" with UCSD CSE professor Loris D'Antoni. Hear how symbolic AI experts have navigated the LLM era and why the future of AI code generation depends on program synthesis and formal methods.

17,982 views • 2 months ago

On the pod: our most-requested guest! Kevin Ellis from Cornell University 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.

On the pod: our most-requested guest! Kevin Ellis from Cornell University 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.

27,551 views • 5 months ago

On the pod: Machine Learning Street Talk's paper "Why Creativity Cannot Be Interpolated" with Tim Scarfe + Dr. Jeremy Budd. A deep dive into creativity, understanding, neuro-symbolic AI, human-AI collaboration, and how systems capable of extending their own phylogeny could become creative.

On the pod: Machine Learning Street Talk's paper "Why Creativity Cannot Be Interpolated" with Tim Scarfe + Dr. Jeremy Budd. A deep dive into creativity, understanding, neuro-symbolic AI, human-AI collaboration, and how systems capable of extending their own phylogeny could become creative.

11,151 views • 2 months ago

Vision-language models (VLMs) can see well, but they struggle to reason. In this episode, Antonia Wüst (PhD researcher, TU Darmstadt) explains how combining VLMs with program synthesis yields more reliable visual reasoning, with fewer tokens than chain-of-thought.

Vision-language models (VLMs) can see well, but they struggle to reason. In this episode, Antonia Wüst (PhD researcher, TU Darmstadt) explains how combining VLMs with program synthesis yields more reliable visual reasoning, with fewer tokens than chain-of-thought.

22,130 views • 8 months ago

The Surprising Performance Drivers of HRM. A paper talk from Ndea AI researcher Konstantin Schürholt. We ran a series of ablation studies to determine what factors had the biggest impact on the Hierarchical Reasoning Model's performance on ARC-AGI.

The Surprising Performance Drivers of HRM. A paper talk from Ndea AI researcher Konstantin Schürholt. We ran a series of ablation studies to determine what factors had the biggest impact on the Hierarchical Reasoning Model's performance on ARC-AGI.

29,275 views • 1 year ago

Introducing the Ndea podcast - Abstract Synthesis. Hear the stories behind interesting academic papers in the world of program synthesis. Episode 1 features Mark Santolucito, Barnard College/Columbia University, discussing his paper "Grammar Filtering for Syntax-Guided Synthesis".

Introducing the Ndea podcast - Abstract Synthesis. Hear the stories behind interesting academic papers in the world of program synthesis. Episode 1 features Mark Santolucito, Barnard College/Columbia University, discussing his paper "Grammar Filtering for Syntax-Guided Synthesis".

15,917 views • 9 months ago

No more content to load