À PROPOS DE CE PODCAST 🔗
Go beyond the paper abstract to synthesize new ideas. AGI research lab Ndea presents the stories behind remarkable academic papers in the field of program synthesis.
Animateurs :
Fréquence de mise à jour:
biweekly
Durée audio moyenne:
48 minutes
Entretiens avec des invités
Anglais
États-Unis
16 épisodes
depuis 15 décembre 2025
episodic
DERNIER ÉPISODE 🔗
Jeremy Budd, Assistant Professor at the University of Birmingham, and Tim Scarfe, CEO of Machine Learning Street Talk, discuss the paper “Why Creativity Cannot Be Interpolated”, which argues that genuine creativity requires respect for constraints that today’s AI lacks.
Building on ideas from Fran…
RECHERCHER LES ÉPISODES PASSÉS
Rechercher les épisodes précédents de Abstract Synthesis.
ÉPISODES PRÉCÉDENTS 🔗
Loris D’Antoni, Professor of Computer Science and Engineering at UC San Diego, discusses his paper “Constrained Adaptive Rejection Sampling,” which introduces a constrained decoding algorithm that preserves the original language model distribution while satisfying formal constraints, enabling highe…
Stephen Muggleton, Emeritus Professor at Imperial College London, discusses his paper “Inductive Logic Programming”, which introduced and named the field. The paper presents a framework that combines logic programming with machine learning, enabling systems to learn interpretable logical rules from…
Aws Albarghouthi, Associate Professor of Computer Science at the University of Wisconsin-Madison, discusses his paper “Recursive Program Synthesis”, which introduced Escher, an inductive synthesis algorithm for learning recursive programs from input-output examples.
The project emerged from Albarg…
Kevin Ellis, Assistant Professor at Cornell University, discusses his influential paper “DreamCoder,” which presents a system that jointly learns reusable program abstractions and a neural search strategy through an iterative wake-sleep process.
The work emerged from early efforts in library learn…
Gust Verbruggen, Senior AI researcher and member of the PROSE team at Microsoft, discusses his paper "Semantic Programming by Example with Pre-trained Models," which introduces a framework for integrating inductive program synthesis with large language models.
The project emerged from an…
Program synthesis is the problem of automatically generating code that satisfies a specification. The real challenge isn’t searching faster, it’s making the right parts of the search space searchable at all.
This week's episode is a short recap of the podcast so far. Across the past 8 conversation…
The way a problem is represented can determine whether it is solvable at all.
Céline Hocquette, AI researcher at Ndea and former postdoctoral researcher at the University of Oxford, discusses her paper “Relational Decomposition for Program Synthesis”, which introduces a representation-driven appro…
Wasu "Top" Piriyakulkij, PhD student at Cornell University advised by Kevin Ellis, discusses his paper "PoE-World: Compositional World Modeling with Products of Programmatic Experts." The episode explores how symbolic, programmatic world models can achieve strong generalization …
Antonia Wüst, PhD student at TU Darmstadt, discusses her paper "Synthesizing Visual Concepts as Vision-Language Programs," which introduces a neurosymbolic approach to visual concept induction by combining vision-language models with program synthesis.
The work grew out of Wüst’s early P…
Avertissement: Le podcast et les illustrations intégrés sur cette page proviennent de Ndea, qui est la propriété de son propriétaire et n'est ni affilié ni approuvé par Listen Notes, Inc.
MOTEUR DE RECHERCHE DE PODCASTS
Vous pouvez utiliser notre site Web pour rechercher des podcasts3,821,571et des épisodes195,377,324par personnes, lieux ou sujets.
If I have seen further than others, it is by listening to podcasts and standing upon the shoulders of
giants.
‐ Isaac "Llamacorn" Newton
RECHERCHER LES ÉPISODES PASSÉS
Rechercher les épisodes précédents de Abstract Synthesis.
DEMANDER CE PODCAST
Why to claim podcasts?
If you are a podcaster, the best way to manage your podcasts on Listen Notes is by claiming your Listen Notes
podcast pages.
It is a great, free way to engage the podcast community and increase the visibility of your podcasts.
After claiming your Listen Notes podcast pages, you will be able to:
✓
Manually refresh the RSS feed to sync up
✓
Get a verified badge (
✓
) alongside with your podcast name on Listen Notes
✓
Post petites annonces for sponsorship,
guests, co-hosts,
cross-promotion...
✓
Respond to listener comments on Listen Notes
✓
Use speech-to-text techniques to transcribe your show and
edit transcripts
✓
Improve the presence of your podcasts, e.g., self-service
interview de podcasteur...
✓
If you share your Listen Notes page and at-mention @ListenNotes
on X (formerly Twitter),
notre compte officiel sur X (anciennement Twitter) will retweet to promote
your show to our followers.
Coming soon:
◯ Self-service promotion on Listen Notes
◯ Track your podcast stats on Listen
Notes, e.g., listens, page
views...
◯ Manage episodes
MODIFIER
Merci de nous avoir aidé à tenir la base de données de podcasts à jour.
