Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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".

ndea's profile picture

Ndea

10,801 subscribers

15,917 Aufrufe • vor 8 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

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.
1:16

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.

Ndea

26,937 Aufrufe • vor 4 Monaten

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.
0:58

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.

Ndea

16,724 Aufrufe • vor 1 Monat

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.
0:46

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.

Ndea

22,130 Aufrufe • vor 7 Monaten

New paper: World models + Program synthesis by Wasu Top Piriyakulkij 1. World modeling on-the-fly by synthesizing programs w/ 4000+ lines of code 2. Learns new environments from minutes of experience 3. Positive score on Montezuma's Revenge 4. Compositional generalization to new environments [1/n]
0:49

New paper: World models + Program synthesis by Wasu Top Piriyakulkij 1. World modeling on-the-fly by synthesizing programs w/ 4000+ lines of code 2. Learns new environments from minutes of experience 3. Positive score on Montezuma's Revenge 4. Compositional generalization to new environments [1/n]

Kevin Ellis

58,751 Aufrufe • vor 1 Jahr

Our brain-to-voice synthesis brain-computer interface paper was published in nature today! This neuroprosthesis synthesized the voice of a man with ALS instantaneously, enabling him to ‘speak’ flexibly and modulate the prosody of his BCI-voice. 1/7 Paper:
1:04

Our brain-to-voice synthesis brain-computer interface paper was published in nature today! This neuroprosthesis synthesized the voice of a man with ALS instantaneously, enabling him to ‘speak’ flexibly and modulate the prosody of his BCI-voice. 1/7 Paper:

Maitreyee Wairagkar

58,428 Aufrufe • vor 1 Jahr

For our next Mr. Bill Podcast, we have Steve Duda, owner of XFer Records & creator of Serum. We're excited to explore his latest—Serum 2, a next-generation synthesis engine, out now. Head to for the full episode.
0:59

For our next Mr. Bill Podcast, we have Steve Duda, owner of XFer Records & creator of Serum. We're excited to explore his latest—Serum 2, a next-generation synthesis engine, out now. Head to for the full episode.

Mr. Bill

54,537 Aufrufe • vor 1 Jahr

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.
38:19

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.

Ndea

29,253 Aufrufe • vor 1 Jahr

DisCo: Disentangled Control for Referring Human Dance Generation in Real World paper page: Generative AI has made significant strides in computer vision, particularly in image/video synthesis conditioned on text descriptions. Despite the advancements, it remains challenging especially in the generation of human-centric content such as dance synthesis. Existing dance synthesis methods struggle with the gap between synthesized content and real-world dance scenarios. In this paper, we define a new problem setting: Referring Human Dance Generation, which focuses on real-world dance scenarios with three important properties: (i) Faithfulness: the synthesis should retain the appearance of both human subject foreground and background from the reference image, and precisely follow the target pose; (ii) Generalizability: the model should generalize to unseen human subjects, backgrounds, and poses; (iii) Compositionality: it should allow for composition of seen/unseen subjects, backgrounds, and poses from different sources. To address these challenges, we introduce a novel approach, DISCO, which includes a novel model architecture with disentangled control to improve the faithfulness and compositionality of dance synthesis, and an effective human attribute pre-training for better generalizability to unseen humans. Extensive qualitative and quantitative results demonstrate that DISCO can generate high-quality human dance images and videos with diverse appearances and flexible motions.
0:29

DisCo: Disentangled Control for Referring Human Dance Generation in Real World paper page: Generative AI has made significant strides in computer vision, particularly in image/video synthesis conditioned on text descriptions. Despite the advancements, it remains challenging especially in the generation of human-centric content such as dance synthesis. Existing dance synthesis methods struggle with the gap between synthesized content and real-world dance scenarios. In this paper, we define a new problem setting: Referring Human Dance Generation, which focuses on real-world dance scenarios with three important properties: (i) Faithfulness: the synthesis should retain the appearance of both human subject foreground and background from the reference image, and precisely follow the target pose; (ii) Generalizability: the model should generalize to unseen human subjects, backgrounds, and poses; (iii) Compositionality: it should allow for composition of seen/unseen subjects, backgrounds, and poses from different sources. To address these challenges, we introduce a novel approach, DISCO, which includes a novel model architecture with disentangled control to improve the faithfulness and compositionality of dance synthesis, and an effective human attribute pre-training for better generalizability to unseen humans. Extensive qualitative and quantitative results demonstrate that DISCO can generate high-quality human dance images and videos with diverse appearances and flexible motions.

AK

161,479 Aufrufe • vor 3 Jahren

"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.
2:02

"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.

Ndea

65,046 Aufrufe • vor 4 Monaten

Exciting news from KAIMRC! Our Drug Discovery Program has just published a paper entitled “First-in-class inhibitors of Nsp15 endoribonuclease of SARS-CoV-2: modeling, synthesis, and enzymatic assay of thiazolidinedione and rhodanine analogs” in JBC, one of the world’s leading scientific journals. All work was done exclusively at KAIMRC — from concept to product. Watch the video for highlights and read the full paper here: #DrugDiscovery #COVID19Research #SARSCoV2 #AntiviralTherapeutics #Nsp15Inhibitors #KAIMRCResearch #ScienceInnovation #JBCPublication
1:33

Exciting news from KAIMRC! Our Drug Discovery Program has just published a paper entitled “First-in-class inhibitors of Nsp15 endoribonuclease of SARS-CoV-2: modeling, synthesis, and enzymatic assay of thiazolidinedione and rhodanine analogs” in JBC, one of the world’s leading scientific journals. All work was done exclusively at KAIMRC — from concept to product. Watch the video for highlights and read the full paper here: #DrugDiscovery #COVID19Research #SARSCoV2 #AntiviralTherapeutics #Nsp15Inhibitors #KAIMRCResearch #ScienceInnovation #JBCPublication

KAIMRC كيمارك

79,452 Aufrufe • vor 1 Jahr

Drumroll… Introducing ‘Story of a Song’, a new segment on my channel where the idea is to choose ONE song and unpack the stories behind it. Episode 1 features composer Leon James and his stories about the utterly gorgeous Vazhithunaye from Dragon. Coming up this evening.
0:52

Drumroll… Introducing ‘Story of a Song’, a new segment on my channel where the idea is to choose ONE song and unpack the stories behind it. Episode 1 features composer Leon James and his stories about the utterly gorgeous Vazhithunaye from Dragon. Coming up this evening.

Sudhir Srinivasan

13,445 Aufrufe • vor 2 Monaten

Elon nails exactly what's wrong with education here and what needs to change. You may not know he actually started a remarkable school at SpaceX for his kids based on his principles... The school was called Ad Astra, Latin for “to the stars”. Elon hired Josh Dahn to build and run the school. When Elon’s kids graduated, Josh and I cofounded Synthesis together. Our goal is to take the best parts of the SpaceX school and make them accessible to everyone. Elon famously follows a “first principles” approach. The primary principle of the school: A good education should produce people who can SOLVE PROBLEMS — real, complex problems with a team. Like how to colonize Mars. Not fake school worksheet problems. This principle was embodied in a class at the school called “Synthesis”. In the class, kids worked in teams to solve problems via complex games and simulations. The skills they build in Synthesis — working with a team, making tradeoffs, risk assessment and critical thinking — are the foundational skills they’ll need to solve problems in any domain. 1/2
1:32

Elon nails exactly what's wrong with education here and what needs to change. You may not know he actually started a remarkable school at SpaceX for his kids based on his principles... The school was called Ad Astra, Latin for “to the stars”. Elon hired Josh Dahn to build and run the school. When Elon’s kids graduated, Josh and I cofounded Synthesis together. Our goal is to take the best parts of the SpaceX school and make them accessible to everyone. Elon famously follows a “first principles” approach. The primary principle of the school: A good education should produce people who can SOLVE PROBLEMS — real, complex problems with a team. Like how to colonize Mars. Not fake school worksheet problems. This principle was embodied in a class at the school called “Synthesis”. In the class, kids worked in teams to solve problems via complex games and simulations. The skills they build in Synthesis — working with a team, making tradeoffs, risk assessment and critical thinking — are the foundational skills they’ll need to solve problems in any domain. 1/2

Chrisman

408,221 Aufrufe • vor 2 Jahren

We asked Chrisman, the 1st hire at ClassDojo, about the lore of Synthesis. "5 years ago, I visited the school Elon Musk made for SpaceX families and his own kids." "His partner Josh Dahn became a friend of mine, and we ended up scaling up the best parts of that school." "The kids are just working together to solve problems, in the form of games. We put that on the Internet (with an AI tutor) and signed up kids from all over the world."
1:12

We asked Chrisman, the 1st hire at ClassDojo, about the lore of Synthesis. "5 years ago, I visited the school Elon Musk made for SpaceX families and his own kids." "His partner Josh Dahn became a friend of mine, and we ended up scaling up the best parts of that school." "The kids are just working together to solve problems, in the form of games. We put that on the Internet (with an AI tutor) and signed up kids from all over the world."

TBPN

24,773 Aufrufe • vor 1 Jahr

🌟Introducing🎻Violin — an Open-source Video Translation Skill. 📹Video is the dominant medium on the internet, yet most high-quality content (lecture, talk, podcast) is locked behind a single language, leaving global audiences behind. So we built Violin: a video skill that combines speech recognition, LLM translation, and speech synthesis into one seamless pipeline. 🌐 Demo: 📝 Blog: 🔗 GitHub: ✨Key Features: 🎙️High-quality multilingual ASR & Translation & TTS. 🗣️Personalize translation & voice (turn an academic talk into something children can follow). 💬Chat with the video — ask any questions grounded in the video. 🧩Support Web app, CLI, and Agent skill 🍃Fully open-source under MIT. ❤️Built with the wonderful Shang Zhu and advised by James Zou ! All features powered by Together AI . Try it and let us know what you think! 🎻
0:41

🌟Introducing🎻Violin — an Open-source Video Translation Skill. 📹Video is the dominant medium on the internet, yet most high-quality content (lecture, talk, podcast) is locked behind a single language, leaving global audiences behind. So we built Violin: a video skill that combines speech recognition, LLM translation, and speech synthesis into one seamless pipeline. 🌐 Demo: 📝 Blog: 🔗 GitHub: ✨Key Features: 🎙️High-quality multilingual ASR & Translation & TTS. 🗣️Personalize translation & voice (turn an academic talk into something children can follow). 💬Chat with the video — ask any questions grounded in the video. 🧩Support Web app, CLI, and Agent skill 🍃Fully open-source under MIT. ❤️Built with the wonderful Shang Zhu and advised by James Zou ! All features powered by Together AI . Try it and let us know what you think! 🎻

Kevin Lin

139,215 Aufrufe • vor 3 Monaten

#Binance just hit 250M users! What’s next for crypto in 2025? 🤔 In the first episode of our Behind Binance podcast, Binance CEO Richard Teng breaks it all down—discussing institutional crypto adoption, the future of Web3, and even tries to predict the price of 1 $BTC this year. Watch now 👉
0:44

#Binance just hit 250M users! What’s next for crypto in 2025? 🤔 In the first episode of our Behind Binance podcast, Binance CEO Richard Teng breaks it all down—discussing institutional crypto adoption, the future of Web3, and even tries to predict the price of 1 $BTC this year. Watch now 👉

Binance

199,155 Aufrufe • vor 1 Jahr

Excited to announce my new weekly podcast "Making Sense of the World" on The Siren Episode 1 features Ahmed Fouad Alkhatib - a Gazan-American leading the charge for a changed perspective on Palestine. His bold views & roadmap to peace are a must listen. Realign For Palestine Atlantic Council
1:13

Excited to announce my new weekly podcast "Making Sense of the World" on The Siren Episode 1 features Ahmed Fouad Alkhatib - a Gazan-American leading the charge for a changed perspective on Palestine. His bold views & roadmap to peace are a must listen. Realign For Palestine Atlantic Council

Joel Rubin

31,490 Aufrufe • vor 1 Jahr

Today, we're joined by Yejin Choi, professor and senior fellow at Stanford University University in the Computer Science Department and Stanford UniversityHAI. In this conversation, we explore Yejin’s recent work on making small language models reason more effectively. We discuss how high-quality, diverse data plays a central role in closing the intelligence gap between small and large models, and how combining synthetic data generation, imitation learning, and reinforcement learning can unlock stronger reasoning capabilities in smaller models. Yejin explains the risks of homogeneity in model outputs and mode collapse highlighted in her “Artificial Hivemind” paper, and its impacts on human creativity and knowledge. We also discuss her team's novel approaches, including reinforcement learning as a pre-training objective, where models are incentivized to “think” before predicting the next token, and "Prismatic Synthesis," a gradient-based method for generating diverse synthetic math data while filtering overrepresented examples. Additionally, we cover the societal implications of AI and the concept of pluralistic alignment—ensuring AI reflects the diverse norms and values of humanity. Finally, Yejin shares her mission to democratize AI beyond large organizations and offers her predictions for the coming year. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 04:44 - "Snowball effect" in AI investments 06:58 - Approaches to smaller models 08:58 - Importance of “better data” 14:07 - Imitation learning 18:24 - Artificial Hivemind paper 25:25 - AI risks 27:50 - Spectrum tuning 28:53 - Future of AI on humanity 33:08 - Reasoning in small models 34:58 - Prismatic Synthesis 48:20 - Reinforcement as a Pretraining Objective 55:04 - Pluralistic alignment 1:03:30 - Predictions
1:05:51

Today, we're joined by Yejin Choi, professor and senior fellow at Stanford University University in the Computer Science Department and Stanford UniversityHAI. In this conversation, we explore Yejin’s recent work on making small language models reason more effectively. We discuss how high-quality, diverse data plays a central role in closing the intelligence gap between small and large models, and how combining synthetic data generation, imitation learning, and reinforcement learning can unlock stronger reasoning capabilities in smaller models. Yejin explains the risks of homogeneity in model outputs and mode collapse highlighted in her “Artificial Hivemind” paper, and its impacts on human creativity and knowledge. We also discuss her team's novel approaches, including reinforcement learning as a pre-training objective, where models are incentivized to “think” before predicting the next token, and "Prismatic Synthesis," a gradient-based method for generating diverse synthetic math data while filtering overrepresented examples. Additionally, we cover the societal implications of AI and the concept of pluralistic alignment—ensuring AI reflects the diverse norms and values of humanity. Finally, Yejin shares her mission to democratize AI beyond large organizations and offers her predictions for the coming year. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 04:44 - "Snowball effect" in AI investments 06:58 - Approaches to smaller models 08:58 - Importance of “better data” 14:07 - Imitation learning 18:24 - Artificial Hivemind paper 25:25 - AI risks 27:50 - Spectrum tuning 28:53 - Future of AI on humanity 33:08 - Reasoning in small models 34:58 - Prismatic Synthesis 48:20 - Reinforcement as a Pretraining Objective 55:04 - Pluralistic alignment 1:03:30 - Predictions

The TWIML AI Podcast

12,141 Aufrufe • vor 6 Monaten

How Much Protein Should You Really Eat Daily? | David Allison, Ph.D. This clip is from episode # 368 of The Drive which was released today (10/13/25). In the full episode, we cover: -Why the protein RDA may be inadequate for most people and how to think about optimal intake -What current evidence shows about muscle protein synthesis and high-protein diets -The limitations and biases of nutrition research, including economic and methodological constraints -How processed and ultra-processed foods fit into the broader discussion of obesity and public health -More Watch or listen (Ep. # 368) to the full episode on my website or your favorite podcast player.
0:41

How Much Protein Should You Really Eat Daily? | David Allison, Ph.D. This clip is from episode # 368 of The Drive which was released today (10/13/25). In the full episode, we cover: -Why the protein RDA may be inadequate for most people and how to think about optimal intake -What current evidence shows about muscle protein synthesis and high-protein diets -The limitations and biases of nutrition research, including economic and methodological constraints -How processed and ultra-processed foods fit into the broader discussion of obesity and public health -More Watch or listen (Ep. # 368) to the full episode on my website or your favorite podcast player.

Peter Attia

97,456 Aufrufe • vor 10 Monaten