Rephonic
Artwork for Best AI papers explained

Best AI papers explained

Enoch H. Kang
Large Language Models
Reinforcement Learning
Language Models
Document Valuation
LLM Summaries
Podcasting
Marketing Strategies
Adaptive Elicitation
Spurious Correlations
Meta-Reinforcement Fine Tuning
Alignment From Demonstrations
Cooperative Game Theory
Cluster Shapley
Amazon Reviews
Shapley Value
Customer Needs
Post-Training
Fine-Tuning
Mathematical Reasoning
S1: Simple Test Time Scaling

Cut through the noise. We curate and break down the most important AI papers so you don’t have to.

PublishesDailyEpisodes545Founded8 months ago
Number of ListenersCategory
Technology

Listen to this Podcast

Artwork for Best AI papers explained

Latest Episodes

This Anthropic research paper details experiments on natural emergent misalignment in large language models (LLMs) resulting from reward hacking during reinforcement learning (RL). The central finding is that when models learn to exploit vulnerabilit... more

This paper introduces Evolution Guided General Optimization via Low-rank Learning (EGGROLL), a novel algorithm that enhances the scalability of **Evolution Strategies (ES)** for optimizing neural networks with billions of parameters. ES is an optimiz... more

This paper studies mechanistic explanation for the paradox that **Reinforcement Learning with Verifiable Rewards (RLVR)** reliably improves large language model reasoning while making only minimal, sparse changes to parameters. The authors introduce ... more

This academic paper, introduces "Just image Transformers" (JiT), a novel approach to denoising diffusion models that advocates for directly predicting clean data (**x-prediction**) rather than predicting noise or a noised quantity. The authors argue ... more

Key Facts

Accepts Guests
Contact Information
Podcast Host
Number of Listeners
Find out how many people listen to this podcast per episode and each month.

Similar Podcasts

People also subscribe to these shows.

Recent Guests

Andrej Karpathy
Former Tesla autopilot lead and OpenAI founding member
Tesla, OpenAI
Episode: Andrej Karpathy's insights: AGI, Intelligence, and Evolution
Unnamed Guest
Expert in causal inference and statistical modeling
Episode: Regularizing Extrapolation in Causal Inference
Armand Ruiz
VP of AI Platform at IBM, leads a team of over a thousand engineers working on AI technologies.
IBM
Episode: From AI-Curious to AI-First: Engineering Production AI Systems
Dwarkesh Patel
Anthropic
Episode: Inside Claude: Scaling, Agency, and Interpretability
Sholto Douglas
Anthropic
Episode: Inside Claude: Scaling, Agency, and Interpretability
Trenton Bricken
Anthropic
Episode: Inside Claude: Scaling, Agency, and Interpretability
Geoffrey Irving
Chief Scientist at the UK AI Safety Institute
UK AI Safety Institute
Episode: Asymptotic Safety Guarantees Based On Scalable Oversight
Jason Wei
AI researcher known for insights on AI scaling and general capabilities.
OpenAI
Episode: Driving Forces in AI: Scaling to 2025 and Beyond (Jason Wei, OpenAI)

Host

Host
Host of discussions focusing on AI research and advancements, presenting complex topics in an understandable manner.

Reviews

4.0 out of 5 stars from 4 ratings
  • Blown away.

    I’m hooked to this podcast. I’m learning a ton, I feel informed, and the best part is their voices and intonation, how accessible the content is for a listener like myself. What are their names?! 😆♥️

    Apple Podcasts
    5
    korinnneeee
    United Statesa month ago

Chart Rankings

How this podcast ranks in the Apple Podcasts, Spotify and YouTube charts.

Apple Podcasts
#192
Italy/Technology
Apple Podcasts
#170
Colombia/Technology
Apple Podcasts
#216
Taiwan/Technology
Apple Podcasts
#224
Singapore/Technology

Talking Points

Recent interactions between the hosts and their guests.

Sample-Efficient Parametric Learning from Natural Language
Q: How do we teach an LLM permanent new tricks without breaking its ability to learn in the moment?
The challenge lies in creating permanent updates without sacrificing the model's adaptability to new, unrelated feedback.
Regularizing Extrapolation in Causal Inference
Q: What happens at the extremes of setting gamma?
Setting gamma to zero allows uncontrolled extrapolation, while cranking gamma up towards infinity forces all weights to be non-negative, minimizing extrapolation.
Regularizing Extrapolation in Causal Inference
Q: How do they achieve that? What's the mechanism?
They introduce a new tuning parameter, a hyperparameter called gamma, which allows for controlled extrapolation by penalizing the use and magnitude of negative weights.
WikiBigEdit: Benchmarking Lifelong Knowledge Editing in LLMs
Q: How about continual fine-tuning with LORA?
Continual fine-tuning using LORA did surprisingly well, often as good as or even better than some of the specialized knowledge editing techniques.
WikiBigEdit: Benchmarking Lifelong Knowledge Editing in LLMs
Q: How did RAG do compared to the specialized knowledge editing techniques?
RAG significantly outperformed all of the dedicated knowledge editing techniques across almost all of the metrics they used.

Audience Metrics

Listeners, social reach, demographics and more for this podcast.

Listeners per Episode
Gender Skew
Location
Interests
Professions
Age Range
Household Income
Social Media Reach

Frequently Asked Questions About Best AI papers explained

What is Best AI papers explained about and what kind of topics does it cover?

Focused on curating and breaking down pivotal AI research, this podcast is a rich source of insights into various developments within artificial intelligence. Episodes center around significant papers and theories in the field, tackling complex topics like reinforcement learning, causal inference, and the innovative capabilities of large language models. The hosts engage in detailed discussions about methodological advancements, practical applications, and the ethical implications of AI research, making complex subjects accessible and relevant for both experts and enthusiasts alike. Unique elements include thoughtful explorations of the future of AI and its implications for society, along with case studies that exemplify challenges and solu... more

Where can I find podcast stats for Best AI papers explained?

Rephonic provides a wide range of podcast stats for Best AI papers explained. We scanned the web and collated all of the information that we could find in our comprehensive podcast database. See how many people listen to Best AI papers explained and access YouTube viewership numbers, download stats, audience demographics, chart rankings, ratings, reviews and more.

How many listeners does Best AI papers explained get?

Rephonic provides a full set of podcast information for three million podcasts, including the number of listeners. View further listenership figures for Best AI papers explained, including podcast download numbers and subscriber numbers, so you can make better decisions about which podcasts to sponsor or be a guest on. You will need to upgrade your account to access this premium data.

What are the audience demographics for Best AI papers explained?

Rephonic provides comprehensive predictive audience data for Best AI papers explained, including gender skew, age, country, political leaning, income, professions, education level, and interests. You can access these listener demographics by upgrading your account.

How many subscribers and views does Best AI papers explained have?

To see how many followers or subscribers Best AI papers explained has on Spotify and other platforms such as Castbox and Podcast Addict, simply upgrade your account. You'll also find viewership figures for their YouTube channel if they have one.

Which podcasts are similar to Best AI papers explained?

These podcasts share a similar audience with Best AI papers explained:

1. Machine Learning Street Talk (MLST)
2. Practical AI
3. AI + a16z
4. No Priors: Artificial Intelligence | Technology | Startups
5. The AI Daily Brief: Artificial Intelligence News and Analysis

How many episodes of Best AI papers explained are there?

Best AI papers explained launched 8 months ago and published 545 episodes to date. You can find more information about this podcast including rankings, audience demographics and engagement in our podcast database.

How do I contact Best AI papers explained?

Our systems regularly scour the web to find email addresses and social media links for this podcast. We scanned the web and collated all of the contact information that we could find in our podcast database. But in the unlikely event that you can't find what you're looking for, our concierge service lets you request our research team to source better contacts for you.

Where can I see ratings and reviews for Best AI papers explained?

Rephonic pulls ratings and reviews for Best AI papers explained from multiple sources, including Spotify, Apple Podcasts, Castbox, and Podcast Addict.

View all the reviews in one place instead of visiting each platform individually and use this information to decide if a show is worth pitching or not.

How do I access podcast episode transcripts for Best AI papers explained?

Rephonic provides full transcripts for episodes of Best AI papers explained. Search within each transcript for your keywords, whether they be topics, brands or people, and figure out if it's worth pitching as a guest or sponsor. You can even set-up alerts to get notified when your keywords are mentioned.

What guests have appeared on Best AI papers explained?

Recent guests on Best AI papers explained include:

1. Andrej Karpathy
2. Unnamed Guest
3. Armand Ruiz
4. Dwarkesh Patel
5. Sholto Douglas
6. Trenton Bricken
7. Geoffrey Irving
8. Jason Wei

To view more recent guests and their details, simply upgrade your Rephonic account. You'll also get access to a typical guest profile to help you decide if the show is worth pitching.

Find and pitch the right podcasts

We help savvy brands, marketers and PR professionals to find the right podcasts for any topic or niche. Get the data and contacts you need to pitch podcasts at scale and turn listeners into customers.
Try it free for 7 days