Rephonic
Artwork for RoboPapers
Reinforcement Learning
Robotics
Vision-Language Models
Humanoid Robots
Project Instinct
Diffusion Policy
Domain Randomization
Robot Manipulation
Humanoids
Sim-To-Real
Stanford University
Videomanip
R2S2
Dreamzero
Molmospaces
Imitation Learning
Unifp
Sim2real
Humanoid Everyday
Maniflow

Chris Paxton & Michael Cho geek out over robotic papers with paper authors. robopapers.substack.com

PublishesTwice weeklyEpisodes93Founded9 months ago
Number of ListenersCategories
TechnologyScience

Listen to this Podcast

Artwork for RoboPapers

Latest Episodes

Many tasks cannot be completed by one robot alone. But coordinating multiple robots performing complex manipulation tasks is very difficult. Many solutions rely on complicated centralized control, which tends towards bespoke methods that do not scale... more

How can we learn robot grasping from egocentric human video alone? General-purpose dexterous manipulation learning will require a lot of data, and yet robot data is hard to find at scale. Better leveraging human data, then, will be key to general-pur... more

Memory is one of the most important problems in robotics. Long horizon memory is key for a variety of robot manipulation problems. However, there exist no good benchmarks for understanding progress in how well generalist robot policies can understand... more

We want humanoid robots to be able to perform complex, long-horizon tasks in the real world — putting away the groceries or cleaning a room, for example. This requires diverse loco-manipulation skills, which can be easily parameterized to handle obje... 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

Ria Doshi
PhD student at Stanford advised by Jeanette Bohg
Stanford University
Episode: Ep#93: CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy
Jeanette Bohg
Associate Professor at Stanford
Stanford University
Episode: Ep#93: CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy
Yinpei Dai
Co-author of RoboMME
University of Michigan
Episode: Ep#91: RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
Yuejiang Liu
Co-author of RoboMME
Stanford University / upcoming at National University of Singapore
Episode: Ep#91: RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
Gary Yang
Co-author of the Handoff paper; Caltech
Caltech
Episode: Ep#90: From Capable Controllers to Deployable Humanoid Systems
Suzannah Wistreich
Incoming PhD student at Stanford; tactile sensing researcher
Stanford University
Episode: Ep#88: DexSkin: High-Coverage Conformable Robotic Skin for Learning Contact-Rich Manipulation
Jiafei Duan
Co-author on MolmoAct2 paper
University of Washington / Stanford / NUS
Episode: Ep#87: MolmoAct 2: An open foundation for robots that work in the real world
Jiazhi Yang
PhD student, Chinese University of Hong Kong
The Chinese University of Hong Kong
Episode: Ep#86: RISE: Self-Improving Robot Policy with Compositional World Model
Kushal Kedia
PhD student, Cornell University; works on SimTooReal
Cornell University / Stanford University (visiting)
Episode: Ep#82: SimTooReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation

Hosts

Chris Paxton
Host of RoboPapers; frequently discusses robotics research and publishes/transcribes podcast episodes.
Michael Cho
Co-host; guides interviews and provides technical context, often focusing on hardware and deployment aspects.

Chart Rankings

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

Apple Podcasts
#250
Netherlands/Technology

Talking Points

Recent interactions between the hosts and their guests.

Ep#92: Human Universal Grasping
Q: Given the hardware limitations, do you think scaling data alone will push performance to near-perfect success?
Even with larger datasets and better hardware, there is a fundamental open-loop limitation in current deployment; recovery from errors without feedback remains challenging, suggesting the need for closed-loop policies and possibly reinforcement learning to improve reliability.
Ep#92: Human Universal Grasping
Q: I'm curious, how accurate do you get out of the box from ARIA Gen 2 for hand landmarks?
The average landmark error is around 1-2 cm across various conditions, with some occlusion cases showing larger errors; this noise is acknowledged and efforts are underway to fine-tune and compensate during deployment to improve accuracy.
Ep#91: RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
Q: How do you pick these representations? Is it just intuition?
The representations are motivated by streaming video literature, using token dropping and frame sampling for perceptual memory, recurrent modules for history compression, and grounded language sub-goals for symbolic memory; choices are informed by prior work and practical efficacy.
Ep#91: RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
Q: Could you give an example, let's say what if you have this task where you are, what's that, the unmask swap, right? So what would be a sub-goal for that, for example?
A sub-goal would be to pick up something that hides the cube and then press the button, followed by sub-goals to unmask the correct cubes depending on the scenario and sequence.
Ep#91: RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
Q: And are those like just hand-curated? Since you already fixed the 16 tasks, I see. And roughly speaking, one task will have maybe five to ten sub-goals?
The language variation provides a single sub-goal per subtask, not a large set of variations; sub-goals are template-based and designed to reflect the task structure rather than enumerating many language expressions.

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 RoboPapers

What is RoboPapers about and what kind of topics does it cover?

A robotics- and AI-focused show where researchers and engineers discuss cutting-edge papers, architectures, and deployments in real-world robotics. Episodes often explore world models, dexterous manipulation, simulation-to-real transfer, and scalable reward systems, with guests ranging from university researchers to startup founders and industry researchers. The conversations tend to balance deep technical detail with practical considerations like data needs, latency, hardware constraints, and deployment at scale. The show frequently highlights open datasets, publication-quality experiments, and cross-domain ideas that could inform product development, perception, planning, and control in industrial or consumer robotics. A standout strength... more

Where can I find podcast stats for RoboPapers?

Rephonic provides a wide range of podcast stats for RoboPapers. 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 RoboPapers and access YouTube viewership numbers, download stats, audience demographics, chart rankings, ratings, reviews and more.

How many listeners does RoboPapers get?

Rephonic provides a full set of podcast information for three million podcasts, including the number of listeners. View further listenership figures for RoboPapers, 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 RoboPapers?

Rephonic provides comprehensive predictive audience data for RoboPapers, 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 RoboPapers have?

To see how many followers or subscribers RoboPapers 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.

How many episodes of RoboPapers are there?

RoboPapers launched 9 months ago and published 93 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 RoboPapers?

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 RoboPapers?

Rephonic pulls ratings and reviews for RoboPapers 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 RoboPapers?

Rephonic provides full transcripts for episodes of RoboPapers. 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 RoboPapers?

Recent guests on RoboPapers include:

1. Ria Doshi
2. Jeanette Bohg
3. Yinpei Dai
4. Yuejiang Liu
5. Gary Yang
6. Suzannah Wistreich
7. Jiafei Duan
8. Jiazhi Yang

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