RoboPapers

48:57

Ep#109: Enigma - Connecting 100 Robots To The Internet

RoboPapers ·

2026/10/05

What happens if you connect a hundred AI-powered robots to the internet and just let people give them any instructions they want? Enigma founder Jonathan Jacobi joins us to talk about his experience deploying a fleet of robots on the internet, keeping them operational, and watching people truly test the generality and robustness of frontier robotics models.Watch Episode 109 of RoboPapers with Chris Paxton and Ruijie He today!Learn MoreOriginal Post on XRobots.online website (no longer

en

51:56

Ep#108: VLS: Steering Pretrained Robot Policies via...

RoboPapers ·

2026/10/01

Pretrained vision-language-action models for robots often fail when a task is performed in a slightly different environment. With Vision-Language Steering, you can get better generalization performance out of a frozen robot policy, by steering the sampling process of your pretrained diffusion or flow-matching policy to handle out-of-distribution changes like obstacle position or changing visual appearance. Shuo Lin and Ishneet Sukhviner Singh join us to talk about how to better generalize robot

en

62:32

Ep#107: Do As I Do: Dexterous Manipulation Data from...

RoboPapers ·

2026/09/25

Achieving human-like dexterity is the next frontier for robotics, and yet dexterity data is often subtly hard to scale. Real-world dexterity data, including things like finger-pose estimates, is often slightly off, making it physically invalid and hard to execute on real hardware and hard to learn from.DO AS I DO is an algorithm for reconstructing and retargeting monocular RGB videos to robot hands, outperforming the state of the art and even working from generated videos. Bhawna Paliwal, Haritheja

en

53:31

Ep#106: Flex-π: A Multi-Stream World-Action Model...

RoboPapers ·

2026/09/23

World Action Models are becoming more popular in robotics, as they learn to predict the world jointly with learning how to act on it. However, these world predictions are usually purely based on reconstructing color images from video. This is limiting, because color is far from the most important quality for a robot moving around in the world — more important are qualities like 3D geometry and object semantics. In Flex-π, Ge Yan, Jesse Zhang, and team train a 6 billion parameter world action model

en

49:35

Ep#105: Beyond Imitation: Self-Improving Robot...

RoboPapers ·

2026/09/18

Imitation learning, especially with interventions, has driven so much recent robotics progress. However, improving a policy via targeted interventions until it reaches a useful and deployable success rate is a time and labor intensive process. Instead, wouldn’t it be great if policies could improve on their own?That’s what Varun Giridhar and Animesh Garg join us to talk about. In Q-Planning, they start with a large policy like pi-0.5, and add a Q-function estimator to predict value instead of just

en

42:45

Ep#104: Light-Loco-Parkour: Versatile Perceptive...

RoboPapers ·

2026/09/14

One of the key advantages of legged robots like humanoids should be how effectively they can move across a wide variety of terrain types to accomplish their task. But Light-Loco-Parkour from the team at Light Origins aims to change that: using only onboard sensing, they show a policy which can decide when to walk, vault, climb, or otherwise traverse as it moves through a complex environment. Unlike many others, it uses sparse seeds instead of relying on a large motion corpus, learning when to use

en

47:58

Ep#103: Freeform Preference Learning for Robotic...

RoboPapers ·

2026/09/09

Specifying reward functions for robots is one of the hardest things about reinforcement learning. Robot rewards often need to be very detailed; metrics like progress can be ill-defined and hard to estimate. This leads to most robot learning defaulting to sparse rewards or simple preference learning. But naive preference learning (having human annotators choose one trajectory over another) is an easy solution, but obscures a lot of the signal in complex tasks and can make learning a lot less

en

69:09

Ep#102: EgoSuite-Open100K from Lightwheel

RoboPapers ·

2026/09/08

Robotics has a data problem, and egocentric data is a compelling way to solve it because egocentric data is (1) scalable — it’s cheap to collect — and (2) easily captures the breadth and diversity of real human tasks, while (3) being true to real physics. Lightwheel recently released a hundred thousand hours of high-quality egocentric video data, spread across a wide range of human tasks from cleaning and tidying to assembly and construction to retail tasks.Here to tell us about this tremendous

en

51:26

Ep#101: Coupled Local and Global World Models for...

RoboPapers ·

2026/09/04

Reinforcement learning has unlocked tremendous gains in broader AI and humanoid robot whole body control, but still has yet to deliver strong results for robot manipulation due to the difficulty of capturing tasks in an accurate simulation; one way to fix this is to create complex environments with learned world models. But learning fully within world models is often intractable as powerful world models are computationally too expensive.Instead, Joseph Amigo and Rooholla Khorrambahkt propose to

en

89:00

Ep#100: 100 Episodes of Embodied AI

RoboPapers ·

2026/09/02

Embodied AI is exploding, and it’s been amazing to learn about it with you all.We have now recorded over a hundred discussions with the best researchers in the world on embodied artificial intelligence and robotics, covering topics like scaling robot learning, humanoid whole body control, tactile sensors, sim-to-real, and so much more.For our hundredth episode, we brought on our newest co-host, Ruijie He, to discuss what we’ve seen and learned in the first hundred episodes. Which were our

en

67:19

Ep#99: DYNA-2: A 1 Million Hour Scaling Law for...

RoboPapers ·

2026/08/18

Excitement about world-action models and robot learning has never been higher — they promise a way to use human egocentric data to train massive robotics models which can provide the “GPT” moment for robotics and unlock general-purpose embodied intelligence. And yet there’s been little concrete demonstration of scaling in robot learning. Dyna Robotics aims to change that, with an in-depth look at how scaling works as they approach 1 million hours of training data.Jason Ma, Tianyu Li, Anh-Quan Pham,

en

59:53

Ep#97: Cross-Embodiment Robot Manipulation via a...

RoboPapers ·

2026/08/14

Representing actions for robot hands is actually very challenging. Robot hands have different sizes and shapes, and different degrees of freedom. Representing their actions purely as joint states — as we naively would — leads to less transfer across the wide variety of available hands. Instead, could we design a universal hand action space to allow robots to learn cross-embodiment dexterous manipulation more easily?Luis Felipe Casas and Yu Xiang come on to tell us about UHAS: the Unified Hand Action

en

36:32

Ep#96: EgoHumanoid: Unlocking In-the-Wild...

RoboPapers ·

2026/08/12

How can roboticists scale human manipulation data in the wild? EgoHumanoid builds a comprehensive pipeline which unlocks mobile manipulation training for robots — meaning that you can walk around and collect data for your robot anywhere you go. There are two key components to their recipe: view alignment, to reduce mismatch between human and robot camera views, and action alignment, to make sure human actions can be converted into robot actions. This makes it easier than ever to train robot policies

en

49:19

Ep#95: Action-to-Action Flow Matching

RoboPapers ·

2026/08/05

Diffusion Policy was one of the big breakthroughs that has enabled an explosion in real-world robot learning. However, it’s always had a weakness, which is that it works by computing a final action trajectory from random noise, which leads to high latency when predicting a final action sequence.Instead, why not initialize the search based on previous actions? This allows for incredibly fast policy inference and in many cases improved generalization, generating high-quality predictions with sub-ms

en

76:39

Ep#94: Learning a Thousand Tasks in a Day

RoboPapers ·

2026/08/03

For general-purpose robots to be useful, we must be able to teach them new tasks quickly and repurpose them to new roles. But most techniques for teaching robots — even from human demonstrations — take a great deal of new data. But it turns out that it is possible, in part through decomposing tasks into component subtasks, that it’s possible to learn a robot skills quickly.Kamil Dreczkowski, Pietro Vitiello and Edward Johns join us to talk about their extensive study on how to teach robots new

en

60:09

Ep#93: CHORUS: Decentralized Multi-Embodiment...

RoboPapers ·

2026/07/29

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 well with team size.Enter CHORUS by Ria Doshi, Jeanette Bohg, and team. They train a single VLA to control multiple, diverse robots, given only local observations and identifying information. This allows robots to collaborate on tasks like using a tape

en

70:03

Ep#92: Human Universal Grasping

RoboPapers ·

2026/07/25

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-purpose dexterous manipulation.Kevin Wu, Irmak Guzey, and Dandan Shan join us to talk about HUG: Human Unversal Grasping. They collect a dataset of 1M frames (27.8 hours) of egocentric human grasping data, and use it to train a new flow-matching algorithm

en

56:38

Ep#91: RoboMME: Benchmarking and Understanding Memory...

RoboPapers ·

2026/07/23

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 language.Yinpei Dai and Yuejiang Liu made RoboMME as a solution: it’s a large benchmark which shows 16 different robot tasks, like counting objects or mastering timing. They show 14 different memory-augmented generalist policies across these different

en

62:32

Ep#90: From Capable Controllers to Deployable...

RoboPapers ·

2026/07/15

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 object affordances and interact with the world around it safely.In HANDOFF, Lizhi Yang proposes a 10-D learned whole body controller, which can be converted to whole body actions, and which can be used by a VLM-driven agentic planner to perform complex,

en

39:20

Ep#89: Contact Grounded Policy

RoboPapers ·

2026/07/08

Contact-rich manipulation is still very challenging for robotics. Problems like opening a jar, or in-hand reorientation of an object, require making repeated contact with different parts of a robot’s hand, and this is hard to do with pure vision. Instead, research is moving towards using tactile sensors in combination with visual policies. But what’s the best way to learn how to handle multi-point contact?Zhengtong Xu and Yeping Wang tell us about their new work Contact-Grounded Policy (CGP). CGP

en

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

The Tech Trek

Elevano

Engineering the Intelligent Enterprise

PRASAD BHONDE

The Vergecast

The Verge

Double Tap

Steven Scott, Shaun Preece, Steven...