PODCAST

RoboPapers

Chris Paxton and Michael Cho

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

technology

All Episodes

51:46

Ep#9: AutoEval: Autonomous Evaluation of Generalist...

RoboPapers ·

2025/08/12

Evaluating robot policies is challenging, because everyone has a slightly different testing setup and environment. Paul joined us to talk about his work AutoEval, which is a continuously-operating benchmark which allows you to test robot policies remotely, in any environment.Abstract:Scalable and reproducible policy evaluation has been a long-standing challenge in robot learning. Evaluations are critical to assess progress and build better policies, but evaluation in the real world, especially at a

58:38

Ep#8: VGGT: Visual Geometry Grounded Transformer

RoboPapers ·

2025/08/08

3D spatial information provides a really strong signal for robotics policies, something we’ve discussed in previous episodes. But computing this 3D structure is hard, and often relies on imperfect, low-quality depth sensors. It would be great if we could reconstruct this information from cameras alone, with little prior information.Well, that’s exactly what VGGT does!We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters,

59:28

Ep#7: AnyDexGrasp: General Dexterous Grasping for...

RoboPapers ·

2025/08/08

Hao-Shu talks to us about how we can learn a contact-centric grasp representation which works across many different robots.We introduce an efficient approach for learning dexterous grasping with minimal data, advancing robotic manipulation capabilities across different robotic hands. Unlike traditional methods that require millions of grasp labels for each robotic hand, our method achieves high performance with human-level learning efficiency: only hundreds of grasp attempts on 40 training objects

53:29

Ep#6: FP3: A 3D Foundation Policy for Robotic...

RoboPapers ·

2025/08/08

3D features are uniquely better at generalizing than 2D image features, given less data. Learn about how we can use them to train generalizable robot manipulation policies with Yang Gao.Following its success in natural language processing and computer vision, foundation models that are pre-trained on large-scale multi-task datasets have also shown great potential in robotics. However, most existing robot foundation models rely solely on 2D image observations, ignoring 3D geometric information, which

60:29

Ep#5: R+X: Retrieval and Execution from Everyday...

RoboPapers ·

2025/08/08

Human data is much more plentiful than robot data, and humans already know how to perform so many tasks. Teaching robots from human videos, then, has a ton of potential.We present R+X, a framework which enables robots to learn skills from long, unlabelled, first-person videos of humans performing everyday tasks. Given a language command from a human, R+X first retrieves short video clips containing relevant behaviour, and then executes the skill by conditioning an in-context imitation learning

71:53

Ep #4: Vision Language Models are In-Context Value...

RoboPapers ·

2025/08/08

Value prediction is an important robotics problem, wherein we can determine how useful a state is to the successful execution of a task in the future. The key insight that Jason and his co-authors showed in this paper was simple:* Large vision-language models already encode a ton of information about task completion from being trained on a wide range of human image and video data* We can use these on robotics tasks to estimate progress, which is a useful surrogate for the “value” of any individual

51:16

Ep#3 Sim-to-Real Reinforcement Learning for...

RoboPapers ·

2025/08/08

Sim-to-real training is an important part of the future of robot skill learning. But a lot of sim-to-real work focuses on navigation, grasping, or, more recently, non-interactive robot behaviors like dancing. Training dexterous policies for humanoids is very different, because manipulation is a very hard problem and multi-finger dexterous hands are even more difficult.Enter this cool work from Toru Lin and colleagues. Their goal is to do long-horizon manipulation with dexterous humanoid

67:17

RoboPapers Episode 2: Robot Utility Models with Mahi...

RoboPapers ·

2025/08/08

One of the dreams of robotics research is being able to download and test out a model and have it *just work*. Mahi talks to us about “robot utility models,” which are essentially just this: models that you can download and test out to do useful things like opening a cabinet or picking up a can.Robot models, particularly those trained with large amounts of data, have recently shown a plethora of real-world manipulation and navigation capabilities. Several independent efforts have shown that given

68:59

RoboPapers Episode 1: SAM2ACT with Jiafei Duan

RoboPapers ·

2025/08/08

Robotic manipulation systems operating in diverse, dynamic environments must exhibit three critical abilities: multitask interaction, generalization to unseen scenarios, and spatial memory. While significant progress has been made in robotic manipulation, existing approaches often fall short in generalization to complex environmental variations and addressing memory-dependent tasks. To bridge this gap, we introduce SAM2Act, a multi-view robotic transformer-based policy that leverages

109 results

RoboPapers

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

Two Blokes Talking Tech

Trevor Long and Stephen Fenech

Pioneers of AI

WaitWhat

The Brave Technologist

Brave Software

The Good Tech Companies

HackerNoon