Jaden Clark

@jadenvclark

PhD @Stanford @KnightHennessy. AI, robotics, and conservation

Los Angeles, CA

jadenvc.github.io

Replies Reposts Media

Pinned
Jaden Clark
@jadenvclark
Jul 2
Can we enable robots to develop a sense of touch without forgetting what they learned from large-scale vision-only pretraining? Introducing MultiSensory World Model (MuSe) 🌍: A new approach for finetuning visuomotor policies on minimal data from new sensor modalities, such as
00:00
8
Jaden Clark
@jadenvclark
Aug 28
Continual learning gets a lot of hype lately, but few works systematically analyze what makes it challenging in robotics. Check out Max's paper for some really interesting insights - the findings were crucial to getting our latest paper MuSe to work
Maximilian Du
@du_maximilian
Aug 28
When a robot learns a new behavior, what keeps it from forgetting the ones it already knows? Prior work, especially on VLAs, shows that rehearsing past experiences can enable strong continual learning. But why does rehearsal work so well, and when does it fail? We find that a
00:00
1
Jaden Clark
@jadenvclark
Aug 26
Want to understand how to get ICL like GEN-1.5 and S1 to work? Check out Behavior Prompting
Austin Patel
@austinapatel
Aug 26
With GEN-1.5 from @GeneralistAI and S1 from @SkildAI, we are seeing exciting progress with in-context demonstration prompting! But can we study this in academia? In our recent work Behavior Prompting Policy (behavior-prompting.github.io), we released open-source sim benchmarks and
00:00
Jaden Clark
@jadenvclark
Jul 9
We've been using iPhumi for MuSE/UMI-FT - iPhone is a big upgrade from original UMI design with better slam and easier UI!
Austin Patel
@austinapatel
Jul 9
Replying to @austinapatel
We are also excited to release iPhUMI ("eye-foo-me”)! It solves the localization challenges with the GoPro UMI, enabling rapid data collection across diverse environments and tasks. During deployment, iPhUMI lets you command your robot via demonstration. github.com/real-stanford/…
Jaden Clark
@jadenvclark
Jan 22
A key aspect of scaling robot data collection is sensor reliability (hence why we haven't really seen tactile sensing at scale yet). UMI-FT addresses this by giving UMI robust/reliable fingertip level force-torque sensing, a major step toward scaling data for contact-rich tasks.
Hojung Choi
@Hojung_Choi_
Jan 22
Robots excel at learning motions from humans, but can they also learn to apply force safely? 💪 Introducing UMI-FT: the UMI gripper equipped with force/torque sensors (CoinFT) on each finger. Multimodal data from UMI-FT, combined with diffusion policy and compliance control,
00:00