Marius Memmel
@memmelma
Followers
405
Following
740
Media
14
Statuses
88
Robotics PhD student @UW and @NVIDIA, previously @Bosch_AI, @DHBW, @EPFL, @TUDarmstadt
Seattle, WA
Joined April 2021
Have some offline data lying around? Use it to robustify few-shot imitation learning! 🤖. STRAP 🎒 is a retrieval-based method that leverages semantic sub-trajectories in offline datasets to augment the training data. 🧵 1/6
3
24
72
RT @YiruHelenWang: 🚨Tired of binary pass/fail metrics that miss the bigger picture?. 🤖Introducing #RoboEval — an open benchmark that shows….
0
34
0
RT @abhishekunique7: So you’ve trained your favorite diffusion/flow based policy, but it’s just not good enough 0-shot. Worry not, in our n….
0
24
0
RT @ajwagenmaker: Diffusion policies have demonstrated impressive performance in robot control, yet are difficult to improve online when 0-….
0
59
0
RT @avibose22: 🚨 Code is live! Check out LoRe – a modular, lightweight codebase for personalized reward modeling from user preferences. 📦 F….
0
6
0
RT @prodarhan: A way to do diverse and distributed evaluations for robotics! Checkout the sim eval tool I’ve made to help cheaply eval and….
0
2
0
RT @IlirAliu_: You don’t need more robot data. You need to look inside the data you already have. [📍 bookmark for later]. Instead of just c….
0
22
0
RT @abhishekunique7: Learned visuomotor policies are notoriously fragile, they break with changes in conditions like lighting, clutter, or….
0
15
0
RT @Jesse_Y_Zhang: How can non-experts quickly teach robots a variety of tasks? . Introducing HAND ✋, a simple, time-efficient method of tr….
0
30
0
RT @Jesse_Y_Zhang: Yes, I’ll be working with @fox_dieter17849 and @abhishekunique7 on enabling real world autonomous learning; super excite….
0
2
0
RT @Jesse_Y_Zhang: Reward models that help real robots learn new tasks—no new demos needed!. ReWiND uses language-guided rewards to train b….
0
53
0
RT @marceltornev: Giving history to our robot policies is crucial to solve a variety of daily tasks. However, diffusion policies get worse….
0
39
0
RT @avibose22: Excited to be at #AISTATS2025 ! Catch me at:.📍 Poster: Hall A–E 17–18.🕒 Sat, May 3rd at 3PM.Presenting our accepted works on….
0
2
0
RT @RohanBaijal: Long Range Navigator (LRN) đź§â€” an approach to extend planning horizons for off-road navigation given no prior maps. Using v….
0
24
0
DRAWER can generate an interactive simulation of a real-world scene from just a single video!. The best part? We can use it to train policies in simulation and transfer them back to the real world!.
Next, we can use this for training in robotics! We show that we can easily generate data in simulation for training robotic policies, and the resulting policies can transfer directly to the real world! The process of data generation becomes as simple as taking a video and then
0
1
11
Small poster, big ideas! Stop by at our poster session starting now to find out about trajectory retrieval in robotics! Hall 3 - 33 🤖
Have some offline data lying around? Use it to robustify few-shot imitation learning! 🤖. STRAP 🎒 is a retrieval-based method that leverages semantic sub-trajectories in offline datasets to augment the training data. 🧵 1/6
0
3
25
RT @abhishekunique7: Very excited to be at #ICLR2025 in Singapore helping present some of the work done by our group! We'll be presenting 4….
0
20
0
RT @XHongchi97338: Glad to introduce our #CVPR2025 paper "DRAWER", allowing one to create a realistic and interactable digital twin from a….
0
18
0
RT @weichiuma: I've been wanting to make 3D reconstructions not just realistic, but also **interactable** and **actionable** for years. Th….
0
17
0