Arhan Jain
@prodarhan
Followers
129
Following
661
Media
25
Statuses
235
A way to do diverse and distributed evaluations for robotics! Checkout the sim eval tool I’ve made to help cheaply eval and debug policies trained for DROID :) . Then submit your policies trained on the DROID platform to the arena and get real world feedback and comparisons!.
We’re releasing the RoboArena today!🤖🦾. Fair & scalable evaluation is a major bottleneck for research on generalist policies. We’re hoping that RoboArena can help!. We provide data, model code & sim evals for debugging! Submit your policies today and join the leaderboard! :).🧵
1
2
18
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 @uwcse: If you visited the @uwcherryblossom, did you “spot” an unusual visitor among the blooms? Researchers in the @UW #UWAllen’s #Robo….
0
6
0
RT @abhishekunique7: Constructing interactive simulated worlds has been a challenging problem, requiring considerable manual effort for ass….
0
22
0
awesome being a part of this work - the ability to cheaply obtain high fidelity, articulated digital twins is incredibly useful for downstream robotics applications 🤠.
Glad to introduce our #CVPR2025 paper "DRAWER", allowing one to create a realistic and interactable digital twin from a video of a static scene without any interactions with the environment. It unlocks many opportunities in gaming and robotics!. Webpage:
0
3
10
RT @weichiuma: I've been wanting to make 3D reconstructions not just realistic, but also **interactable** and **actionable** for years. Th….
0
17
0
RT @kjha02: Our new paper (first one of my PhD!) on cooperative AI reveals a surprising insight: Environment Diversity > Partner Diversity.….
0
33
0
RT @jerelsantos: I've been meaning to post more of my work on here. So here's the video I scripted, directed, and edited for the recent Se….
0
2
0
RT @abhishekunique7: World modeling and imitation learning have largely been considered two disparate worlds. In our recent work, Unified W….
0
13
0
RT @chuning_zhu: Scaling imitation learning has been bottlenecked by the need for high-quality robot data, which are expensive to collect.….
0
39
0
RT @abhishekunique7: Over the last few months, we’ve been thinking about how to learn from “off-domain” data - data from non-robot sources….
0
17
0
RT @abhishekunique7: So we did a bunch of projects with real world reinforcement learning - but it was often too inefficient to be practica….
0
30
0
RT @physical_int: Many of you asked for code & weights for π₀, we are happy to announce that we are releasing π₀ and pre-trained checkpoin….
0
215
0
was pretty wild seeing the droid model work zero shot irl - first signs of actual robustness.
Excited to release FAST, our new robot action tokenizer! 🤖. Some highlights:.- Simple autoregressive VLAs match diffusion VLA performance.- Trains up to 5x faster.- Works on all robot datasets we tested.- First VLAs that work out-of-the-box in new environments!. 🧵/
0
2
14
RT @vikhyatk: what I thought AI would do to programming vs what actually seems to have happened
0
11
0
RT @abhishekunique7: In my experience, robot 'generalists' are often jacks of all trades but masters of none. In training across multiple t….
0
21
0
RT @memmelma: Have some offline data lying around? Use it to robustify few-shot imitation learning! 🤖. STRAP 🎒 is a retrieval-based method….
0
24
0
RT @jang_yoel: Check out our new work on aligning VLAs to customized preferences via trajectory-based preference optimization!.
0
3
0
RT @abhishekunique7: So I heard we need more data for robot learning :) Purely real world teleop is expensive and slow, making large scale….
0
22
0