arya (@eps_greedy) header
arya (@eps_greedy) profile picture

wizardry, alchemy, and research @RhodaAI

Bay Area
Joined August 2023
Photo by arya (@eps_greedy)Photo by arya (@eps_greedy)Photo by arya (@eps_greedy)Photo by arya (@eps_greedy)Photo by arya (@eps_greedy)Photo by arya (@eps_greedy)Photo by arya (@eps_greedy)
been working on open ml resources for early-in-career people to learn. here's a collection of free + extremely valuable lectures, blogs, etc discord.gg/hA7exCh6tH contributions welcome
5
2
1
21
3,007
the best time to be in robotics is now, second best time is ASAP there are incredibly cool problems to solve every day, that no one has solved
3
25
1,246
anyone surprised by the gemini 4 line clearly didnt learn from 2.5 flash / experimental
2
284
we're hiring across roles and teams! join us at the new office, maybe you can pick up a cupcake :)
Wonderful first day at our new offices and robotics lab in Sunnyvale! A huge thank you to our facilities and IT team for setting up this amazing new space and making the move seamless!
20
4
1
158
5,622
arya retweeted
We taught a robot how to move around in only 15 minutes. That’s all the mobility data our Direct Video-Action-powered robot needed to accomplish a task that requires mobility and manipulation.
12
18
17
139
17,902
finally taking the leap
2
9
562
Super cool! Alan is an absolute beast, and one of the most principled researchers I've met. See his newest work below :)
1/ The tokenizer is a new scaling axis! We introduce an approach for diffusable representation learning that's principled, scalable, and works when DINO/LeJEPA collapse. We get joint tokenizer+diffusion scaling laws and it's compute-optimal vs raw diffusion w/ @drfeifei @GordonWetzstein @jcjohnss @ericryanchan @vincesitzmann @KyleSargentAI Thread, Paper, and Blogpost below
1
6
782
1/ The tokenizer is a new scaling axis! We introduce an approach for diffusable representation learning that's principled, scalable, and works when DINO/LeJEPA collapse. We get joint tokenizer+diffusion scaling laws and it's compute-optimal vs raw diffusion w/ @drfeifei @GordonWetzstein @jcjohnss @ericryanchan @vincesitzmann @KyleSargentAI Thread, Paper, and Blogpost below
17
74
17
648
95,548
arya retweeted
What can a robot do without vision? We gave our robot a sense of touch and showed it can recognize and retrieve objects with its cameras blindfolded. Introducing Rhoda’s new tactile sensor—it feels pressure, texture, vibration, slip, and temperature, just like your fingertips.
59
56
61
579
107,333
interning at rhoda was life changing. our team is full of world-class leaders, scientists, engineers, and mentors. if you're a curious and motivated student, please apply below and feel free to send me a note. i can't promise to reply to all, but i am quite invested in you!
we're hiring interns! looking for current students or recent graduates for robot swe and product management internships i joined rhoda as an intern in early 2025 and it completely changed my life. come solve robotics with us :)
5
1
40
4,094
paid to read about and play with robotic video models all day.. what a life
3
358
seeing lots of money flow into world modeling and spatial intelligence :) excited for the advent of AI in the real world
General Intuition has raised another $220M at a $6.2B valuation as we start making our models available. These are an entirely new class of foundation models, trained on billions of action-labeled videos, capable of acting in realtime in never seen before environments. 1/6
10
600
not now honey, I'm doing frontier AI research
46
109
18
1,916
103,148
arya retweeted
At Rhoda, we care deeply about the science of pre-training for robotics. In one of the most rigorous studies of its kind, over thousands of trials and hundreds of hours of robot evaluations, we show how scaling web-video pre-training leads to better real-world robot performance.
14
33
11
260
82,538
Does scaling pre-training on general web video improve a complex manipulation task in real deployment? We scale model size and pre-training compute, and test on one industrial task. Yes. The better a pre-trained model predicts web video, the better its post-trained policy. 🧵
33
38
26
295
98,962
arya retweeted
i made this right after our launch @RhodaAI with some leftover b-roll - watch with sound on 🔉! we've been silent for a while, but we have many exciting things to share in the future 👀
8
5
2
72
15,859
arya retweeted
This Post is from an account that no longer exists. Learn more
10
13
1
533
23,239
🤖 Made with AI
Replying to @suchenzang
the paper has like equation and math formula all over the place 😅
8
73
5
1,518
63,329
arya retweeted
i'm so excited to finally share what we've been working on @rhodaai! taking lessons from success in LLMs, we identify autoregressive video generation as a scalable objective for training robot policies. 1/n
After operating in stealth for the last 18 months @rhodaai , we’re excited today to finally show the world what we’ve been working on. We believe we’re on a path to physical AGI with the launch of our brand new foundation model, the Direct Video Action (DVA) model.
7
9
1
111
31,273
Decided to implement Deepseek's new paper (mHC: Manifold-Constrained Hyper-Connections) in CUDA.
29
36
9
970
179,500