gentleman scientist 🤖 @voyagerobotics
Joined May 2020
- Tweets 2,014
- Following 897
- Followers 3,198
- Likes 9,443
421 Photos and videos
Pinned Tweet
Apr 23
A month ago @pravsels and I set out to reproduce @physical_int’s RL Token paper. Today, I am sharing our research notes from the journey we’ve been on.
x.com/VilleKuosmanen/status/…
Mar 24
"RL Token" looks like a great and surprisingly simple post-training methodology for optimising robot models for dexterous tasks in the real world!
Over the next few weeks, me and @pravsels will be attempting to reproduce the results (& open source the code)
Stay tuned 👀
1
13
125
16,972
Jun 11
fun part about running a hardware startup is sometimes people steal your amazon parcels and now your lead time has doubled 🥲
2
8
886
Jun 11
Great to see robotics taking off in Finland 🇫🇮🇫🇮
Jun 11
Low-cost arms built in Finland, assembling part of an actuator. Nice precision task.
7
834
Jun 10
that's a lot of robots
839
Jun 4
While the labs and their agents will run at the speed of compute, the physical world will not
not until we solve robotics
and after we do, physical actions are just another tool call
in 10 years we will be talking about vibe construction and vibe cooking
Anthropic is questioning whether AI may turn out to be altogether useless. This is the single most honest thing Anthropic has ever written.
“But achieving recursive improvement alone does not suggest an immediate change in how industrial production occurs, societies organize, or markets function. More intelligence can’t learn what a drug does over decades of use, can’t hold elections sooner than a constitution dictates, and can’t turn a stranger into an old friend in a weekend. For most people, the felt pace of this future will still be set by the bottlenecks, even if the laboratory upstream runs at the speed of compute. That collision, where recursive intelligence building itself ever faster meets the world of humans, relationships, and governance, is another part of this future we can’t predict.”
2
13
654
Jun 4
anyone in the UK with a DROID setup (robotiq gripper, franka arm) they don't need anymore and would consider selling second-hand?
1
310
Ville🤖 retweeted
Jun 1
Excited to introduce SOLE-R1, a video-language reasoning model for zero-shot reward prediction for robot manipulation tasks!
SOLE-R1 reasoning can serve as the SOLE signal for learning new tasks (completely from scratch) through online RL - i.e., robots start with random actions and learn previously unseen tasks guided only by SOLE-R1 rewards, without any demonstrations, ground-truth rewards, success indicators, or task-specific tuning.
SOLE-R1 significantly outperforms strong baselines (e.g., Robometer, RoboReward, TOPReward, GPT-5, Gemini-3-Pro) in zero-shot online RL when evaluated across 40 tasks - including a real-world tabletop manipulation setting and 4 sim environments (LIBERO, ManiSkill, Meta-World, RoboSuite).
We open source all models, training data, and code.
Website, demos, and paper at: philip-mit.github.io/sole-r1…
🧵 (1/6)
1
9
54
14,012
Jun 3
noticing a trend where robotics startups take photos/videos from other people's robots, slap their logo on them, and use it in a launch video and ads
am I the only one thinking this is misleading?
2
1
25
1,684
Jun 1
familiar looking desk 🤔🤔
Jun 1
🤖 Another zero-shot reward model is now in LeRobot: ROBOMETER.
A general-purpose, zero-shot video-language reward model from @UofSC, @UT_Dallas, @MIT, @UW, @allen_ai, and @nvidia that predicts frame-level task progress.
Trained on 1M trajectories from 21 robot embodiments, generalizes zero-shot to unseen tasks, scenes, and robots. 2.4–4.5x better downstream success rates across online RL, offline RL, data filtering, failure detection, and data retrieval for IL.
Project: robometer.github.io/
Paper: arxiv.org/abs/2603.02115
1
1
10
2,178
Ville🤖 retweeted
May 28
Right now we're just:
- Scoring episodes 1-5 during collection for later filtering
- Rating episodes on task-specific grading scales.
We'd like to:
- Grab a frame per episode from context cam and annotate static objects with SAM to compare positional distributions in a dataset.
- Add subtask annotations.
- See if we can build something like a UMAP plot of episodes for a given dataset - not sure yet, how to best implement this and how well it works.
- Overlay reward model scores
1
7
514
May 28
I've said it for a while, silicon valley is the worst messenger for technological progress and a big reason why the general public across the west has turned against AI
May 27
JUST IN: Senator Elizabeth Warren urgently calls for AI regulations to prevent a “permanent underclass”
2
4
1,411
May 28
notice how AI pretty much disappeared from consumer advertisements, and how profilic AI ad campaigns like Apple Intelligence flopped?
AI is still front and centre in ad campaigns in China btw, saw lots of AI ads in April, they haven't conditioned the public to hate tech
1
5
859
May 28
lots to think about for robotics folks
go talk about your work to people outside the Valley. can you make a case how what you are building will help them?
we need our fellow citizens to *want* robots in their homes and workplaces, to view them as helpers not job-stealers
1
532
May 26
robotics might be the most multi-disciplinary engineering field today
add installing and repairing the robot, and wrapping the robot with bubble wrap and putting it to the back of a van for customer deployments ( sometimes driving the van as well)
6
7
135
7,315
May 22
robot-grown strawberries spotted in a British supermarket 🇬🇧
May 22
Just checked, and I’ve been unknowingly eating Dyson Strawberries the last couple days.
My favourite bit is “Not for EU”.
Proper Brexit strawberries.
7
706
May 19
tip for founders - send hedge fund recruiters to your competitors inboxes for psychological damage
2
7
599
May 14
this is how europeans view wine from california btw
sorry sf bros I don't make the rules 🤷♂️
4
975
May 14
if anyone is interested in remotely accessing an so-101 arm farm, for any purpose (inc. evals, data collection, RL), DM me 😎
6
34
3,423