PhD @ MPI_IS
Joined November 2017
- Tweets292
- Following187
- Followers345
- Likes1.6K
Nikos Athanasiou retweeted
One of the most impactful lines of work in recent years, and we see similar scaling laws at @FlexionAI.
It raises the question: Why spend millions collecting real world data when you can learn this in sim way cheaper?
Kudos to @octi_zhang @mateoguaman @abhishekunique7 and co!
(1/5) Everyone says dexterous manipulation needs real-world data. These policies were trained with none. Our robots mesh gears, thread nuts, and insert pegs zero-shot from RGB, and the same recipe works for locomotion across terrains much harder than before.
The missing piece wasn't a better RL algorithm, but a small tweak to what the robot practices.
Today we're releasing Success-Guided Sampling (SGS), a simple change to the task sampler that unlocks new levels of dexterity and agility with large-scale, end-to-end sim2real RL.
No demonstrations, no per-task reward tuning. Just PPO at scale.
Check out the policies yourself at sgs-rl.github.io! All videos at 1x speed! 🧵 🔈
Nikos Athanasiou retweeted
I use Claude Code in one terminal, Codex in another, and a training job beside them.
Next month, I’ll use something else.
I realised I don’t want remote access to an agent. I want remote access to where they all already live: my terminal.
So I built PocketTUI.com
Nikos Athanasiou retweeted
In the old days we used to talk about "graduate student descent" or "researcher gradient descent" as referring to the phase in research where one tries various techniques, changes parameters in the hope of getting to some desired output. Now we can get AI agents to do it. The classic CV paradigm of analysis by synthesis becomes considerably more powerful this way.
Nikos Athanasiou retweeted
Today at ECCV:
Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation, ExHall Poster: #70, PM CEST, Poster Session 2.
* 3D hand–object pose estimation in unconstrained, cluttered, occluded egocentric video
* EPIC-Contact, an in-the-wild dataset with dense 3D hand–object contact
* HOPformer, a transformer that conditions object pose on strong hand priors to predict both hands and the object in a single forward pass.
co-authors: @Sid__Bansal, @zhifan_zhu , @sha2nk_t, @terry_jhzhao00, @dimadamen
sid2697.github.io/epic-conta…
Nikos Athanasiou retweeted
📄 TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction
📍 Saturday 12.09 10:30-12:00 - Poster #386
🤝Joint work with @_nikos_athan Angela Yao, Shugao Ma, Eric Sauser Edoardo Remelli, Shreyas Hampali, Johannes Schönberger, Fadime Sener, Bugra Tekin
Nikos Athanasiou retweeted
🎉 Excited to be at #ECCV2026 🇸🇪 . I'll be presenting two posters here, so come say hi if you are around!
📄 ECHO: Ego-centric Modeling of Human-Object Interactions
📍 Friday 11.09 10:30-12:00 - Poster #267
Nikos Athanasiou retweeted
Historically, RL policies for robots have been trained in synthetic, untextured environments, limiting perceptive policies to depth images where the sim-to-real gap is manageable. RGB has always had more potential, but leveraging it to train policies in simulation remained an open problem.
Partnering with @NianticSpatial and @NVIDIARobotics, we built a pipeline that addresses exactly that. We can now scan a real deployment site with off-the-shelf hardware, reconstruct it into a photorealistic Gaussian splat, and run massively parallel RL training. The policies trained in our Gym environment then transfer zero-shot to the real robot and environments they were trained for. This enables faster deployment of more capable and robust policies for the end user.
The new resulting capabilities are a big step towards solving sim-to-real and also apply well beyond navigation. Read the full technical breakdown on our blog; link in the comments.
#HumanoidRobots #Flexion #NianticSpatial #NVIDIA
Nikos Athanasiou retweeted
Awesome lineup on MTS today:
@ahall_research just discussed AGI politics
@Ronalfa on the AI x Bio explosion happening
@evan_wineland & @kaandogrusoz discussing their home robot, Isaac 1
@jared_western telling us about Western Chemicals
@kmad sharing his thoughts on FDEs versus consultants
@rdn_nikita on Flexion's approach to robotics
@jasonhausenloy to discuss the frontier lab brain drain
@StevenGlinert about Nvidia & geopolitics
+ timeline review and coverage of important stories like government equity stakes in OpenAI, the return of Fable, and other breaking stories at the frontier of the singularity
GOVT STAKE IN OAI | ANTHROPIC X SAMSUNG | NVDA REVENUE SHARING nitter.cf/i/broadcasts/1dJrPPvMe…
Nikos Athanasiou retweeted
🚀 Code release!
The code for SAM3D Animal is now available!
🐾 Estimates the 3D shape and pose of multiple animals from a single image
🐾 Supports multiple species with the SMAL+ parametric animal model
Project page :
georgehux.com/SAM3D-Animal-p…
Congratulations @GeorgeHu240266
The most complete pipeline I have seen! Proud to be part of this team 😉
"A parcel with snacks has been delivered for Flexion. Retrieve it using the stairs and come up using the elevator. Then unpack it and place the items into the empty drawer on the shelf in the snack area."
One instruction. No human operator. Everything that follows is autonomous.
Today we're introducing Reflect v1.0, our robotics intelligence platform for long-horizon work. From a single natural-language command, the robot understands the task, navigates a multi-floor building, calls elevators, handles doors, uses tools to unpack a box, and puts the items away. The biggest shift in v1.0 is that we use reinforcement learning across every layer, from low-level control to high-level reasoning.
Long-horizon autonomy is unforgiving. The robot must recover on its own when things don't go to plan because in the real world, they never do. Combining reasoning, perception, physical execution and runtime robustness into a single mission-capable system is the foundation required to solve humanoid autonomy.
Our team is just getting started.
#HumanoidRobots #Flexion
Nikos Athanasiou retweeted
I’ve been capturing 3D human motion for 30 years and today is maybe the biggest day in that history. We are presenting MAMMA at CVPR (oral session 2A). MAMMA is a markerless multi-camera system that has accuracy similar to marker-based systems.
Nikos Athanasiou retweeted
I want to offer some unsolicited advice to computer vision researchers jumping into robotics. Don't focus too much on VLMs, VLAs etc. That's fine, but the real action is at the sensorimotor level. Most of the open problems in robotics are in manipulation, which is about hand-object interaction, and contacts and forces are central. Proprioception and tactile sensing are as important as vision. Don't get seduced by cherry-picked demos. You can't do robotics without doing robotics.
Nikos Athanasiou retweeted
Looking for a nice home for your paper? #3DV2027 is waiting! 🎉
⏰ Conference dates: April 6-9, 2027
✈️ Place: #Thessaloniki (#SKG), #Greece 🇬🇷
📝 Paper ddl: Aug 28
🎥 Supp ddl: Sep 02
🆕 Rebuttal only upon invite for borderline papers!
#CallForPapers: 3dvconf.github.io/2027/call-…
Nikos Athanasiou retweeted
working on human motion and in #3DV206 ?
then don’t miss this interesting work!
in “Dense Motion Captioning”, the authors propose a new task, dataset, and the model for dense 3D human motion captioning
is there anyone interested in 3D human motion understanding?
this interesting work and arch... xusy2333.com/demo/
i know the author🦧, she's a nice guy has some ideas... anyone interested in chatting...?
Sai is sharing some cool stuff about how-to Claude.
Amazing dataset ❤️ synthetic for the win!
BEDLAM2.0 image and depth data are now available via Hugging Face, providing high-speed worldwide download access to over 26TB of synthetic data for non-commercial research.
Hugging Face: huggingface.co/datasets/Inte…
Project: bedlam2.is.tuebingen.mpg.de/
Nikos Athanasiou retweeted
Big news: @Meshcapade is now part of Epic Games. This is a perfect match for our technology and team and I am super excited about what we will build together.
I want to thank our many supporters who have provided funding and/or advice on our journey from 2018 to today, including @MP_Innovation, @maxplanckpress, @MPI_IS, @PerceivingSys, @matrixvc, @dcstalder, @dianaberlin, @HV_Capital, Zuzanna Czapinska, LBBW VC, @GoodwaterCap, CLO Virtual Fashion (@itsclo3d), @grbradsk, @lucvincent, @JeffDean, @ballmatthew, Andrew Hamel, Bill O’Farrell, Ammar Zakiullah, @Nicolas_Keller, Alex Diehl, @goodwinlaw, YPOG, @NVIDIA Inception Program, @msft4startups, and many more!
Most importantly, I want to thank my co-founders @naureenmahmood and Talha Zaman and the whole @Meshcapade team. There is nothing more rewarding than working with great people who you like and trust to build products that customers love using technology you believe in. Thank you, thank you, thank you. Now, on to the next phase!
mpg.de/26082348/max-planck-s…
Nikos Athanasiou retweeted
Quite literally all of 3D vision
This includes VGGT, Dust3r and friends which are trained on COLMAP-generated data
Also gaussian splatting and NERFs in most cases use COLMAP-generated poses
Nikos Athanasiou retweeted
Introducing CARI4D: category agnostic 4D reconstruction of human object interaction. We reconstruct consistent 4D human-object from just an RGB video.
Website: nvlabs.github.io/CARI4D
Paper: arxiv.org/abs/2512.11988
Code: github.com/NVlabs/CARI4D