
Researching autonomy, robots and vision algorithms. Ex Staff Software Engineer / 3D Mapping at @OusterLidar, building drones for warehouses
San Francisco
Joined September 2008
- Tweets5.2K
- Following1.6K
- Followers3.3K
- Likes1.1K
Pavlo Bashmakov retweeted
It's strange how much easier it gets not to make certain mistakes after making them just once. You'd think a mistake that was easy to avoid making twice wouldn't be too too difficult to avoid making even once, but that's not usually how it works.
Pavlo Bashmakov retweeted
Training our most capable Gemini models relies heavily on our JAX software stack + Google's TPU hardware platforms.
If you want to learn more, see this awesome book "How to Scale Your Model":
jax-ml.github.io/scaling-boo…
It was put together by my @GoogleDeepMind colleagues
@_sholtodouglas, @charliexychen, @pchoy95, @albertwebson, @vinayramasesh, @froystig, @anselmlevskaya, @sharadvikram, and Fede Lebron, and describing the work of many, many people!
With LLMs (Claude 3.5) you still need to argue and defend the solution until it's understood, i've not expected this and thought the code comprehension of a small contained programs was solved :thinking
Pavlo Bashmakov retweeted
Awesome touch perception work from Meta Robotics researchers, including @mukadammh !
Today at Meta FAIR we’re announcing three new cutting-edge developments in robotics and touch perception — and releasing a collection of artifacts to empower the community to build on this work.
Details on all of this new work ➡️ go.fb.me/mmmu9d
1️⃣ Meta Sparsh is the first general-purpose encoder for vision-based tactile sensing that works across many tactile sensors and many tasks. Trained on 460K+ tactile images using self-supervised learning.
2️⃣ Meta Digit 360 is a breakthrough artificial fingertip-based tactile sensor, equipped with 18+ sensing features to deliver detailed touch data with human-level precision and touch-sensing capabilities.
3️⃣ Meta Digit Plexus is a standardized platform for robotic sensor connections and interactions. It provides a hardware-software solution to integrate tactile sensors on a single robot hand and enables seamless data collection, control and analysis over a single cable.
The potential impact of expanding capabilities and components like these for the open source community ranges from medical research to supply chain, manufacturing and much more. We’re excited to continue this work with the broader community.
Pavlo Bashmakov retweeted
Amazing results!!
I'm excited to share our new work, VistaDream, which generates a 3D Gaussian field from a single-view image. The codes have already been released.
Project page: vistadream-project-page.gith… (with interactive demos)
Code: github.com/WHU-USI3DV/VistaD…
Paper: arxiv.org/abs/2410.16892
Pavlo Bashmakov retweeted
*Shortcut models* are a plug-and-play replacement for diffusion models that can generate in a single step (or more). This speeds up inference by up to 128x.
Shortcut models are trained end-to-end, and do not require a separate distillation phase or learning schedules.
Pavlo Bashmakov retweeted
What is the right benchmark for a 3D Egocentric Foundation model? We recently open-sourced a small, high quality egocentric benchmark consisting of 1) 3D surfaces 2) 3D objects. We released a simple 3D CNN baseline model called EVL: projectaria.com/research/efm…
Try to beat our model!
Pavlo Bashmakov retweeted
How can we infer 3D-consistent poses and dense geometry in real-time given only RGB images?
𝗖𝗢𝗠𝗢 decodes dense geometry from a compact and optimizable set of 3D anchor points to enforce 3D consistency.
Project page: edexheim.github.io/como/
Work with @AjdDavison
1/n
Oh, its brutal
SCOOP: OpenAI may lose $5B this year & may run out of cash in 12 months, unless they raise more $, per analysis @theinformation.
Investors should ask: What is their moat? Unique tech? What is their route in profitability when Meta is giving away similar tech for free? Do they have a killer app? Will the tech ever be reliable? What is real and what is just demo?
Pavlo Bashmakov retweeted
⚡️ Excited to share that I am starting an AI+Education company called Eureka Labs.
The announcement:
---
We are Eureka Labs and we are building a new kind of school that is AI native.
How can we approach an ideal experience for learning something new? For example, in the case of physics one could imagine working through very high quality course materials together with Feynman, who is there to guide you every step of the way. Unfortunately, subject matter experts who are deeply passionate, great at teaching, infinitely patient and fluent in all of the world's languages are also very scarce and cannot personally tutor all 8 billion of us on demand.
However, with recent progress in generative AI, this learning experience feels tractable. The teacher still designs the course materials, but they are supported, leveraged and scaled with an AI Teaching Assistant who is optimized to help guide the students through them. This Teacher + AI symbiosis could run an entire curriculum of courses on a common platform. If we are successful, it will be easy for anyone to learn anything, expanding education in both reach (a large number of people learning something) and extent (any one person learning a large amount of subjects, beyond what may be possible today unassisted).
Our first product will be the world's obviously best AI course, LLM101n. This is an undergraduate-level class that guides the student through training their own AI, very similar to a smaller version of the AI Teaching Assistant itself. The course materials will be available online, but we also plan to run both digital and physical cohorts of people going through it together.
Today, we are heads down building LLM101n, but we look forward to a future where AI is a key technology for increasing human potential. What would you like to learn?
---
@EurekaLabsAI is the culmination of my passion in both AI and education over ~2 decades. My interest in education took me from YouTube tutorials on Rubik's cubes to starting CS231n at Stanford, to my more recent Zero-to-Hero AI series. While my work in AI took me from academic research at Stanford to real-world products at Tesla and AGI research at OpenAI. All of my work combining the two so far has only been part-time, as side quests to my "real job", so I am quite excited to dive in and build something great, professionally and full-time.
It's still early days but I wanted to announce the company so that I can build publicly instead of keeping a secret that isn't. Outbound links with a bit more info in the reply!
This is amazing results!
Our paper "Foundations of Spatial Perception for Robotics: Hierarchical Representations and Real-Time Systems" has been published in the Intl. Journal of Robotics Research (IJRR): journals.sagepub.com/doi/10.…
In conjunction with the IJRR paper, we are pleased to announce ... [1/n]
Pavlo Bashmakov retweeted
Spent six years making this sucker . Hope you guys enjoy. Coming to HBO on July 17
Wild Wild Space | HBO
#WildWildSpace premieres July 17 on @StreamOnMax.
Pavlo Bashmakov retweeted
Some cool work using @gtsam4
DBA-Fusion
[RA-L 2024] Fusing deep dense bundle adjustment (DBA) with multi-sensor factor graph optimization.
github.com/GREAT-WHU/DBA-Fus…
Better maps on the other end!
Neural Visibility Field for Uncertainty-Driven Active Mapping
@ShangjieXue, Jesse Dill, Pranay Mathur, @fdellaert, Panagiotis Tsiotra, @danfei_xu
tl;dr: visibility->uncertainty estimation;distribution of a color along a ray->GMM->entropy->next best view
arxiv.org/pdf/2406.06948
Pavlo Bashmakov retweeted
I'm back to building! Excited to share I've started a company with @pariljain and @lukeholoubek. We're building bots that do chores so you don't have to. Everyone is busy. Bots can help.
So many things compete for our time - commutes, longer working hours, and the complexities of modern life. Our team has spent years building robots (including the self-driving kind) that give people some of that time back, and we're taking that a step further with this company.
We've raised $150m from an amazing group of investors and entrepreneurs, led by @natfriedman, @danielgross, and @nabeel. Also including @QuietCapital, @patrickc, @collision, @eladgil , @byersblake, @fiftyyears, and many more.
More to come soon! Follow our progress here @thebotcompany.
Pavlo Bashmakov retweeted
📢A new learning-based approach to SfM: #ACEZero
No img-to-img matching, optimises image-to-scene correspondences directly. Needs no pose priors. Works on unordered image sets. Efficiently handles thousands of images.
Paper: arxiv.org/abs/2404.14351
Page: nianticlabs.github.io/acezer…
Pavlo Bashmakov retweeted
We are raising baby GR00T with ❤️ in a cozy lab
xitter.cf/DrJimFan/status/176105…
Career update: I am co-founding a new research group called "GEAR" at NVIDIA, with my long-time friend and collaborator Prof. @yukez. GEAR stands for Generalist Embodied Agent Research.
We believe in a future where every machine that moves will be autonomous, and robots and simulated agents will be as ubiquitous as iPhones. We are building the Foundation Agent — a generally capable AI that learns to act skillfully in many worlds, virtual and real.
2024 is the Year of Robotics, the Year of Gaming AI, and the Year of Simulation. We are setting out on a moon-landing mission, and getting there will spin off mountains of learnings and breakthroughs.
Join us on the journey: research.nvidia.com/labs/gea…
Love the depth and basic things mixed together to produce that educational exploration of physics of airflow.
Airfoil – ciechanow.ski/airfoil/


































