Pavlo Bashmakov @bashmakov

Researching autonomy, robots and vision algorithms. Ex Staff Software Engineer / 3D Mapping at @OusterLidar, building drones for warehouses capsulesbot.com San Francisco Joined September 2008

Tweets

5K
Followers

3K
Following

2K
Likes

1K

Glenn Tunes @glenn_tunes

a month ago

THIS IS HOW YOU INTERVIEW TRUMP AND SHOW THE WORLD WHO AND WHAT HE IS ✊✊✊✊

2K 35K 292K 4.5M 13K

View Details

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-book/ 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!

Jacob Austin @jacobaustin132

a year ago

Making LLMs run efficiently can feel scary, but scaling isn’t magic, it’s math! We wanted to demystify the “systems view” of LLMs and wrote a little textbook called “How To Scale Your Model” which we’re releasing today. 1/n

25 393 2K 465K 3K

23 163 981 129K 665

View Details

Pavlo Bashmakov @bashmakov

2 years ago

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

0 0 0 171 0

View Details

Frank Dellaert @fdellaert

2 years ago

Awesome touch perception work from Meta Robotics researchers, including @mukadammh !

AI at Meta @AIatMeta

2 years ago

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

81 491 3K 453K 913

0 3 14 1K 3

View Details

Lingjie Liu @LingjieLiu1

2 years ago

Amazing results!!

Yuan Liu @YuanLiu41955461

2 years ago

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.github.io (with interactive demos) Code: github.com/WHU-USI3DV/Vis… Paper: arxiv.org/abs/2410.16892

21 138 827 80K 630

1 1 38 5K 10

View Details

Kevin Frans @kvfrans

2 years ago

*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.

17 104 679 142K 470

View Details

Daniel DeTone @ddetone

2 years ago

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/efm3d/ Try to beat our model!

1 40 226 22K 135

View Details

Pavlo Bashmakov @bashmakov

2 years ago

nice!

0 0 3 275 0

View Details

Eric Dexheimer @eric_dexheimer

2 years ago

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

3 54 265 42K 157

View Details

Pavlo Bashmakov @bashmakov

2 years ago

@GaryMarcus Seems like a good summary of the info from the page that it refers too busbud.com/en/train-new-y… and btw, Russia troops recently took New York, after prolonged shelling.

0 0 1 15 0

View Details

Pavlo Bashmakov @bashmakov

2 years ago

Oh, its brutal

Gary Marcus @GaryMarcus

2 years ago

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

199 494 3K 964K 1K

0 0 1 214 0

View Details

Andrej Karpathy @karpathy

2 years ago

⚡️ 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!

2K 4K 28K 2.5M 8K

View Details

Pavlo Bashmakov @bashmakov

2 years ago

This is amazing results!

Luca Carlone @lucacarlone1

2 years ago

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/10.1177/02… In conjunction with the IJRR paper, we are pleased to announce ... [1/n]

1 16 99 8K 46

0 0 0 144 0

View Details

Ashlee Vance @ashleevance

2 years ago

Spent six years making this sucker . Hope you guys enjoy. Coming to HBO on July 17

247 593 6K 792K 2K

View Details

Frank Dellaert @fdellaert

2 years ago

Some cool work using @gtsam4

Ryohei Sasaki@engineer @rsasaki0109

2 years ago

DBA-Fusion [RA-L 2024] Fusing deep dense bundle adjustment (DBA) with multi-sensor factor graph optimization. github.com/GREAT-WHU/DBA-…

0 17 107 9K 45

0 3 24 4K 10

View Details

Pavlo Bashmakov @bashmakov

2 years ago

Better maps on the other end!

Zhenjun Zhao @zhenjun_zhao

2 years ago

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

2 11 71 11K 28

0 0 0 176 0

View Details

Kyle Vogt @kvogt

2 years ago

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.

102 65 1K 368K 276

View Details

Eric Brachmann @eric_brachmann

2 years ago

📢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/acezero

12 89 478 71K 276

View Details

Jim Fan @DrJimFan

2 years ago

We are raising baby GR00T with ❤️ in a cozy lab x.com/DrJimFan/statu…

Jim Fan @DrJimFan

2 years ago

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