Vladimir Salnikov
v4ldelund.bsky.social
Vladimir Salnikov
@v4ldelund.bsky.social
Currently studying Masters in Human centered AI in Technical university of Denmark, interested in 3D vision and Vision Language Models

Previously bachelor student in Lund university
Image-caption dataset, but instead of describing the content of the image people will describe what they feel looking at the image
November 30, 2025 at 9:32 PM
It is interesting that synthetic data is popular within Optical flow research for quite some time already (at least my impression), but only recently started to propagate to other vision tasks (like monocular depth estimation)
Learning about synthetic data generation for computer vision and encountered Flying chairs dataset

I have so many questions, I don't even know where to start
November 29, 2025 at 3:52 PM
Learning about synthetic data generation for computer vision and encountered Flying chairs dataset

I have so many questions, I don't even know where to start
November 29, 2025 at 3:29 PM
They really did put Open in the OpenReview
Let's put a positive spin on it:

Good news, everyone!🥳 The task of screwing up peer review in AI has been solved! There is no way someone can improve significantly over that.
And furthermore, it was done without using Generative AI at all! Good old handcrafted work solved it!

🙃
November 28, 2025 at 2:44 PM
I am strongly considering doing a PhD after my masters, because I feel it is something that might suit me (more ownership/personal freedom/ independence and I feel I like discussing and doing research in general)

But I am so afraid I am not good enough for it ->
November 27, 2025 at 5:54 PM
Denmark in November - outside looks like grayscale Depth map
November 27, 2025 at 5:26 PM
My GPU :
November 27, 2025 at 4:48 PM
The fact that Denmark still doesn't have electrified railway till the second largest city - is kind of shocking

Hopefully it will be fixed soon, and train rides will become more enjoyable and sustainable
November 24, 2025 at 8:57 AM
I am 99% sure that physically based rendering was created so that physicists could feel on their own skin the same pain that mathematicians feel looking at physicists doing math
November 23, 2025 at 5:16 AM
What is the difference between "Inverse Rendering" and "Computer Vision" ?

Or is it just "Inverse Rendering" is what graphics people call computer vision, like how some people in the vision call graphics image synthesis ?
November 23, 2025 at 3:38 AM
Realistically predicting the AGI timeline is like waiting for the Deutsche Bahn train :

Every time the expected departure time just keeps moving further until it is either cancelled, or just wait long enough and pick a next train
In line with recent trends I will create my own AGI timeline and call it :

AI n+1
November 23, 2025 at 2:23 AM
In line with recent trends I will create my own AGI timeline and call it :

AI n+1
November 23, 2025 at 1:40 AM
reviewer 2 - lawful good version
he’s nice even when he’s trashing someone
November 23, 2025 at 12:31 AM
Why can't it be like this for the whole winter 😭😭

I hate global warming
November 22, 2025 at 8:00 PM
Great thing about my education:

I can take up to 30 ECTS in so called "special courses", which are just research projects under PhD student supervision

Which is incredibly fun and way more exciting then regular courses (well at least for me, I am not sure about PhD students who supervise me 😁😁)
November 22, 2025 at 7:57 PM
Before the new Olmo 3 release I thought I was not colorblind

Now I am questioning that
November 20, 2025 at 4:17 PM
Only SAM I care about :
a young man with red hair is wearing a hooded cape and a scarf around his neck .
ALT: a young man with red hair is wearing a hooded cape and a scarf around his neck .
media.tenor.com
November 20, 2025 at 3:05 PM
Just realized that right now on my PC model called "Baguettotron" runs on a benchmark called "Common sense reasoning" in Croatian
November 18, 2025 at 6:36 AM
Copenhagen municipal elections in a nutshell:
November 17, 2025 at 4:50 AM
I am wondering if it is possible to use synthetic data for VLM training (maybe as a supplemental part to real world image-text pairs)

Haven't seen any releases on this topic
Breaking: we release a fully synthetic generalist dataset for pretraining, SYNTH and two new SOTA reasoning models exclusively trained on it. Despite having seen only 200 billion tokens, Baguettotron is currently best-in-class in its size range. pleias.fr/blog/blogsyn...
November 17, 2025 at 4:20 AM
Got an email that I was accepted as a volunteer at EurIPS 🎉🥳

Explained to my girlfriend that EuroIPS is like a Comic con, but for those who know what gradient descent is
November 13, 2025 at 2:44 PM
Hear me out :

University course in AI where students will write tech blogs and post them on their web page, instead of regular notebook-style assignments
November 12, 2025 at 7:26 AM
My first bike in Denmark got stolen 🎉🎉

I mean partially it was my fault (I left it near the S-tog station for a couple of days)

But I honestly thought that my shitty 100€ bike won't be worth the trouble (clearly I was mistaken)
November 7, 2025 at 2:31 PM
There is a new night train between Basel and Malmö 🎉

Pros :
1. New night train in Europe
2. Quite affordable at the time of ticket release (seated around 40€, bed in shared compartment starts from 150€)

Cons :
1. The train goes through Germany (meaning no way it will arrive on time)
November 5, 2025 at 9:27 AM
I am not so sure about the construction cost, considering how damaging the bus of this size to the asphalt below it

When I was living in Lund I saw that almost every year the municipality was changing asphalt near bust stops because of the damage that even regular Man Lions City were doing
Smart tram in Zhuzhou, China. Follows markings on the road, so construction costs are way lower. Basically bus rapid transit but with the option for huge buses.
November 2, 2025 at 5:25 PM