Vasileios Lampos
lampos.net
Vasileios Lampos
@lampos.net
Associate Professor @ UCL Computer Science | research: AI, NLP, health | dad | 🇺🇳 | ☮ | here I will be focusing more on less scientific matters, go to https://x.com/lampos for research-related content

Website: lampos.net
Microsoft Sharepoint... 😡 😡 😡 I do not how they do it, but universities manage to opt-in for the worst software platforms possible. Avoid Sharepoint at all costs, if you can. Then, never use WISEflow either.
July 16, 2025 at 4:00 PM
Current state of science in a nutshell: SOTA time series forecasting models that predict a sequence of outputs up to a time step t+H (t: current time step, H: forecasting horizon) evaluate their forecasting accuracy using the entire output sequence.
June 30, 2025 at 9:17 AM
The quality of our EMNLP reviews (mostly rubbish) can be summarised by the typo the reviewer found in our paper. According to them "e.g." should by followed by a comma as in "e.g.,". My dear reviewer this is not the case for British English. We are paying the price of corporate "science".
June 26, 2025 at 3:42 PM
This is yet another great lesson that idiots should never be in positions of power. Yet, no smart person wants to govern. Perhaps, it is about time for a change of perspective on this. People might be forced to become political again when less is left to lose, I suppose.
June 22, 2025 at 4:03 PM
Interesting interview with a sane explanation for Trump's tariffs. Plus a great commentary about AI+tech lords. Yanis Varoufakis (@yanisvaroufakis.bsky.social) certainly gets economics better than many, but he also understands the AI space better than AI "experts".

www.youtube.com/watch?v=Ax7T...
Yanis Varoufakis Explains Trump’s Tariffs
YouTube video by Nexus
www.youtube.com
April 11, 2025 at 5:37 PM
Talent [?] shows and autotune. Funny!

www.youtube.com/watch?v=Xqrc...
They've dropped the ball. AGAIN.
YouTube video by Wings of Pegasus
www.youtube.com
April 7, 2025 at 7:46 AM
"DeformTime: capturing variable dependencies with deformable attention for time series forecasting" led by Yuxuan Shu

Just out @tmlrorg.bsky.social (TMLR)

Link: openreview.net/forum?id=M62...

Plus a teaser figure comparing SOTA forecasters (e.g. TimeXer, iTransformer) with a persistence model!
April 2, 2025 at 9:04 PM
Keir Starmer's statement was deeply confusing. He referred to peace without a deal in place. Yet, he mentioned increased defence budgets and NATO arms on the ground (of Ukraine). I'm not sure Russia will go along with this. My fear is that more intense war will follow.
March 2, 2025 at 5:35 PM
Perhaps we should thank Trump for showing us how the United States of America is bullying other countries into submission. I have never liked bullies.

www.youtube.com/watch?v=Ch0q...
Trump accuses Zelensky of 'gambling with World War Three' in angry White House meeting | BBC News
YouTube video by BBC News
www.youtube.com
February 28, 2025 at 7:53 PM
The land of the free is now directly governed by a billionaire, whereas in the previous "democratic" iteration, it was only an indirect relationship.
February 23, 2025 at 5:23 PM
Fascism is fed from oligarchy and vice versa. What's new to learn?
February 23, 2025 at 5:21 PM
Life expectancy losses in the Gaza Strip during the period
October, 2023, to September, 2024

TLDR: Life expectancy was reduced to half in the Gaza Strip area (of Palestine) compared to prewar levels

Paper: www.thelancet.com/journals/lan...
Life expectancy losses in the Gaza Strip during the period October, 2023, to September, 2024
Our approach to estimating life expectancy losses in this study is conservative as it ignores the indirect effect of the war on mortality. Even ignoring this indirect effect, results show that the ong...
www.thelancet.com
February 14, 2025 at 7:47 AM
Thank you for your interest in this opportunity. I have now invited successful candidates for an interview and will not be considering further applications (for this particular scholarship).
📢 🔊 G-Research UCL PhD Scholarship
-
A fully-funded PhD scholarship has become available at UCL Computer Science (4 years, tuition fees covered, stipend provided). International candidates are also eligible to apply.

/1
February 13, 2025 at 9:16 AM
Nowadays, new PC products tend to be thoroughly tested by the consumers and not the companies that manufacture them.

www.youtube.com/watch?v=Ndmo...

#Nvidia #RTX5090
12VHPWR on RTX 5090 is Extremely Concerning
YouTube video by der8auer EN
www.youtube.com
February 13, 2025 at 9:02 AM
Reposted by Vasileios Lampos
One of the guys from DOGE who's been let loose in the Treasury payments system wrote a book about using deep learning to predict the stock market. Over the weekend I wrote a short review of it.

magnusross.github.io/posts/sparta...
A Spartan's guide to trading | Magnus Ross
magnusross.github.io
February 11, 2025 at 9:42 AM
To time series forecasting people:

Can you please stop evaluating forecasts using the entire output series? It doesn't tell much about the accuracy of a forecast at the actual target forecasting horizon.

And could you please try to understand a task prior to trying to model it?

Thanks!
January 29, 2025 at 10:05 AM
ChatGPT seems to be a more developed end-user LLM than DeepSeek. However, DeepSeek and its RL/R1 module (DeepThink) is way more fun. The sole existence of DeepSeek that currently contradicts the OpenAI business model is the most fun of all. chat.deepseek.com
DeepSeek
Chat with DeepSeek AI.
chat.deepseek.com
January 27, 2025 at 8:56 PM
📢 🔊 G-Research UCL PhD Scholarship
-
A fully-funded PhD scholarship has become available at UCL Computer Science (4 years, tuition fees covered, stipend provided). International candidates are also eligible to apply.

/1
January 17, 2025 at 6:49 PM
A good reminder for those who have not, do watch a TV series titled "Twin Peaks".

www.imdb.com/title/tt0098...
Twin Peaks (TV Series 1990–1991) ⭐ 8.7 | Crime, Drama, Mystery
50m | TV-MA
www.imdb.com
January 17, 2025 at 6:42 PM
Reposted by Vasileios Lampos
I wrote a slightly controversially titled blog post about benchmarking for time series models. Often the benchmarks don't align with real world problems, which I think is slowing progress!

magnusross.github.io/posts/tsf_benchmarks/
Time series benchmarks are broken | Magnus Ross
magnusross.github.io
December 3, 2024 at 11:08 AM