iiinova — where your digital self keeps evolving

Vasileios Lampos @lampos.net · 16/07/2025

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.

000

Vasileios Lampos @lampos.net · 30/06/2025

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.

110

Vasileios Lampos @lampos.net · 26/06/2025

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".

010

Vasileios Lampos @lampos.net · 22/06/2025

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.

000

Vasileios Lampos @lampos.net · 11/04/2025

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...

youtube.com

Yanis Varoufakis Explains Trump’s Tariffs

YouTube video by Nexus

000

Vasileios Lampos @lampos.net · 02/04/2025

"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!

28 days ahead forecasting results for influenza rates for the season 2018/19 in England for all models in our study. DeformTime, the model we proposes, performs best (and quite accurately), whereas some of the other forecasters (e.g. PatchTST, iTransformer, TimeXer) are very similar to a persistence model, i.e. they are performing very poorly.

010

Vasileios Lampos @lampos.net · 02/03/2025

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.

010

Vasileios Lampos @lampos.net · 28/02/2025

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...

youtube.com

Trump accuses Zelensky of 'gambling with World War Three' in angry White House meeting | BBC News

YouTube video by BBC News

000

Vasileios Lampos @lampos.net · 23/02/2025

The land of the free is now directly governed by a billionaire, whereas in the previous "democratic" iteration, it was only an indirect relationship.

000

Vasileios Lampos @lampos.net · 23/02/2025

Fascism is fed from oligarchy and vice versa. What's new to learn?

000

Vasileios Lampos @lampos.net · 14/02/2025

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...

thelancet.com

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...

021

Vasileios Lampos @lampos.net · 13/02/2025

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).

000

Vasileios Lampos @lampos.net · 13/02/2025

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

youtube.com

12VHPWR on RTX 5090 is Extremely Concerning

YouTube video by der8auer EN

000

Reposted by Vasileios Lampos

Magnus Ross @magnusar.bsky.social · 11/02/2025

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...

magnusross.github.io

A Spartan's guide to trading | Magnus Ross

142

Vasileios Lampos @lampos.net · 29/01/2025

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!

020

Vasileios Lampos @lampos.net · 27/01/2025

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

chat.deepseek.com

DeepSeek

Chat with DeepSeek AI.

000

Vasileios Lampos @lampos.net · 17/01/2025

📢 🔊 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

110

Vasileios Lampos @lampos.net · 17/01/2025

A good reminder for those who have not, do watch a TV series titled "Twin Peaks". www.imdb.com/title/tt0098...

imdb.com

Twin Peaks (TV Series 1990–1991) ⭐ 8.7 | Crime, Drama, Mystery

50m | TV-MA

030

Reposted by Vasileios Lampos

Magnus Ross @magnusar.bsky.social · 03/12/2024

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/

magnusross.github.io

Time series benchmarks are broken | Magnus Ross

173