iiinova — where your digital self keeps evolving

Teemu Sarapisto @tsarpf.bsky.social · 23/11/2025

Infograph of my previous paper. Generated via Nano Banana Pro. These models are getting quite useful! I think it has genuinely good explanations. Maybe I would've opted for a bit less "AI does this and that", and there are some small mistakes, but not too much to distract from the main message.

210

Teemu Sarapisto @tsarpf.bsky.social · 28/03/2025

Just received the first volume, and damn, clearly a ton of effort was put into it! There's a ~90 page intro to "foundations of complexity science" (which is also sold separately). (The super interesting) papers each have a 5-10 page intro with historical context, and are full of annotations ❤️

1122

Teemu Sarapisto @tsarpf.bsky.social · 20/03/2025

I was out of curiosity scatter plotting a double pendulum's x1/y1/x2/y2 positions in euclidean coordinates against each other.... Turns out they are sooo aesthetic 😍

130

Teemu Sarapisto @tsarpf.bsky.social · 05/03/2025

Two very interesting papers on identifiably (provably) recovering "true"/unique latent states + dynamics / time-evolution from high-dimensional data in ICLR2025: 1. VAE + nonlinear ICA-style aux variables openreview.net/forum?id=d16... 2. Contrastive learning openreview.net/forum?id=ONf...

openreview.net

Self-supervised contrastive learning performs non-linear system...

Self-supervised learning (SSL) approaches have brought tremendous success across many tasks and domains. It has been argued that these successes can be attributed to a link between SSL and...

010

Teemu Sarapisto @tsarpf.bsky.social · 28/01/2025

Basic idea of #DeepSeek R1, the new RL LLM model: Start from a pretrained LLM, sample K responses for tasks (e.g., LeetCode problems with N tests). Update weights to favor better-than-average responses, as the true correct code is unknown. Also, reward correct output format. #LLM #genAI #RL

030

Teemu Sarapisto @tsarpf.bsky.social · 22/11/2024

Interested to see if a proper academic bsky will happen! The amount of great papers and memes I found on Twitter made me stick to it this long, but definitely something new would be nice.

010

Teemu Sarapisto @tsarpf.bsky.social · 22/11/2024

Hi, lets try bsky! New paper: Subsystem Discovery in High-Dimensional Time-Series Using Masked Autoencoders Code/data/paper: github.com/helsinki-sda... Presented at European Conference on Artificial Intelligence 2024 Map graph learned from weather #timeseries, adjacency from 7 engines!

020