Mathis Pink @MathisPink

👀🧠(x) | x ∈ {👀🧠,🤖} PhD student @mpi_sws_ trying to trick rocks into thinking and remembering. Saarbrücken, Germany Joined August 2020

Tweets

86
Followers

364
Following

3K
Likes

869

Tim Kietzmann @TimKietzmann

2 months ago

Exciting new preprint from the lab: “Adopting a human developmental visual diet yields robust, shape-based AI vision”. A most wonderful case where brain inspiration massively improved AI solutions. Work with @lu_zejin @martisamuser and Radoslaw Cichy arxiv.org/abs/2507.03168

5 48 146 16K 75

Omer Moussa @ohmoussa2

3 months ago

🚨Excited to share our latest work published at Interspeech 2025: “Brain-tuned Speech Models Better Reflect Speech Processing Stages in the Brain”! 🧠🎧 arxiv.org/abs/2506.03832 W/ @mtoneva1 We fine-tuned speech models directly with brain fMRI data, making them more brain-like.🧵

1 5 30 2K 8

Martina Vilas @martinagvilas

5 months ago

We will be presenting this 💫 spotlight 💫 paper at #ICLR2025. Come say hi or DM me if you're interested in discussing AI #interpretability in Singapore! 📆 Poster Session 4 (#530) 🕰️ Fri 25 Apr. 3:00-5:30 PM 📝 openreview.net/forum?id=QogcG… 📊 iclr.cc/virtual/2025/p…

6 28 212 16K 111

Download Image

Sebastian Michelmann @s_michelmann

3 years ago

Excited to share our new preprint bit.ly/402EYEb with @mtoneva1, @ptoncompmemlab, and @manojneuro), in which we ask if GPT-3 (a large language model) can segment narratives into meaningful events similarly to humans. We use an unconventional approach: ⬇️

2 30 94 20K 19

Karan Goel @krandiash

9 months ago

A few interesting challenges in extending context windows. A model with a big prompt =/= "infinite context" in my mind. 10M tokens of context is not exactly on the path to infinite context. Instead, it requires a streaming model that has - an efficient state with fast…

Chubby♨️ @kimmonismus

9 months ago

104 68 1K 233K 397

Download Video

2 10 84 11K 34

François Chollet @fchollet

9 months ago

Anyway, glad to see that the whole "let's just pretrain a bigger LLM" paradigm is dead. Model size is stagnating or even decreasing, while researchers are now looking at the right problems -- either test-time training or neurosymbolic approaches like test-time search, program…

10 34 511 38K 103

Mathis Pink @MathisPink

9 months ago

x.com/MathisPink/sta… We think this is because LLMs do not have parametric episodic memory (as opposed to semantic memory)! We recently created SORT, a new benchmark task that tests temporal order memory in LLMs

Riley Goodside @goodside

9 months ago

69 69 960 128K 278

0 0 4 301 0

François Fleuret @francoisfleuret

10 months ago

Consider the prompt X="Describe a beautiful house." We can consider two processes to generate the answer Y: (A) sample P(Y | X) or, (B) sample an image Z with a conditional image density model P(Z | X) and then sample P(Y | Z). 1/3

5 3 64 13K 28

Mathis Pink @MathisPink

11 months ago

4/n💡We find that fine-tuning or RAG do not support episodic memory capabilities well (yet). In-context presentation supports some episodic memory capabilities but at high costs and insufficient length-generalization, making it a bad candidate for episodic memory!

1 1 4 4K 1

Omer Moussa @ohmoussa2

11 months ago

We are so excited to share the first work that demonstrates consistent downstream improvements for language tasks after fine-tuning with brain data!! Improving semantic understanding in speech language models via brain-tuning arxiv.org/abs/2410.09230 W/ @dklakow, @mtoneva1