2 20 105

Kostis Gourgoulias

kgourgou

http://kgourgou.me

AI & ML interests

Language modeling, few-shot learning, bayesian inference, information theory, uncertainty quantification.

Recent Activity

liked a dataset 1 day ago

mlabonne/ultrafeedback-sft

reacted to Jaward's post with 👀 1 day ago

Super Interesting Paper! Proposes neural networks (CRNNs) that can learn to produce traveling waves in their hidden state in response to visual stimuli, thus enabling the transfer and integration of spatial information across neural connections. In other words they showed that neural networks have wave-like properties that blends and processes visual information over time, cool seeing a union of AI and physics in this way. Paper: https://arxiv.org/pdf/2502.06034 Code: https://github.com/KempnerInstitute/traveling-waves-integrate

new activity 7 days ago

madrylab/gsm8k-platinum:Typo

View all activity

Organizations

kgourgou's activity

upvoted a collection 9 days ago

Hallucination detection

Collection

Trained ModernBERT (base and large) for detection hallucinations in LLM responses. The models are trained as token classifications. • 4 items • Updated 8 days ago • 15

upvoted a paper 27 days ago

An Open Recipe: Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging

Paper • 2502.09056 • Published 28 days ago • 30

upvoted a paper about 1 month ago

Agency Is Frame-Dependent

Paper • 2502.04403 • Published Feb 6 • 22

upvoted an article about 2 months ago

Article

Train 400x faster Static Embedding Models with Sentence Transformers

Jan 15

• 159

upvoted a paper 8 months ago

Can Large Language Models Infer Causation from Correlation?

Paper • 2306.05836 • Published Jun 9, 2023 • 6

upvoted a paper 9 months ago

TextGrad: Automatic "Differentiation" via Text

Paper • 2406.07496 • Published Jun 11, 2024 • 31

upvoted a collection 10 months ago

Models and Linearity

Collection

2 items • Updated Jun 14, 2024 • 1

upvoted 2 papers 10 months ago

Your Transformer is Secretly Linear

Paper • 2405.12250 • Published May 19, 2024 • 153

Not All Language Model Features Are Linear

Paper • 2405.14860 • Published May 23, 2024 • 41

upvoted an article 10 months ago

Article

Let's talk about LLM evaluation

•

May 23, 2024

• 158

upvoted an article 11 months ago

Article

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent

Apr 22, 2024

• 80

upvoted 2 papers 11 months ago

Low-rank Adaptation of Large Language Model Rescoring for Parameter-Efficient Speech Recognition

Paper • 2309.15223 • Published Sep 26, 2023 • 19

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 14

upvoted a collection about 1 year ago

Model Merging

Collection

Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it! • 30 items • Updated Jun 12, 2024 • 234

upvoted a paper about 1 year ago

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Paper • 2203.05482 • Published Mar 10, 2022 • 6

upvoted a collection about 1 year ago

Papers about model merging

Collection

referenced in the mergekit repo: https://github.com/cg123/mergekit • 4 items • Updated Feb 13, 2024 • 14

upvoted a paper about 1 year ago

LLM in a flash: Efficient Large Language Model Inference with Limited Memory

Paper • 2312.11514 • Published Dec 12, 2023 • 259

upvoted a paper over 1 year ago

Textbooks Are All You Need

Paper • 2306.11644 • Published Jun 20, 2023 • 142