2 11

Maria Marina

zlatamaria

marialysyuk

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 minute ago

Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models

upvoted a paper 1 day ago

Image Reconstruction as a Tool for Feature Analysis

upvoted a paper 1 day ago

Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models

View all activity

Organizations

None yet

zlatamaria's activity

upvoted a paper 1 minute ago

Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models

Paper • 2506.06395 • Published 7 days ago • 35

upvoted 2 papers 1 day ago

Image Reconstruction as a Tool for Feature Analysis

Paper • 2506.07803 • Published 3 days ago • 27

Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models

Paper • 2506.06751 • Published 5 days ago • 58

authored 3 papers 3 days ago

Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home

Paper • 2501.12835 • Published Jan 22 • 4

LLM-Independent Adaptive RAG: Let the Question Speak for Itself

Paper • 2505.04253 • Published May 7 • 12

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

Paper • 2505.21115 • Published 16 days ago • 115

commented 2 papers 3 days ago

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

Paper • 2505.21115 • Published 16 days ago • 115 •

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

Paper • 2505.21115 • Published 16 days ago • 115 •

upvoted a paper 3 days ago

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

Paper • 2505.21115 • Published 16 days ago • 115

commented a paper 3 days ago

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

Paper • 2505.21115 • Published 16 days ago • 115 •

upvoted a paper 7 days ago

AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment

Paper • 2506.04089 • Published 8 days ago • 45

upvoted a paper 15 days ago

Exploring the Latent Capacity of LLMs for One-Step Text Generation

Paper • 2505.21189 • Published 16 days ago • 60

upvoted a paper 23 days ago

Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images

Paper • 2505.07704 • Published about 1 month ago • 29

upvoted 2 papers 3 months ago

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Paper • 2503.03601 • Published Mar 5 • 234

RuCCoD: Towards Automated ICD Coding in Russian

Paper • 2502.21263 • Published Feb 28 • 133

commented a paper 4 months ago

How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?

Paper • 2502.14502 • Published Feb 20 • 91 •

upvoted a paper 4 months ago

MoM: Linear Sequence Modeling with Mixture-of-Memories

Paper • 2502.13685 • Published Feb 19 • 36

authored a paper 4 months ago

How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?

Paper • 2502.14502 • Published Feb 20 • 91

upvoted a paper 4 months ago

How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?

Paper • 2502.14502 • Published Feb 20 • 91

updated a dataset about 1 year ago

zlatamaria/RuBQ

Viewer • Updated Apr 4, 2024 • 1.19k • 14