Irina Proskurina PRO

iproskurina's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 3 days ago

The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Data

Paper • 2608.04268 • Published Aug 4 • 1

upvoted a paper 5 days ago

Debias-SparseGPT: Bias-Aware Pruning for Large Language Models

Paper • 2609.02496 • Published 7 days ago • 3

upvoted a paper 7 days ago

Fair-GPTQ: Bias-Aware Quantization for Large Language Models

Paper • 2509.15206 • Published Sep 18, 2025 • 1

upvoted a paper 24 days ago

Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity

Paper • 2608.13430 • Published 27 days ago • 13

upvoted a paper 25 days ago

Alaya-EVOKE: From Linear-Scaling Supervision to Endless World

Paper • 2608.13546 • Published 27 days ago • 166

upvoted a paper 2 months ago

HatePrototypes: Interpretable and Transferable Representations for Implicit and Explicit Hate Speech Detection

Paper • 2511.06391 • Published Apr 5 • 1

upvoted a paper 4 months ago

When Vision Speaks for Sound

Paper • 2605.16403 • Published May 13 • 161

upvoted a paper over 1 year ago

Histoires Morales: A French Dataset for Assessing Moral Alignment

Paper • 2501.17117 • Published Jan 28, 2025 • 5

upvoted an article about 2 years ago

view article

Article

Understanding Vector Quantization in VQ-VAE

• 

ariG23498

•

Aug 28, 2024

• 65