Maciej Chrabąszcz

mchraba's activity

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

authored a paper about 1 month ago

Conditioned Activation Transport for T2I Safety Steering

Paper • 2603.03163 • Published Mar 3 • 1

submitted a paper to Daily Papers about 2 months ago

Conditioned Activation Transport for T2I Safety Steering

Paper • 2603.03163 • Published Mar 3 • 1

published a dataset about 2 months ago

NASK-PIB/SafeSteerDataset

Viewer • Updated Mar 4 • 2.3k • 19 • 2

updated a dataset about 2 months ago

NASK-PIB/SafeSteerDataset

Viewer • Updated Mar 4 • 2.3k • 19 • 2

authored 2 papers 2 months ago

PLLuM: A Family of Polish Large Language Models

Paper • 2511.03823 • Published Nov 5, 2025

The PLLuM Instruction Corpus

Paper • 2511.17161 • Published Nov 21, 2025

authored a paper 5 months ago

Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation

Paper • 2507.06363 • Published Jul 8, 2025

updated a collection 9 months ago

PLLuM 12B-nc-250715

Collection

Collection containing all PLLuM 12B-nc-250715 models • 6 items • Updated Mar 2 • 2

authored a paper 10 months ago

Evaluating LLMs Robustness in Less Resourced Languages with Proxy Models

Paper • 2506.07645 • Published Jun 9, 2025 • 3

commented a paper 10 months ago

Evaluating LLMs Robustness in Less Resourced Languages with Proxy Models

Paper • 2506.07645 • Published Jun 9, 2025 • 3 •

2

authored 2 papers about 1 year ago

Be Careful When Evaluating Explanations Regarding Ground Truth

Paper • 2311.04813 • Published Nov 8, 2023

Maybe I Should Not Answer That, but... Do LLMs Understand The Safety of Their Inputs?

Paper • 2502.16174 • Published Feb 22, 2025

authored 2 papers over 1 year ago

Swin SMT: Global Sequential Modeling in 3D Medical Image Segmentation

Paper • 2407.07514 • Published Jul 10, 2024

Aggregated Attributions for Explanatory Analysis of 3D Segmentation Models

Paper • 2407.16653 • Published Jul 23, 2024