Patrick Schramowski

PSaiml's activity

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

authored a paper 3 days ago

LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Gaps

Paper • 2412.15035 • Published 7 days ago • 4

upvoted an article 7 months ago

view article

Article

Announcing Occiglot-Fineweb

By •

Jun 4

• 6

liked 3 datasets 7 months ago

AIML-TUDA/TEdBench_plusplus

Viewer • Updated Nov 27, 2023 • 139 • 241 • 14

AIML-TUDA/i2p-adversarial-split

Viewer • Updated Oct 11, 2023 • 1.1k • 44 • 4

AIML-TUDA/LlavaGuard

Updated Jun 13 • 46 • 8

liked a dataset 8 months ago

Babelscape/ALERT

Viewer • Updated Jun 20 • 45.7k • 242 • 10

authored a paper 8 months ago

Introducing v0.5 of the AI Safety Benchmark from MLCommons

Paper • 2404.12241 • Published Apr 18 • 10

upvoted a collection 10 months ago

occiglot-eu5-7b-v0.1

Collection

First release of 7B LLMs models for the 5 biggest European languages. All models initialised from mistral-7b-v0.1. • 10 items • Updated Mar 7 • 21

New activity in editing-images/leditsplusplus about 1 year ago

Question about the reproduction of the edited images with LEdits++ on TEdBench++

2

#12 opened about 1 year ago by

badzzz

liked a Space about 1 year ago

Running on A10G

413

🦀

LEDITS++

authored a paper about 1 year ago

LEDITS++: Limitless Image Editing using Text-to-Image Models

Paper • 2311.16711 • Published Nov 28, 2023 • 22

liked a Space over 1 year ago

Runtime error

21

🦁

LeoLM 7b Chat

updated 2 Spaces over 1 year ago

Runtime error

21

🦁

LeoLM 7b Chat

Runtime error

40

🦁

LeoLM 13b Chat

liked a Space over 1 year ago

Runtime error

40

🦁

LeoLM 13b Chat

authored 5 papers over 1 year ago

Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models

Paper • 2211.05105 • Published Nov 9, 2022

Speaking Multiple Languages Affects the Moral Bias of Language Models

Paper • 2211.07733 • Published Nov 14, 2022 • 1

Revision Transformers: Instructing Language Models to Change their Values

Paper • 2210.10332 • Published Oct 19, 2022

Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulations

Paper • 2303.09289 • Published Mar 16, 2023 • 1

The Stable Artist: Steering Semantics in Diffusion Latent Space

Paper • 2212.06013 • Published Dec 12, 2022