Felix Friedrich's picture

Felix Friedrich

felfri

·

https://ml-research.github.io/people/ffriedrich/

AI & ML interests

GenAI safety/fairness & model steerability

Recent Activity

upvoted an article 5 days ago

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

updated a dataset 6 days ago

felfri/M-ALERT

new activity 9 days ago

mulanai/mulan-lang-adapter:model_index.json missing

View all activity

Organizations

felfri's activity

upvoted an article 5 days ago

Article

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

By

•

16 days ago

• 42

upvoted a collection about 1 month ago

MSTS

3 items • Updated Jan 23 • 1

upvoted a paper about 1 month ago

MSTS: A Multimodal Safety Test Suite for Vision-Language Models

Paper • 2501.10057 • Published Jan 17 • 8

upvoted a paper 2 months ago

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

Paper • 2412.15035 • Published Dec 19, 2024 • 4

upvoted a collection 4 months ago

M-ALERT

evaluating in LLMs on a large scale and with policy compliance. multilingual eval available! • 4 items • Updated about 1 month ago • 2

upvoted a collection 5 months ago

Moshi v0.1 Release

MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi • 13 items • Updated Sep 18, 2024 • 227

upvoted a collection 7 months ago

occiglot-eu5-7b-v0.1

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, 2024 • 21

upvoted 2 papers 8 months ago

SEGA: Instructing Diffusion using Semantic Dimensions

Paper • 2301.12247 • Published Jan 28, 2023 • 6

Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness

Paper • 2302.10893 • Published Feb 7, 2023 • 6

upvoted a paper 9 months ago

LLavaGuard: VLM-based Safeguards for Vision Dataset Curation and Safety Assessment

Paper • 2406.05113 • Published Jun 7, 2024 • 2

upvoted a collection 9 months ago

LlavaGuard

This collection contains the original repos of the LlavaGuard releases • 17 items • Updated Nov 22, 2024 • 6

upvoted a collection 10 months ago

Aurora-M models

Aurora-M models (base, biden-harris redteams and instruct) • 5 items • Updated May 6, 2024 • 17

upvoted an article 11 months ago

Article

Aurora-M: The First Open Source Biden-Harris Executive Order Red teamed Multilingual Language Model

By

•

Apr 2, 2024

• 7

upvoted a paper about 1 year ago

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

Paper • 2311.16711 • Published Nov 28, 2023 • 22