Felix Friedrich's picture

Open to Collab

Felix Friedrich

felfri

·

https://felifri.github.io/

AI & ML interests

Multimodal AI; Post-training/Inference; AI Safety; AI Alignment

Recent Activity

liked a model about 16 hours ago

black-forest-labs/FLUX.2-klein-base-4B

upvoted a collection about 16 hours ago

liked a model about 16 hours ago

black-forest-labs/FLUX.2-klein-9b-kv

View all activity

Organizations

upvoted a collection about 16 hours ago

FLUX.2

Our second generation of FLUX • 20 items • Updated 8 days ago • 158

upvoted an article 14 days ago

Article

We’re open-sourcing our text-to-image model and the process behind it

Nov 12, 2025

•

96

upvoted a collection 14 days ago

PRX

PRX text-to-image models • 9 items • Updated Nov 10, 2025 • 11

upvoted 3 articles 14 days ago

Article

Text-to-image Architectural Experiments

Nov 13, 2025

•

55

Article

Training Design for Text-to-Image Models: Lessons from Ablations

Feb 3

•

69

Article

PRX Part 3 — Training a Text-to-Image Model in 24h!

17 days ago

•

55

upvoted a paper 2 months ago

Inference-time Physics Alignment of Video Generative Models with Latent World Models

Paper • 2601.10553 • Published Jan 15 • 12

upvoted a collection 5 months ago

EmoNet-Voice

2 items • Updated 18 days ago • 2

upvoted a paper 5 months ago

OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows

Paper • 2510.03506 • Published Oct 3, 2025 • 15

upvoted a paper 6 months ago

Measuring and Guiding Monosemanticity

Paper • 2506.19382 • Published Jun 24, 2025 • 2

upvoted a paper 9 months ago

EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition

Paper • 2505.20033 • Published May 26, 2025 • 4

upvoted a collection 9 months ago

How to Train your Text‑to‑Image Model

4 items • Updated Jun 23, 2025 • 1

upvoted an article 9 months ago

Article

DO THEY SEE WHAT WE SEE?

Jun 22, 2025

•

6

upvoted a paper 9 months ago

EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection

Paper • 2506.09827 • Published Jun 11, 2025 • 21

upvoted a paper 10 months ago

Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Models

Paper • 2505.22232 • Published May 28, 2025 • 18

upvoted an article about 1 year ago

Article

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

Feb 7, 2025

•

280

upvoted a collection about 1 year ago

MSTS

3 items • Updated Jan 23, 2025 • 1

upvoted 2 papers about 1 year ago

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

Paper • 2501.10057 • Published Jan 17, 2025 • 10

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

Paper • 2412.15035 • Published Dec 19, 2024 • 4

upvoted a collection over 1 year ago

M-ALERT

evaluating in LLMs on a large scale and with policy compliance. multilingual eval available! • 4 items • Updated Jan 24, 2025 • 2