2 5 25

Mads Kuhlmann-Joergensen

maalber

https://rapidata.ai

AI & ML interests

None yet

Recent Activity

reacted to jasoncorkill's post with 🔥 6 days ago

This dataset was collected in roughly 4 hours using the Rapidata Python API, showcasing how quickly large-scale annotations can be performed with the right tooling! All that at less than the cost of a single hour of a typical ML engineer in Zurich! The new dataset of ~22,000 human annotations evaluating AI-generated videos based on different dimensions, such as Prompt-Video Alignment, Word for Word Prompt Alignment, Style, Speed of Time flow and Quality of Physics. https://huggingface.co/datasets/Rapidata/text-2-video-Rich-Human-Feedback

reacted to jasoncorkill's post with 🔥 10 days ago

Runway Gen-3 Alpha: The Style and Coherence Champion Runway's latest video generation model, Gen-3 Alpha, is something special. It ranks #3 overall on our text-to-video human preference benchmark, but in terms of style and coherence, it outperforms even OpenAI Sora. However, it struggles with alignment, making it less predictable for controlled outputs. We've released a new dataset with human evaluations of Runway Gen-3 Alpha: Rapidata's text-2-video human preferences dataset. If you're working on video generation and want to see how your model compares to the biggest players, we can benchmark it for you. 🚀 DM us if you’re interested! Dataset: https://huggingface.co/datasets/Rapidata/text-2-video-human-preferences-runway-alpha

liked a dataset 11 days ago

alexandrainst/coral

View all activity

Organizations

maalber's activity

reacted to jasoncorkill's post with 🔥 6 days ago

Post

2479

This dataset was collected in roughly 4 hours using the Rapidata Python API, showcasing how quickly large-scale annotations can be performed with the right tooling!

All that at less than the cost of a single hour of a typical ML engineer in Zurich!

The new dataset of ~22,000 human annotations evaluating AI-generated videos based on different dimensions, such as Prompt-Video Alignment, Word for Word Prompt Alignment, Style, Speed of Time flow and Quality of Physics.

Rapidata/text-2-video-Rich-Human-Feedback

reacted to jasoncorkill's post with 🔥 10 days ago

Post

4517

Runway Gen-3 Alpha: The Style and Coherence Champion

Runway's latest video generation model, Gen-3 Alpha, is something special. It ranks #3 overall on our text-to-video human preference benchmark, but in terms of style and coherence, it outperforms even OpenAI Sora.

However, it struggles with alignment, making it less predictable for controlled outputs.

We've released a new dataset with human evaluations of Runway Gen-3 Alpha: Rapidata's text-2-video human preferences dataset. If you're working on video generation and want to see how your model compares to the biggest players, we can benchmark it for you.

🚀 DM us if you’re interested!

Dataset: Rapidata/text-2-video-human-preferences-runway-alpha

1 reply

liked a dataset 11 days ago

alexandrainst/coral

Viewer • Updated Jan 15 • 239k • 5.24k • 16

liked a dataset 12 days ago

Rapidata/text-2-video-human-preferences-runway-alpha

Viewer • Updated 13 days ago • 632 • 150 • 10

liked 2 datasets 19 days ago

Rapidata/text-2-video-Rich-Human-Feedback

Viewer • Updated 16 days ago • 198 • 447 • 12

Rapidata/sora-video-generation-time-flow

Viewer • Updated 19 days ago • 198 • 164 • 12

upvoted a collection 19 days ago

Sora Rich annotation

Collection

Contains a rich set of different types of annotations for a set of 198 videos • 6 items • Updated 19 days ago • 10

liked 4 datasets 20 days ago

liked a dataset 24 days ago

Rapidata/xAI_Aurora_t2i_human_preferences

Viewer • Updated 20 days ago • 26.2k • 1.15k • 14

reacted to jasoncorkill's post with 👍 24 days ago

Post

2674

We benchmarked @xai-org 's Aurora model, as far as we know the first public evaluation of the model at scale.

We collected 401k human annotations in over the past ~2 days for this, we have uploaded all of the annotation data here on huggingface with a fully permissive license
Rapidata/xAI_Aurora_t2i_human_preferences