Hugging Face's logo
Marian Kannwischer's picture
3 29

Marian Kannwischer PRO

canwiper
Alliance529's profile picture jasoncorkill's profile picture davanstrien's profile picture
·

AI & ML interests

RLHF & Computer Vision

Recent Activity

liked a dataset 2 days ago
Rapidata/OpenGVLab_Lumina_t2i_human_preference
reacted to jasoncorkill's post with 🔥 3 days ago
The Sora Video Generation Aligned Words dataset contains a collection of word segments for text-to-video or other multimodal research. It is intended to help researchers and engineers explore fine-grained prompts, including those where certain words are not aligned with the video. We hope this dataset will support your work in prompt understanding and advance progress in multimodal projects. If you have specific questions, feel free to reach out. https://huggingface.co./datasets/Rapidata/sora-video-generation-aligned-words
reacted to jasoncorkill's post with 👀 16 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
View all activity

Organizations

mlo-data-cleaning's profile picture mlo-data-collab's profile picture Rapidata's profile picture

canwiper's activity

liked a dataset 2 days ago
reacted to jasoncorkill's post with 🔥 3 days ago
view post
Post
2442
The Sora Video Generation Aligned Words dataset contains a collection of word segments for text-to-video or other multimodal research. It is intended to help researchers and engineers explore fine-grained prompts, including those where certain words are not aligned with the video.

We hope this dataset will support your work in prompt understanding and advance progress in multimodal projects.

If you have specific questions, feel free to reach out.
Rapidata/sora-video-generation-aligned-words
reacted to jasoncorkill's post with 👀 16 days ago
view post
Post
4528
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 24 days ago
upvoted a collection 24 days ago
liked 2 datasets 24 days ago
liked 3 datasets 25 days ago
reacted to jasoncorkill's post with 🔥 28 days ago
view post
Post
2677
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
liked a dataset 29 days ago
liked 2 datasets about 1 month ago
liked 6 datasets about 2 months ago