Excited to share our new research at Jasper Research! 🚀

LBM: Latent Bridge Matching for Fast Image-to-Image Translation

Try out our @hf.co space for object relighting!

🤗 @gradio-hf.bsky.social demo: huggingface.co/spaces/jaspe...
👉 Paper: arxiv.org/abs/2503.07535
💻 Repo: github.com/gojasper/LBM

Alright who’s making this

Align3R: estimates camera poses and consistent depth maps from monocular videos.

Combining it with trackers like Cotracker3 or SAM2 could unlock many fun applications! (cf: VideoDoodles by Yu & al)

Project page (with demo): igl-hkust.github.io/Align3R.gith...
Code: github.com/jiah-cloud/A...

Am I the only one amazed that this is what 2*4TB (with thermal case) looks like now?

The UX of LEGO Interface Panels interactionmagic.com/UX-LEGO-Inte...

Oh no 😂 I’m torn between rofl for this troll and a fear to see this little drama escalating

The past few months have been... intense! There's still quite some work to do before the finish line, but excited to launch in the coming weeks 💪⚡️

Adobe Podcast V2 is a really impressive audio enhancer.
Is there any open-source tech close to it?

bsky.app/profile/pins...

SAMURAI: improve the tracking robustness of SAM2 with 2 main contributions:
- adding motion information to the mask selection
- curating the memory bank based on motion cues

Project: yangchris11.github.io/samurai
Code: github.com/yangchris11/...
Paper: arxiv.org/abs/2411.11922

Pyramid Flow is quite impressive for img2video, given than it was only trained on public datasets. Clearly not as dynamic and stable as commercial solutions, but the gap seems to be closing github.com/jy0205/Pyram...

A bit surprised with this data from Clerk on sign-in methods preferences: From a sample of 2.5M sign-in, <2% of users chose to use magic links.

"A nicely maintained and over-spec’d server just has a smell to it" - great writeup by @kcimc.bsky.social benchmarking various cloud GPU providers for a realtime diffusion installation: kcimc.medium.com/realtime-dif...

Very cool idea for working with videos and transformers: remove duplicate patches and add length embeddings instead. They get a 40% speedup finetuning Vit-L using example packing.

Run-Length Tokenization (NeurIPS 2024 spotlight):
Project: rccchoudhury.github.io/rlt
Code: github.com/rccchoudhury...

Hello there! I’m an AI indie hacker based in Paris.
I love everything related to generative AI, from research papers and techniques to cool AI content, frontend dev…etc.
I’m currently working on generative video models, and working hard to do a public release in the coming weeks.
Cheers ✌️