Excited to share our new research at Jasper Research! ๐
LBM: Latent Bridge Matching for Fast Image-to-Image Translation
Try out our @hf.co space for object relighting!
๐ค @gradio-hf.bsky.social demo: huggingface.co/spaces/jaspe...
๐ Paper: arxiv.org/abs/2503.07535
๐ป Repo: github.com/gojasper/LBM
13.03.2025 16:00 โ ๐ 22 ๐ 7 ๐ฌ 2 ๐ 4
Amazing!
14.03.2025 08:10 โ ๐ 2 ๐ 0 ๐ฌ 1 ๐ 0
Wow awesome work!! ๐คฉ
14.03.2025 08:09 โ ๐ 3 ๐ 0 ๐ฌ 0 ๐ 0
Alright whoโs making this
07.03.2025 17:08 โ ๐ 4 ๐ 0 ๐ฌ 0 ๐ 0
oh wow looks awesome, somehow missed it
25.01.2025 15:42 โ ๐ 4 ๐ 0 ๐ฌ 0 ๐ 0
๐
16.01.2025 15:44 โ ๐ 5 ๐ 0 ๐ฌ 0 ๐ 0
Hopefully they'll remove some of the FP16 nerfs they have on the 4090.. The 2-slots factor is also a nice improvement for multi-gpu builds
16.01.2025 08:52 โ ๐ 6 ๐ 0 ๐ฌ 1 ๐ 0
๐ฅฐ
11.12.2024 19:50 โ ๐ 3 ๐ 0 ๐ฌ 0 ๐ 0
How does one keep track? The monodepth/tracking field these days:
06.12.2024 10:05 โ ๐ 13 ๐ 2 ๐ฌ 0 ๐ 0
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...
06.12.2024 09:48 โ ๐ 24 ๐ 3 ๐ฌ 2 ๐ 0
Am I the only one amazed that this is what 2*4TB (with thermal case) looks like now?
04.12.2024 09:41 โ ๐ 9 ๐ 0 ๐ฌ 0 ๐ 0
๐ฎ - wall street seems to take the news well though
02.12.2024 16:24 โ ๐ 2 ๐ 0 ๐ฌ 1 ๐ 0
quite the illustration ๐
01.12.2024 12:32 โ ๐ 2 ๐ 0 ๐ฌ 0 ๐ 0
Banned from bsky or HF?
28.11.2024 12:48 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
fair enough!
28.11.2024 11:44 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Oh no ๐ Iโm torn between rofl for this troll and a fear to see this little drama escalating
28.11.2024 10:38 โ ๐ 7 ๐ 0 ๐ฌ 1 ๐ 0
Look Ma, no markers
Why the preference for multiview? Maybe something like github.com/ttxskk/AiOS can be adapted/finetuned with multiple views from a synthetic dataset like microsoft.github.io/SynthMoCap/
27.11.2024 23:26 โ ๐ 2 ๐ 0 ๐ฌ 1 ๐ 0
oh nice, bookmarked!
27.11.2024 21:53 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
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 ๐ชโก๏ธ
27.11.2024 16:42 โ ๐ 13 ๐ 0 ๐ฌ 2 ๐ 0
And early social media platforms!
22.11.2024 16:35 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Resemble Enhance seems pretty good: github.com/resemble-ai/...
22.11.2024 08:39 โ ๐ 6 ๐ 0 ๐ฌ 1 ๐ 0
Adobe Podcast V2 is a really impressive audio enhancer.
Is there any open-source tech close to it?
bsky.app/profile/pins...
22.11.2024 08:38 โ ๐ 8 ๐ 1 ๐ฌ 2 ๐ 0
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
21.11.2024 08:17 โ ๐ 17 ๐ 6 ๐ฌ 0 ๐ 1
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...
20.11.2024 09:35 โ ๐ 4 ๐ 0 ๐ฌ 0 ๐ 0
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.
20.11.2024 09:31 โ ๐ 2 ๐ 1 ๐ฌ 0 ๐ 0
Yessss ๐ฅ๐ฅ
19.11.2024 19:20 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Realtime diffusion in the cloud
In December 2023, I implemented a realtime diffusion toolkit with Daito Manabe and Rhizomatiks. The toolkit is based on SDXL Turbo runningโฆ
"A nicely maintained and over-specโd 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...
19.11.2024 09:18 โ ๐ 12 ๐ 2 ๐ฌ 0 ๐ 0
new life goal: be added to that list ๐
18.11.2024 21:38 โ ๐ 3 ๐ 0 ๐ฌ 0 ๐ 0
These are really impressive
18.11.2024 19:44 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0
Computational วสศถษจึศถ; Curious philomath;
Cosmosapience;
CosmosยทConsciousnessยทLifeยทIntelligence; EcologyยทTechnologyยทScienceยทRitualยทSpirituality;
PhD ArtรAI;
Prof @UCSD;
memo.tv
superradiance.net
Postdoc at Kyutai
https://juliettemarrie.github.io
Professor of Marketing at NYU Stern School of Business, serial entrepreneur, and host of the Prof G and Pivot Podcasts.
Technology news and analysis with a focus on founders and startup teams.
Got a tip? http://techcrunch.com/tips
Top news and commentary for technology's leaders, from all around the web.
This account shares top-level Techmeme headlines. Visit https://techmeme.com/ for full context.
https://mkremins.github.io
The best of FT journalism, including breaking news and analysis.
https://www.ft.com
The users this account follows are verified FT staff or contributors.
Google Chief Scientist, Gemini Lead. Opinions stated here are my own, not those of Google. Gemini, TensorFlow, MapReduce, Bigtable, Spanner, ML things, ...
Amanda Katz said this was the cool kids table.
AI & CV scientist, CEO at @kyutai-labs.bsky.social
๐ Bienvenue sur le compte Bluesky de la Ville de Pantin !
Professor, University of Tรผbingen @unituebingen.bsky.social.
Head of Department of Computer Science ๐.
Faculty, Tรผbingen AI Center ๐ฉ๐ช @tuebingen-ai.bsky.social.
ELLIS Fellow, Founding Board Member ๐ช๐บ @ellis.eu.
CV ๐ท, ML ๐ง , Self-Driving ๐, NLP ๐บ
AI nerd by day & writer by night โ๏ธ
Books, bold tales, & business ideas fuel my life.
Author๐| Growth Mktg ๐| Biz & Trends๐ธ
Co-CEO, Yutori. Join the waitlist at yutori.com
Prof (CS @Stanford), Co-Director @StanfordHAI, Cofounder/CEO @theworldlabs, CoFounder @ai4allorg #AI #computervision #robotics #AI-healthcare
Seรฑor swesearcher @ Google DeepMind, adjunct prof at Universitรฉ de Montrรฉal and Mila. Musician. From ๐ช๐จ living in ๐จ๐ฆ.
https://psc-g.github.io/