Simple ML.
London, UK
Joined August 2023
- Tweets443
- Following155
- Followers1.1K
- Likes8.1K
Pinned Tweet
A Significantly simplified 2D Gaussian Splatting as part of a bigger research experiment regarding image signal processing that I am working on
Github : github.com/OutofAi/2D-Gaussi…
For those looking to gain a deeper understanding of Gaussian splatting, this is an excellent starting point.
The observed noise during convergence is attributed to densification (pruning/cloning/splitting)
OutofAi retweeted
Come work with us @BritishProgress! A great role for a data virtuoso new grad
🚨 We’re hiring: Data Analyst 🚨
Join us @BritishProgress to source, clean and analyse UK policy data and turn it into clear charts and sharp written analysis that drives our research programme.
We’re looking for someone quantitatively rigorous, AI-native in their workflow, and genuinely interested in public policy.
£33,000 - £38,000 | London (80 Strand) | 4 days in office
Applications reviewed on a rolling basis:
👉 britishprogress.org/opportun…
OutofAi retweeted
Now with optional audio-driven driven and/or lipsync controlled motion on the same HF Space, for anyone interested to try it out
The LTX-2 release (from 2 days ago) is the VEO/Sora moment for open source video generation 😍
- First open model with synchronized audio+video in one pass
- 19B params, runs on consumer GPUs (~24GB+)
- Lip-synced dialogue, ambient sound, music
- Native 4K at 50 FPS, up to 20 sec
⬇️ Try the demo on Hugging Face (it's super fast)
OutofAi retweeted
The data is pretty clear: high-skilled immigration drives innovation & growth
OutofAi retweeted
Agree with @matthewclifford - the UK can and should be rich again.
The next decade’s growth will come from a handful of tech companies being built today.
Our choice is simple... capture the value from our world-class universities and startup ecosystem - or watch every great British tech company end up foreign-owned, operated, and listed.
We have the talent and the capital. What’s missing is the policy and ambition.
"Whatever you care about, whatever your vision for this country, it will be much easier to achieve it if we make the UK rich again."
@matthewclifford at LFG: Make or Break 🚀
OutofAi retweeted
We need to restore Parliament into being a decision-making body that is focused on governing our country.
A clip from our latest LFG podcast with @jujulemons and @jo3hill
OutofAi retweeted
we should be way more excited about Ovi 🔥
> open source, apache 2.0 license
> text/image-to-video + audio generation
> based on Wan2.2 5B
> great latency <> quality balance
Thermal Infrared in Robotics.....................!! exciting! 🤔
Exploring beyond RGB? Join us at ICRA 2025 for an exciting workshop on Thermal Infrared in Robotics (TIRO)! 🔥🤖 Share your latest thermal imaging projects in robotics or take part in our competition.
🔥 Workshop webpage
sites.google.com/view/tiro25…
OutofAi retweeted
Imitation Learning meets limitation learning 🤔
In student-teacher #ReinforcementLearning, the student may fail to imitate the teacher if the teacher’s behavior isn’t inferable from the student’s partial observability🤖. Our #ICLR2025 paper tackles this by training the teacher to adapt to the student’s limitations. Links ⬇️
One of the most interesting paper that I read recently was arxiv.org/abs/2403.16990 Investigating two common issues with diffusion model image sampling, which the paper tackles by an training free approach, optimisation or guiding latents in the process of generation (1/3)
The first one being the cross-attention leakage, resulting similar subjects to shares traits that doesn't inherently belong to them (2/3)
and the aspect of self-attention leakage which similar to the cross attention one but on a semantic level, which both issues are tackled through masking the subjects on attention layers and calculating the relevant loss, to increase the attention of individual items on their own subjects during generation (3/3)
Thanks @TheAIAdvantage for the great review 🥲 you can watch the full clip on YouTube
YT Link: youtu.be/7FCm_KZFJug?t=887
and if you wanna try Out of Focus v1.0:
Github: github.com/OutofAi/OutofFocu…
Colab: colab.research.google.com/gi…
When the paper claims that no additional training data is required and you get excited and then you realise you need 8xA100s to train the model💔
Thanks for sharing our work🧡@_akhaliq
Out of Focus v1.0
github: github.com/OutofAi/OutofFocu…
Out of AI presents a flexible tool in Gradio to manipulate your images. This is our first version of Image modification tool through prompt manipulation by reconstruction through diffusion inversion process. We recommend running it on GPU with at least 22GB VRAM and preferabbly a A100 GPU for the best experience.
Out of Focus V1.0
Page: github.com/OutofAi/OutofFocu…
We released our first version of our photo editing tool based on @Gradio. It attends to semantic similarities of prompts. By reconstructing given image in diffusion models.
Whether you want the change the context of our product ad (🧵1/3)
And as always your support for our open source work would be appreciated so can continue our open source journey buymeacoffee.com/outofai
