hisham bedri (@ultimate_afro) header
hisham bedri (@ultimate_afro) profile picture

Technologist working on reality-capture and creative tools. Tiktok: @ultrafro2

Joined November 2015
Yo check out this volumetric video!
Here's what we do at the Reality Lab when we can't book the village people
1
5
if you don't have to change the device's clock today, you can assume it's been compromised by ASI
1
28
Some Sunday fun: trash collecting droid using lerobot.
39
hisham bedri retweeted
I used to make games in a former life with @ultimate_afro now he's working on putting agent loops inside of game engines and honestly it works pretty well
Aura is an AI agent that can make logic graphs, write and compile flawless Unreal C++, make assets, and perform any action you can in Engine. Runs on frontier models like Claude Opus 4.5. Here's 10 min showing how it works: Dropping 25 invites with $40 of usage in the reply. Let us know what you think.
8
7
1
120
22,896
hisham bedri retweeted
Aura is an AI agent that can make logic graphs, write and compile flawless Unreal C++, make assets, and perform any action you can in Engine. Runs on frontier models like Claude Opus 4.5. Here's 10 min showing how it works: Dropping 25 invites with $40 of usage in the reply. Let us know what you think.
11
8
1
48
23,687
hisham bedri retweeted
Replying to @jordannoone
8
7
3
809
16,498
hisham bedri retweeted
if the government can own 10% of Intel, I feel like a few grocery stores are fine
13
6
3
160
16,079
hisham bedri retweeted
I joined Anthropic last week! It’s obvious to me that we’re bottlenecked not by model capabilities, but by creativity and understanding. I’ll be building demos and prototypes that highlight new capabilities and share what we learn about building using these models at Anthropic. Excited to build with the best team and the best models.
84
57
7
1,491
165,646
hisham bedri retweeted
✨ New AI Interfaces powered by Interpretability I'm excited to share LatentLit, the result of my applied AI research fellowship with @GoodfireAI Mechanistic interpretability isn’t just important for AI safety, it also gives us new ways to steer and interact with LLMs.
40
54
25
565
68,433
hisham bedri retweeted
Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.
15
93
10
603
52,996
now with some head-motion
5
78
big performance improvement on selfie -> vr-avatar
60
lots of progress on selfie -> avatar
54
making progress, it looks better and runs fast now
1
49
hisham bedri retweeted
[NeurIPS '24] Generalizable and Animatable Gaussian Head Avatar Remark: Runs at 67 fps as reported and comes with code🤯 Contributions: • We propose GAGAvatar, which to our knowledge is the first generalizable 3D Gaussian head avatar framework that achieves single forward reconstruction and real-time reenactment. • To achieve this, we propose a dual-lifting method to lift Gaussians from a single image and introduce a method that uses 3DMM priors to constrain the lifting process. • We combine 3DMM priors and 3D Gaussians to accurately transfer expression information while avoiding redundant computations.
3
55
8
284
90,320
working on some real-time avatars, very cool what's possible these days
2
66
MIT ARMS EMBARGO NOW. 🇵🇸🇵🇸 (location to be posted soon) @BDSBoston @SJPtufts
2
13
1
30
4,047
Breaking: The students and workers of #MIT establish the Scientists Against Genocide Encampment on MIT’s Kresge Lawn “MIT has received OVER $11 MILLION in research funding from the Ministry of Defense of Israel since 2015…. We will NOT REST until MIT cuts research ties with the Israeli military.”
138
3,488
235
10,314
1,391,533