Joseph Bradley
@josephcbradley.bsky.social
Science and Tech at TBI. Former PGR Student @ King's College London. Econophysics, Complex Networks, Fractals. All views my own.
TBI's newest report is great. Lots of recommendations on:
- compute
- talent
- data access
- funding
Full report below:
- compute
- talent
- data access
- funding
Full report below:
February 19, 2025 at 1:51 PM
TBI's newest report is great. Lots of recommendations on:
- compute
- talent
- data access
- funding
Full report below:
- compute
- talent
- data access
- funding
Full report below:
Reposted by Joseph Bradley
impeachment speedrun any%
December 3, 2024 at 4:26 PM
impeachment speedrun any%
Yesterday saw two great papers from @tonelangengen.bsky.social, @jeegarkakkad.bsky.social, and Ben from TBI on nuclear power
December 3, 2024 at 11:26 AM
Yesterday saw two great papers from @tonelangengen.bsky.social, @jeegarkakkad.bsky.social, and Ben from TBI on nuclear power
Reposted by Joseph Bradley
TLDR for me/others: Diffusion model to predict image at new time and camera loc given image at diff time and diff camera loc.
Trained on synthetic data with all of required data, augmented with real vids with diff time but static camera and static time but diff camera angles. Impressive!
Trained on synthetic data with all of required data, augmented with real vids with diff time but static camera and static time but diff camera angles. Impressive!
Stop watching videos, start interacting with worlds.
Stoked to share CAT4D, our new method for turning videos into dynamic 3D scenes that you can move through in real-time!
cat-4d.github.io
arxiv.org/abs/2411.18613
Stoked to share CAT4D, our new method for turning videos into dynamic 3D scenes that you can move through in real-time!
cat-4d.github.io
arxiv.org/abs/2411.18613
November 29, 2024 at 2:12 AM
TLDR for me/others: Diffusion model to predict image at new time and camera loc given image at diff time and diff camera loc.
Trained on synthetic data with all of required data, augmented with real vids with diff time but static camera and static time but diff camera angles. Impressive!
Trained on synthetic data with all of required data, augmented with real vids with diff time but static camera and static time but diff camera angles. Impressive!
Had a great day with Trillium tech talking all things space and AI. A few thoughts ☁️
November 28, 2024 at 6:18 PM
Had a great day with Trillium tech talking all things space and AI. A few thoughts ☁️