Papers:
0:30 – Bifurcations and loss jumps in RNN training
8:40 – LEDITS++: Limitless Image Editing using Text-to-Image Models
13:50 – Lexinvariant Language Models
19:15 – Transformers learn to implement preconditioned gradient descent for in-context learning
23:25 – Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
30:40 – GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization
37:00 – Hardware Resilience Properties of Text-Guided Image Classifiers
Links:
Homepage:
Merch:
YouTube:
Twitter:
Discord:
LinkedIn:
If you want to support me, the best thing to do is to share out the content 🙂
If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this):
SubscribeStar:
Patreon:
Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq
Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2
Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m
Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n
source
