Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
Optimising computation at the token-level
This is the rendered collections of notes by me, Lex Toumbourou.
You can find the source on the GitHub project.
The notes are collecting using my interpretation of the Zettelkasten method.
More
You can find the source on the GitHub project.
The notes are collecting using my interpretation of the Zettelkasten method.
More
-
-
Absurdly Good Doggo Consistency with FLUX.1 Kontext
Experiments with multi-turn character consistent editing
-
-
-
Imagen 4 is faster, but GPT is still the GOAT
a few comparisons of Google's Imagen 4 vs OpenAI's gpt-image-1
-
-
NoProp: Training Neural Networks Without Back-Propagation or Forward-Propagation
an alternative training method to backprop that does local layer learning
-
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
learn to reason without any human-annotated data.
-
Playing Atari with Deep Reinforcement Learning
a classic paper applying neural networks to RL for game playing
-
