@jm_alexia
Alexia Jolicoeur-Martineau
@jm_alexia
1 year
Diffusion models have become overcrowded and more focused on scaling/engineering than algorithms. I'm slowly weaning off from diffusion models, just like I did with GANs. I'm now exploring small subareas of AI that have great potential. I will have cool stuff to show in Spring.
8
12
303

Replies

@HRKeshavarz
Hamidreza Keshavarz
@HRKeshavarz
1 year
@jm_alexia I think one area will be on-device model training.
0
0
1
@Sim_Startup_
Sim
@Sim_Startup_
1 year
@jm_alexia Could you give an example?
0
0
1
@ereb0s_labs
ereb0s
@ereb0s_labs
1 year
@jm_alexia Gradient-Aligned Generative Energy Models🤭
0
1
5
@p_bartet
Pierre Bartet
@p_bartet
1 year
@jm_alexia Do you mean diffusion models themselves or generative models in general?
0
0
0
@rosikand
~/rohan
@rosikand
1 year
@jm_alexia Diffusion models (and LLMs) have brought new challenges in systems and infra never seen before in ML which, imo, is partly why it’s so interesting. The algorithms themselves are only part of the story here… unlike GANs.
0
0
4
@artistexyz
www.ar-tiste.xyz
@artistexyz
1 year
@jm_alexia Two words young lady: causal inference
0
0
0
@johnboithefifth
johnboithefifth
@johnboithefifth
1 year
@jm_alexia What else man
0
0
0