keivan alizadeh
k1al
AI & ML interests
LLM efficiency
Recent Activity
upvoted
a
paper
about 2 months ago
Enhancing LLM Reasoning via Critique Models with Test-Time and
Training-Time Supervision
upvoted
a
paper
3 months ago
SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF
upvoted
a
paper
3 months ago
Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse
Autoencoders
Organizations
None yet
k1al's activity
finetuning 2B model taking more gpu than 7B parameter model
6
#25 opened about 1 year ago
by
deleted