Merging in a Bottle: Differentiable Adaptive Merging (DAM) and the Path from Averaging to Automation
Paper
•
2410.08371
•
Published
•
3
Malikeh Ehghaghi
Malikeh1375
AI & ML interests
NLP, Modular ML, Model Merging, Decentralized Training, Efficient LLMs
Recent Activity
authored
a paper
about 10 hours ago
Merging in a Bottle: Differentiable Adaptive Merging (DAM) and the Path
from Averaging to Automation
authored
a paper
about 10 hours ago
DEPAC: a Corpus for Depression and Anxiety Detection from Speech
authored
a paper
about 10 hours ago
TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior
Organizations
authored
3
papers
about 10 hours ago
submitted
a
paper
to Daily Papers
1 day ago
authored
a
paper
almost 2 years ago