Leshem Choshen's picture

Leshem Choshen

borgr

·

https://ktilana.wixsite.com/leshem-choshen

AI & ML interests

Merging models, collaboratively improving pretraining, evaluation, understanding

Recent Activity

New activity about 12 hours ago

chuxin-llm/Scaling-Laws-for-Local-SGD-in-LLM-Intermediate-Checkpoints:Losses and checkpoints

upvoted a paper about 1 month ago

LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content

upvoted a paper about 2 months ago

SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image Classification

View all activity

Organizations

Papers 18

arxiv:2408.16961

arxiv:2408.08291

arxiv:2407.21530

arxiv:2401.14367

models

None public yet

datasets

None public yet