Roman Garipov's picture

Roman Garipov

garipovroma

·

https://garipovroma.github.io

AI & ML interests

ML & DL

Recent Activity

upvoted a paper 14 days ago

Rethinking Global Text Conditioning in Diffusion Transformers

upvoted a paper 23 days ago

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation

upvoted a paper 4 months ago

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

View all activity

Organizations

Papers 1

arxiv:2504.06261

models 3

garipovroma/DeepSeek-R1-Distill-Qwen-1.5B-GRPO

Text Generation • 2B • Updated Jul 5, 2025 • 3

garipovroma/my_DeepSeek-R1-Distill-Qwen-1.5B-GRPO

Updated Jun 19, 2025

garipovroma/gpt_2_shakespeare_finetuned

Text Generation • Updated Nov 14, 2023 • 2

datasets 0

None public yet