Daniil Tiapkin's picture

Daniil Tiapkin

dtiapkin

·

https://d-tiapkin.github.io/

AI & ML interests

Reinforcement learning enjoyer

Recent Activity

upvoted a paper about 5 hours ago

Unsupervised Process Reward Models

published a model 3 months ago

dtiapkin/gemma3-4b-sft

updated a model 4 months ago

dtiapkin/gemma3-4b-sft

View all activity

Organizations

None yet

Papers 4

arxiv:2505.19731

arxiv:2502.02671

arxiv:2310.17303

arxiv:2303.08059

models 2

dtiapkin/gemma3-4b-sft

Image-Text-to-Text • 4B • Updated Jan 15 • 4

dtiapkin/gemma3-1b-sft

Text Generation • 1.0B • Updated Jan 15 • 5

datasets 1

dtiapkin/prompt-collection-rlhflow

Viewer • Updated Jan 12 • 84.4k • 42