arxiv:2605.00347
Chengshuai Shi
shichengshuai98
·
AI & ML interests
None yet
Recent Activity
authored a paper 3 days ago
Building Math Agents with Multi-Turn Iterative Preference Learning authored a paper 3 days ago
Provably Efficient Offline Reinforcement Learning with Perturbed Data
Sources authored a paper 3 days ago
Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement LearningOrganizations
models 9
shichengshuai98/gemma2_2b_it_0107_morning_gsm8k_0105_all_merged
Text Generation • 3B • Updated • 2 •
shichengshuai98/gemma2_2b_it_0106_evening_gsm8k_0105_all_merged
Text Generation • 3B • Updated • 1 •
shichengshuai98/gemma2_2b_it_0107_morning_gsm8k_0105_all
Updated
shichengshuai98/gemma2_2b_it_0106_evening_gsm8k_0105_all
Updated
shichengshuai98/gemma2_2b_it_0106_morning_gsm8k_0105_all_merged
Text Generation • 3B • Updated • 2
shichengshuai98/gemma2_2b_it_0106_morning_gsm8k_0105_all
Updated
shichengshuai98/gemma2_2b_it_0106_afternoon_gsm8k_0105_all
Updated
shichengshuai98/zephyr-7b-dpo-qlora
Updated • 6
shichengshuai98/zephyr-7b-sft-qlora
Updated • 8