arxiv:2503.00897
Shashank Gupta
shashankg7
AI & ML interests
Off-policy learning, RLHF, Multimodal models
Recent Activity
authored
a paper
13 days ago
A Simple and Effective Reinforcement Learning Method for Text-to-Image
Diffusion Fine-tuning
updated
a model
4 months ago
shashankg7/color_PPO_baseline_42
updated
a model
4 months ago
shashankg7/RLOO_aesthetic_PPO_k_4_16
Organizations
None yet
Papers
1
models
48
shashankg7/color_PPO_baseline_42
Text-to-Image
•
Updated
shashankg7/RLOO_aesthetic_PPO_k_4_16
Text-to-Image
•
Updated
shashankg7/RLOO_aesthetic_PPO_k_3_16
Text-to-Image
•
Updated
shashankg7/RLOO_aesthetic_PPO_k_2_16
Text-to-Image
•
Updated
shashankg7/RLOO_aesthetic_PPO_k_4_27
Text-to-Image
•
Updated
shashankg7/RLOO_aesthetic_PPO_k_3_27
Text-to-Image
•
Updated
shashankg7/RLOO_aesthetic_PPO_k_2_27
Text-to-Image
•
Updated
shashankg7/RLOO_aesthetic_PPO_k_4_42
Text-to-Image
•
Updated
shashankg7/RLOO_aesthetic_PPO_k_3_42
Text-to-Image
•
Updated
shashankg7/RLOO_aesthetic_PPO_k_2_42
Text-to-Image
•
Updated
datasets
None public yet