Dhruv Pendharkar

drvp

·

AI & ML interests

RL, Computer Vision, and Meta Learning

Recent Activity

updated a dataset 2 days ago

drvp/modified_rl_with_reasoning_arbiter

published a dataset 2 days ago

drvp/modified_rl_with_reasoning_arbiter

updated a model 3 days ago

drvp/web-wmrm-best_wm-warm-start

View all activity

Organizations

None yet

models 9

drvp/web-wmrm-best_wm-warm-start

Updated 3 days ago • 137

drvp/wm-eval-logs

drvp/chuyi-sft-baseline

drvp/web_arbiter_wm_rl_data

drvp/web-wmrm-ep2-warm-start

Updated May 23 • 3

drvp/world_model

Text Generation • Updated May 6 • 2

drvp/reward_data

drvp/visual_reasoning_stage_1

Updated Apr 27 • 2

drvp/web_world_sft

4B • Updated Apr 24 • 2

datasets 3

drvp/modified_rl_with_reasoning_arbiter

Viewer • Updated 2 days ago • 18.9k • 15

drvp/bestwm_webarbiter_data

Preview • Updated 16 days ago • 123

drvp/world_model_eval

Viewer • Updated May 19 • 875 • 12