arxiv:2504.15477
Rohan Surana
rohan2810
AI & ML interests
None yet
Recent Activity
upvoted a paper about 7 hours ago
MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization submitted a paper 1 day ago
F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and RankingOrganizations
None yet
models 32
rohan2810/movielens_heissen_theta_normalized_massdpo_theta_normalized_llama-3.2-3b-instruct_0.1_3_lastlaye
Updated
rohan2810/debug-lastlayer-theta3-rerun-20260328-001108
Updated
rohan2810/debug-lastlayer-theta3-rerun-20260327-204700
Updated
rohan2810/debug-lastlayer-theta3-foreground-20260327-140219
Updated
rohan2810/movielens-llama-3.2-3b-instruct-sdpo-all-neg19-20260326-021023
Updated
rohan2810/movielens-llama-3.2-3b-instruct-massdpo-theta-neg10-20260326-053614
Updated
rohan2810/movielens-llama-massdpo-theta-neg3-20260325-145401
Updated
rohan2810/movielens-llama-3.2-3b-instruct-massdpo-theta-neg10-20260326-021023
Updated
rohan2810/movielens-llama-3.2-3b-instruct-sdpo-all-neg19-20260326-020522
Updated
rohan2810/movielens-llama-3.2-3b-instruct-sdpo-all-neg19-20260326-020357
Updated
datasets 21
rohan2810/hotpotqa20
Viewer • Updated • 23.1k • 5
rohan2810/ambigqa_ice
Viewer • Updated • 6.08k • 3
rohan2810/hotpotqa_ice_old
Viewer • Updated • 23.1k • 38
rohan2810/MusiCRS
Viewer • Updated • 477 • 69 • 5
rohan2810/movielens50
Viewer • Updated • 90.6k • 113
rohan2810/movielens30
Viewer • Updated • 90.6k • 6
rohan2810/movielens
Viewer • Updated • 90.6k • 50
rohan2810/qasc
Viewer • Updated • 9.06k • 12
rohan2810/nectar
Viewer • Updated • 62.5k • 2
rohan2810/musique
Viewer • Updated • 22.4k • 82