MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization
Paper • 2605.10784 • Published • 1
Rohan Surana
rohan2810
AI & ML interests
None yet
Recent Activity
authored a paper 4 days ago
MusiCRS: Benchmarking Audio-Centric Conversational Recommendation authored a paper 4 days ago
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning authored a paper 4 days ago
F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and RankingOrganizations
None yet
upvoted a paper 7 days ago