GD^2PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization
Paper • 2606.16771 • Published • 13
Liu
happyfighting
·
AI & ML interests
None yet
Recent Activity
updated a model 9 months ago
happyfighting/Qwen2.5-3B-Instruct-kklogic_grpo_baseline_53_gpg_sig_r_js2_kl_false published a model 9 months ago
happyfighting/Qwen2.5-3B-Instruct-kklogic_grpo_baseline_53_gpg_sig_r_js2_kl_falseOrganizations
upvoted a paper 29 days ago