-
DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization
Paper • 2508.14460 • Published • 80 -
MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement
Paper • 2508.09670 • Published -
URPO: A Unified Reward & Policy Optimization Framework for Large Language Models
Paper • 2507.17515 • Published • 1
Emmanuel Sugut
Sugutt
·
AI & ML interests
Reinforcement learning
Transformer models
Recent Activity
updated
a model
11 days ago
Sugutt/whisper-kalenjin-large
published
a model
13 days ago
Sugutt/whisper-kalenjin-large
updated
a collection
17 days ago
RL
Organizations
