TOBI-X/XGLM-finetune-real
Text Generation
•
Updated
•
1
ZHOU
TOBI-X
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
27 days ago
Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence
Reweighting
upvoted
a
paper
27 days ago
Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense
Organizations
None yet
datasets
0
None public yet