arXiv:2510.26658
Li Dong
unilm
AI & ML interests
Language Model Pre-Training
Recent Activity
authored
a paper
8 days ago
Benefits and Pitfalls of Reinforcement Learning for Language Model
Planning: A Theoretical Perspective
authored
a paper
8 days ago
DocReward: A Document Reward Model for Structuring and Stylizing
authored
a paper
8 days ago
Information-Preserving Reformulation of Reasoning Traces for
Antidistillation
Organizations
models
0
None public yet
datasets
0
None public yet