Li Dong's picture

Li Dong

unilm

·

AI & ML interests

Language Model Pre-Training

Recent Activity

upvoted a paper 7 days ago

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs

upvoted a paper 14 days ago

SeerAttention-R: Sparse Attention Adaptation for Long Reasoning

authored a paper 16 days ago

Think Only When You Need with Large Hybrid-Reasoning Models

View all activity

Organizations

Papers 64

arxiv:2506.08007

arxiv:2506.04108

arxiv:2505.23585

arxiv:2505.14674

spaces 1

Promptist

models 0

None public yet

datasets 0

None public yet