Hangliang Ding's picture

4 10 2

Hangliang Ding

foreverpiano

·

foreverpiano

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders

upvoted an article about 1 month ago

Proximal Policy Optimization (PPO)

upvoted a paper about 2 months ago

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

View all activity

Organizations

None yet

Papers 2

arxiv:2502.06155

arxiv:2502.04507

models 1

foreverpiano/mochi

Updated Oct 27, 2024 • 1

datasets 0

None public yet