Richard Lian's picture

Richard Lian PRO

richardlian

·

dachenlian

AI & ML interests

None yet

Recent Activity

upvoted an article 1 day ago

KV Cache from scratch in nanoVLM

upvoted a paper 3 days ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

updated a Space 16 days ago

richardlian/gradio-demo

View all activity

Organizations

spaces 1

gradio-demo

models 3

richardlian/taxi-v3

Reinforcement Learning • Updated Jul 27, 2024

richardlian/q-FrozenLake-v1-4x4-noSlippery

Reinforcement Learning • Updated Jul 27, 2024

richardlian/ppo-LunarLander-v2

Reinforcement Learning • Updated Jul 25, 2024 • 1

datasets 0

None public yet