liyaxuan's picture

8 1

liyaxuan

lllyx

·

AI & ML interests

None yet

Recent Activity

liked a model 5 days ago

openbmb/MiniCPM-o-4_5

upvoted a paper 7 days ago

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

upvoted a paper 20 days ago

Your Group-Relative Advantage Is Biased

View all activity

Organizations

None yet

upvoted a paper 7 days ago

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published 10 days ago • 89

upvoted a paper 20 days ago

Your Group-Relative Advantage Is Biased

Paper • 2601.08521 • Published 27 days ago • 150

upvoted an article 28 days ago

Article

Re-understanding KL Approximation from an RL-for-LLM Lens: Notes on “Approximating KL Divergence”

Aug 11, 2025

•

7

upvoted a paper about 1 month ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Paper • 2601.05242 • Published Jan 8 • 222

upvoted a paper about 2 months ago

Pre-training Distillation for Large Language Models: A Design Space Exploration

Paper • 2410.16215 • Published Oct 21, 2024 • 17

upvoted a paper 4 months ago

A Survey of Reinforcement Learning for Large Reasoning Models

Paper • 2509.08827 • Published Sep 10, 2025 • 190

upvoted a collection 4 months ago

DeepPrune

Parallel Scaling without Inter-trace Redundancy • 3 items • Updated Oct 10, 2025 • 2

upvoted a paper 4 months ago

DeepPrune: Parallel Scaling without Inter-trace Redundancy

Paper • 2510.08483 • Published Oct 9, 2025 • 24