Zhenyi Shen's picture

Zhenyi Shen

zen-E

·

https://www.zhenyishen.com/

AI & ML interests

LLM Reasoning

Recent Activity

upvoted a paper 6 days ago

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

upvoted a paper 6 days ago

NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning

upvoted a paper 9 days ago

SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space

View all activity

Organizations

None yet

Papers 2

arxiv:2511.20102

arxiv:2502.21074

models 12

zen-E/llama1be4mask0p4

1B • Updated Sep 11

zen-E/llama3be2mask0p4

zen-E/CODI-llama3.2-1b-Instruct

zen-E/CODI-gpt2

zen-E/bert-mini-sentence-distil-unsupervised-pca

Updated Oct 3, 2023

zen-E/bert-mini-sentence-distil-supervised

Feature Extraction • Updated Oct 3, 2023 • 11

zen-E/bert-mini-sentence-distil-unsupervised

Feature Extraction • Updated Oct 3, 2023 • 18

zen-E/q-Taxi-v3-v1

Reinforcement Learning • Updated Jul 15, 2023

zen-E/q-FrozenLake-v1-4x4-noSlippery

Reinforcement Learning • Updated Jul 14, 2023

zen-E/deepspeed-chat-step2-model-opt350m

Text Generation • Updated Apr 27, 2023 • 21 • 1

datasets 7

zen-E/StrategyQA_CoT_GPT4o

Viewer • Updated May 10 • 2.04k • 114 • 1

zen-E/StrategyQA_GPT4o_CoTx10

Viewer • Updated May 7 • 17k • 15

zen-E/CommonsenseQA-GPT4omini

Viewer • Updated May 6 • 9.42k • 1.72k

zen-E/GSM8k-Aug

Viewer • Updated Apr 16 • 387k • 2.99k • 2

zen-E/GSM8k-Aug-NL

Viewer • Updated Apr 13 • 385k • 854 • 1

zen-E/NEWS5M-simcse-roberta-large-embeddings-pca-256

Updated Oct 3, 2023 • 23

zen-E/ANLI-simcse-roberta-large-embeddings-pca-256

Updated Oct 3, 2023 • 35