Jingzhi Wang

jzwang666

5 1

·

JingzhiWang111

AI & ML interests

LLM pretrain & finetuning, develop high effiency attention architecture, agentic RL system

Recent Activity

upvoted a paper 22 days ago

NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction

authored a paper about 2 months ago

MemSFT: Mitigating Alignment Tax with an External Parametric Memory

authored a paper about 2 months ago

JTok: On Token Embedding as another Axis of Scaling Law via Joint Token Self-modulation

View all activity

Organizations

upvoted a paper 22 days ago

NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction

Paper • 2609.10715 • Published 24 days ago • 331

upvoted a paper about 2 months ago

MemSFT: Mitigating Alignment Tax with an External Parametric Memory

Paper • 2607.25614 • Published Jul 28 • 23

upvoted 2 papers 2 months ago

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Paper • 2607.28568 • Published Jul 30 • 188

Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory

Paper • 2607.27919 • Published Jul 30 • 62

upvoted a paper 3 months ago

Information-Aware KV Cache Compression for Long Reasoning

Paper • 2606.26875 • Published Jun 25 • 12