ZHENG JINGNAN

Nannanzi's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 6 days ago

Safin-1: Safety from Within through Memory-Native State Evolution

Paper • 2609.00092 • Published Aug 31 • 22

liked a model 6 days ago

AI45Research/Safin-1.5

Text Generation • 36B • Updated 13 days ago • 298 • 6

upvoted a paper 12 days ago

Towards Architectural-Level Safety Control: Relocating Hazardous Knowledge into Removable Experts in Mixture-of-Experts Models

Paper • 2610.25791 • Published 24 days ago • 4

upvoted a collection 12 days ago

REX

Collection

Towards Architectural-Level Safety Control: Relocating Hazardous Knowledge into Removable Experts in Mixture-of-Experts Models • 7 items • Updated 23 days ago • 3

published a model 14 days ago

AI45Research/Safin-1.5

Text Generation • 36B • Updated 13 days ago • 298 • 6

updated a model 14 days ago

AI45Research/Safin-1.5

Text Generation • 36B • Updated 13 days ago • 298 • 6

upvoted a collection 20 days ago

ReSI

Collection

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI • 5 items • Updated Oct 11 • 1

authored 6 papers about 1 month ago

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI

Paper • 2610.12233 • Published Oct 8 • 30

Safin-1: Safety from Within through Memory-Native State Evolution

Paper • 2609.00092 • Published Aug 31 • 22

Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer

Paper • 2602.19058 • Published Feb 22

Transport and Merge: Cross-Architecture Merging for Large Language Models

Paper • 2602.05495 • Published Feb 5

VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions

Paper • 2605.27141 • Published May 26 • 18

RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards

Paper • 2506.07736 • Published Jun 9, 2025 • 1

updated a collection about 1 month ago

ReSI

Collection

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI • 5 items • Updated Oct 11 • 1

updated a model about 1 month ago

AI45Research/ReSI-DeepSeek-V4-Flash

Text Generation • 284B • Updated Oct 11 • 21

updated a collection about 1 month ago

ReSI

Collection

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI • 5 items • Updated Oct 11 • 1

upvoted a paper about 1 month ago

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI

Paper • 2610.12233 • Published Oct 8 • 30

published a model about 1 month ago

AI45Research/ReSI-DeepSeek-V4-Flash

Text Generation • 284B • Updated Oct 11 • 21

updated a collection about 1 month ago

ReSI

Collection

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI • 5 items • Updated Oct 11 • 1

updated a model about 1 month ago

AI45Research/ReSI-Ministral-3-14B-Reasoning

Image-Text-to-Text • 14B • Updated Oct 11 • 21