AI & ML interests
AGI, Nex
Recent Activity
Papers
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
Organization Card
Nex-AGI是由上海创智学院发起的创新联盟，旨在建设一个可持续的能动性闭环开源生态
Nex-AGI, an innovation alliance initiated by the Shanghai Innovation Institute, aims to build a sustainable, agency-driven, closed-loop, open-source ecosystem.
-
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
Paper • 2512.04987 • Published • 80 -
nex-agi/DeepSeek-V3.1-Nex-N1
Text Generation • 671B • Updated • 130 • 41 -
nex-agi/Qwen3-32B-Nex-N1
Text Generation • 33B • Updated • 64 • 14 -
nex-agi/Qwen3-30B-A3B-Nex-N1
31B • Updated • 28 • 15
-
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
Paper • 2512.04987 • Published • 80 -
nex-agi/DeepSeek-V3.1-Nex-N1
Text Generation • 671B • Updated • 130 • 41 -
nex-agi/Qwen3-32B-Nex-N1
Text Generation • 33B • Updated • 64 • 14 -
nex-agi/Qwen3-30B-A3B-Nex-N1
31B • Updated • 28 • 15
models
7
nex-agi/DeepSeek-V3.1-Nex-N1.1
683B
•
Updated
•
1
nex-agi/SGLANG-EAGLE3-Qwen3-30B-A3B-Nex-N1
0.2B
•
Updated
•
12
•
2
nex-agi/SGLANG-EAGLE3-Qwen3-32B-Nex-N1
0.8B
•
Updated
•
96
•
3
nex-agi/internlm3-8B-Nex-N1
Text Generation
•
9B
•
Updated
•
3
•
13
nex-agi/DeepSeek-V3.1-Nex-N1
Text Generation
•
671B
•
Updated
•
130
•
41
nex-agi/Qwen3-32B-Nex-N1
Text Generation
•
33B
•
Updated
•
64
•
14
nex-agi/Qwen3-30B-A3B-Nex-N1
31B
•
Updated
•
28
•
15