Intern Science

company

https://discovery-home.intern-ai.org.cn/home

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Lonepic authored a paper 29 days ago

Multi-view Vision-Prompt Fusion Network: Can 2D Pre-trained Model Boost 3D Point Cloud Data-scarce Learning?

Lonepic authored a paper 29 days ago

Intern-S2-Preview: Scientific Agentic Foundation Model

Lonepic authored a paper 29 days ago

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

View all activity

Papers

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

View all Papers

InternScience 's collections 6

Agents-A1

Agents-A1 is a Long-horizon Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon.

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Paper • 2606.30616 • Published Jun 29 • 106
InternScience/Agents-A1

Text Generation • 35B • Updated Jul 15 • 44.3k • 640
InternScience/Agents-A1-FP8

Text Generation • 35B • Updated Jul 15 • 584 • 23
InternScience/Agents-A1-Q4_K_M-GGUF

Text Generation • 35B • Updated Jul 15 • 5.76k • 146

ResearchClawBench

ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

Paper • 2606.07591 • Published May 28 • 105
InternScience/ResearchClawBench

Benchmark • Updated Jul 28 • 57 • 27k • 16
Running

7

ResearchHarness

🚀

7

Lightweight harness for tool-using LLM agents.
Running

Agents

1

ResearchClawBench Task Submission

📦

1

Submit and validate a ResearchClawBench task ZIP

SciEval-Bench

Paused

Agents

4

SciEval Leaderboard

🥇

4

Open, science-focus leaderboards benchmarking LLMs and VLMs
InternScience/SciEval

Preview • Updated Dec 4, 2025 • 97 • 1
SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence

Paper • 2512.22334 • Published Dec 26, 2025 • 38

InternAgent

InternAgent aims to facilitate AI+X innovative research across diverse scientific domains

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

Paper • 2602.08990 • Published Feb 9 • 85
BoZhang/OmniCaptioner

8B • Updated Apr 10, 2025 • 70 • 20
InternScience/StructTable-base

Image-to-Text • 0.3B • Updated Dec 6, 2025 • 116 • 13
InternScience/MME-Reasoning

Preview • Updated Jun 13, 2025 • 274 • 12

SGI-Bench

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Running

Agents

9

SGI-Bench Leaderboard

🥇

9

Scientific General Intelligence of LLMs/vLLMs
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Paper • 2512.16969 • Published Dec 18, 2025 • 122
InternScience/SGI-DeepResearch

Viewer • Updated Jun 2 • 318 • 119 • 11
InternScience/SGI-IdeaGeneration

Viewer • Updated Jun 2 • 315 • 68 • 4

SFE

Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning

Paper • 2506.10521 • Published Jun 12, 2025 • 75
InternScience/SFE

Viewer • Updated Dec 24, 2025 • 1.66k • 3.29k • 19
InternScience/SFE-train

Preview • Updated Oct 10, 2025 • 674 • 1

Agents-A1

Agents-A1 is a Long-horizon Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon.

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Paper • 2606.30616 • Published Jun 29 • 106
InternScience/Agents-A1

Text Generation • 35B • Updated Jul 15 • 44.3k • 640
InternScience/Agents-A1-FP8

Text Generation • 35B • Updated Jul 15 • 584 • 23
InternScience/Agents-A1-Q4_K_M-GGUF

Text Generation • 35B • Updated Jul 15 • 5.76k • 146

InternAgent

InternAgent aims to facilitate AI+X innovative research across diverse scientific domains

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

Paper • 2602.08990 • Published Feb 9 • 85
BoZhang/OmniCaptioner

8B • Updated Apr 10, 2025 • 70 • 20
InternScience/StructTable-base

Image-to-Text • 0.3B • Updated Dec 6, 2025 • 116 • 13
InternScience/MME-Reasoning

Preview • Updated Jun 13, 2025 • 274 • 12

ResearchClawBench

ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

Paper • 2606.07591 • Published May 28 • 105
InternScience/ResearchClawBench

Benchmark • Updated Jul 28 • 57 • 27k • 16
Running

7

ResearchHarness

🚀

7

Lightweight harness for tool-using LLM agents.
Running

Agents

1

ResearchClawBench Task Submission

📦

1

Submit and validate a ResearchClawBench task ZIP

SGI-Bench

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Running

Agents

9

SGI-Bench Leaderboard

🥇

9

Scientific General Intelligence of LLMs/vLLMs
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Paper • 2512.16969 • Published Dec 18, 2025 • 122
InternScience/SGI-DeepResearch

Viewer • Updated Jun 2 • 318 • 119 • 11
InternScience/SGI-IdeaGeneration

Viewer • Updated Jun 2 • 315 • 68 • 4

SciEval-Bench

Paused

Agents

4

SciEval Leaderboard

🥇

4

Open, science-focus leaderboards benchmarking LLMs and VLMs
InternScience/SciEval

Preview • Updated Dec 4, 2025 • 97 • 1
SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence

Paper • 2512.22334 • Published Dec 26, 2025 • 38

SFE

Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning

Paper • 2506.10521 • Published Jun 12, 2025 • 75
InternScience/SFE

Viewer • Updated Dec 24, 2025 • 1.66k • 3.29k • 19
InternScience/SFE-train

Preview • Updated Oct 10, 2025 • 674 • 1

AI & ML interests

Recent Activity

Papers

Team members 11

InternScience 's collections 6

ResearchHarness

ResearchClawBench Task Submission

SciEval Leaderboard

SGI-Bench Leaderboard

ResearchHarness

ResearchClawBench Task Submission

SGI-Bench Leaderboard

SciEval Leaderboard