# Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

arXiv: https://arxiv.org/abs/2603.25040 · HTML: https://mlsanity.com/paper/2603.25040/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 49 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 30 of 33)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models](https://mlsanity.com/paper/2407.11691/) (2024)
- [OS-ATLAS: A Foundation Action Model for Generalist GUI Agents](https://mlsanity.com/paper/2410.23218/) (2024)
- [Generalizing Verifiable Instruction Following](https://mlsanity.com/paper/2507.02833/) (2025)
- [OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning](https://mlsanity.com/paper/2501.00321/) (2024)
- [Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models](https://mlsanity.com/paper/2306.08018/) (2023)
- [LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset](https://mlsanity.com/paper/2402.09391/) (2024)
- [MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing](https://mlsanity.com/paper/2509.22186/) (2025)
- [Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark](https://mlsanity.com/paper/2202.06767/) (2022)
- [Scientific Large Language Models: A Survey on Biological & Chemical Domains](https://mlsanity.com/paper/2401.14656/) (2024)
- [Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers](https://mlsanity.com/paper/2510.11370/) (2025)
- [Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model](https://mlsanity.com/paper/2510.18855/) (2025)
- [XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?](https://mlsanity.com/paper/2503.23771/) (2025)
- [Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization](https://mlsanity.com/paper/2412.17739/) (2024)
- [CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning](https://mlsanity.com/paper/2509.22647/) (2025)
- [Sparse Backpropagation for MoE Training](https://mlsanity.com/paper/2310.00811/) (2023)
- [GRIN: GRadient-INformed MoE](https://mlsanity.com/paper/2409.12136/) (2024)

## Built on by (most cited first, 29 of 29)

- [Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMs](https://mlsanity.com/paper/2605.02735/) (2026)
- [A Definition and Roadmap for World Models](https://mlsanity.com/paper/2607.06401/) (2026)
- [Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions](https://mlsanity.com/paper/2607.20891/) (2026)
- [Intern-S2-Preview: Scientific Agentic Foundation Model](https://mlsanity.com/paper/2608.13505/) (2026)
- [DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding](https://mlsanity.com/paper/2605.08888/) (2026)
- [Scaling Scientific Discovery Environments for Turn-Level Agentic RL](https://mlsanity.com/paper/2607.28990/) (2026)
- [SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification](https://mlsanity.com/paper/2606.04579/) (2026)
- [Knowing the Self, Understanding the World: A Dual-Cognition Benchmark for UAV Spatio-temporal Reasoning with MLLMs](https://mlsanity.com/paper/2607.16193/) (2026)
- [OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models](https://mlsanity.com/paper/2607.28609/) (2026)
- [A systematic evaluation of vision-language models for observational astronomical reasoning tasks](https://mlsanity.com/paper/2604.24589/) (2026)
- [ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning](https://mlsanity.com/paper/2606.03503/) (2026)
- [BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language](https://mlsanity.com/paper/2606.22138/) (2026)
- [SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring](https://mlsanity.com/paper/2607.18665/) (2026)
- [ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?](https://mlsanity.com/paper/2607.20868/) (2026)
- [COHERENCE: Benchmarking Fine-Grained Image-Text Alignment in Interleaved Multimodal Contexts](https://mlsanity.com/paper/2604.27389/) (2026)
- [LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretation](https://mlsanity.com/paper/2605.07640/) (2026)
- [ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning](https://mlsanity.com/paper/2605.18799/) (2026)
- [OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science Subfields](https://mlsanity.com/paper/2605.29833/) (2026)
- [Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games](https://mlsanity.com/paper/2606.19338/) (2026)
- [AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification](https://mlsanity.com/paper/2607.11849/) (2026)
- [Monkey King Bang: A Unified Scientific Multimodal Foundation Model](https://mlsanity.com/paper/2607.20557/) (2026)
- [Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations](https://mlsanity.com/paper/2608.00711/) (2026)
- [Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning](https://mlsanity.com/paper/2608.14290/) (2026)
- [SinoGlyphBench: A Diagnostic Benchmark for Chinese Glyph-Level Obfuscation in Language-Model Moderation](https://mlsanity.com/paper/2609.05843/) (2026)
- [PhyMo: A Physical-Field Modality for Multimodal AI4Physics](https://mlsanity.com/paper/2609.27554/) (2026)
- [IndustryLLM: Failure-Driven LLM Training for Industrial Procurement](https://mlsanity.com/paper/2609.31871/) (2026)
- [EyeVQA: Benchmarking Ophthalmic Vision-Language Models from Recognition to Spatial Grounding](https://mlsanity.com/paper/2609.32352/) (2026)
- [PhysFieldBench: Can Multimodal Models Understand Physical Fields?](https://mlsanity.com/paper/2609.34072/) (2026)
- [RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology](https://mlsanity.com/paper/2610.02242/) (2026)

## Abstract (arXiv)

We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancement across both general and scientific domains. Beyond stronger reasoning and image-text understanding capabilities, its intelligence is augmented with advanced agent capabilities. Simultaneously, its scientific expertise has been vastly expanded to master over 100 specialized tasks across critical science fields, including chemistry, materials, life sciences, and earth sciences. Achieving this massive scale is made possible by the robust infrastructure support of XTuner and LMDeploy, which facilitates highly efficient Reinforcement Learning (RL) training at the 1-trillion parameter level while ensuring strict precision consistency between training and inference. By seamlessly integrating these advancements, Intern-S1-Pro further fortifies the fusion of general and specialized intelligence, working as a Specializable Generalist, demonstrating its position in the top tier of open-source models for general capabilities, while outperforming proprietary models in the depth of specialized scientific tasks.