mlsanityData to 7 Oct 2026

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

arXiv 2603.25040 ↗First posted 26 Mar 2026cs.LG cs.CL cs.CVcited by 25

Not on the map. Why?

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.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 33 of its 49 references that are in the map. First posted on arXiv 26 Mar 2026.

Builds on

33 of 49 references.

References · 33

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2020Scaling Laws for Neural Language Modelscited by 6,411
  3. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  4. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  5. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  6. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  7. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  8. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  9. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  10. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,209
  11. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  12. 2022Galactica: A Large Language Model for Sciencecited by 736
21 more
  1. 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 558
  2. 2024MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmarkcited by 494
  3. 2024VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Modelscited by 443
  4. 2024OS-ATLAS: A Foundation Action Model for Generalist GUI Agentscited by 370
  5. 2025Generalizing Verifiable Instruction Followingcited by 178
  6. 2024OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoningcited by 165
  7. 2023Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Modelscited by 131
  8. 2024LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Datasetcited by 124
  9. 2022Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmarkcited by 114
  10. 2025MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsingcited by 108
  11. 2024Scientific Large Language Models: A Survey on Biological & Chemical Domainscited by 80
  12. 2025Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routerscited by 67
  13. 2025XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?cited by 50
  14. 2025Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Modelcited by 50
  15. 2024Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalizationcited by 37
  16. 2025CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learningcited by 36
  17. 2023Sparse Backpropagation for MoE Trainingcited by 16
  18. 2024GRIN: GRadient-INformed MoEcited by 16
  19. 2025SciTS: Scientific Time Series Understanding and Generation with LLMscited by 13
  20. 2024Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Modelscited by 9
  21. 2025MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 25.

25 papers.

Sort:

By area:

  1. 2026Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMscited by 4
  2. 2026A Definition and Roadmap for World Modelscited by 3
  3. 2026Is Deep Research Reliable? Misleading Knowledge Induces False Conclusionscited by 3
  4. 2026Intern-S2-Preview: Scientific Agentic Foundation Modelcited by 3
  5. 2026DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understandingcited by 2
  6. 2026Scaling Scientific Discovery Environments for Turn-Level Agentic RLcited by 2
  7. 2026A systematic evaluation of vision-language models for observational astronomical reasoning taskscited by 1
  8. 2026ThoughtFold: Folding Reasoning Chains via Introspective Preference Learningcited by 1
  9. 2026SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verificationcited by 1
  10. 2026Knowing the Self, Understanding the World: A Dual-Cognition Benchmark for UAV Spatio-temporal Reasoning with MLLMscited by 1
  11. 2026ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?cited by 1
  12. 2026OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Modelscited by 1
13 more
  1. 2026LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretationcited by 0
  2. 2026ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoningcited by 0
  3. 2026OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science Subfieldscited by 0
  4. 2026Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Gamescited by 0
  5. 2026AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verificationcited by 0
  6. 2026SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoringcited by 0
  7. 2026Monkey King Bang: A Unified Scientific Multimodal Foundation Modelcited by 0
  8. 2026Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinationscited by 0
  9. 2026Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoningcited by 0
  10. 2026SinoGlyphBench: A Diagnostic Benchmark for Chinese Glyph-Level Obfuscation in Language-Model Moderationcited by 0
  11. 2026PhyMo: A Physical-Field Modality for Multimodal AI4Physicscited by 0
  12. 2026EyeVQA: Benchmarking Ophthalmic Vision-Language Models from Recognition to Spatial Groundingcited by 0
  13. 2026PhysFieldBench: Can Multimodal Models Understand Physical Fields?cited by 0