Intern-S1: A Scientific Multimodal Foundation Model

• URL: http://arxiv.org/abs/2508.15763v2
• Date: Sun, 24 Aug 2025 19:35:34 GMT
• Title: Intern-S1: A Scientific Multimodal Foundation Model
• Abstract summary: We introduce Intern-S1, a specialized generalist equipped with general understanding and reasoning capabilities.<n>Intern-S1 undergoes offline and then online reinforcement learning (RL) in InternBootCamp.<n>On comprehensive evaluation benchmarks, Intern-S1 demonstrates competitive performance on general reasoning tasks among open-source models.
• Score: 282.73189976071427
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, a plethora of open-source foundation models have emerged, achieving remarkable progress in some widely attended fields, with performance being quite close to that of closed-source models. However, in high-value but more challenging scientific professional fields, either the fields still rely on expert models, or the progress of general foundation models lags significantly compared to those in popular areas, far from sufficient for transforming scientific research and leaving substantial gap between open-source models and closed-source models in these scientific domains. To mitigate this gap and explore a step further toward Artificial General Intelligence (AGI), we introduce Intern-S1, a specialized generalist equipped with general understanding and reasoning capabilities with expertise to analyze multiple science modal data. Intern-S1 is a multimodal Mixture-of-Experts (MoE) model with 28 billion activated parameters and 241 billion total parameters, continually pre-trained on 5T tokens, including over 2.5T tokens from scientific domains. In the post-training stage, Intern-S1 undergoes offline and then online reinforcement learning (RL) in InternBootCamp, where we propose Mixture-of-Rewards (MoR) to synergize the RL training on more than 1000 tasks simultaneously. Through integrated innovations in algorithms, data, and training systems, Intern-S1 achieved top-tier performance in online RL training. On comprehensive evaluation benchmarks, Intern-S1 demonstrates competitive performance on general reasoning tasks among open-source models and significantly outperforms open-source models in scientific domains, surpassing closed-source state-of-the-art models in professional tasks, such as molecular synthesis planning, reaction condition prediction, predicting thermodynamic stabilities for crystals. Our models are available at https://huggingface.co/internlm/Intern-S1.

Related papers

• Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale [243.02537333434245]
  Intern-S1-Pro is the first one-trillion- parameter scientific multimodal foundation model.<n>Its scientific expertise has been vastly expanded to master over 100 specialized tasks across critical science fields.<n>XTuner and LMDeploy facilitate highly efficient Reinforcement Learning (RL) training at the 1-trillion parameter level.
  arXiv  Detail & Related papers  (2026-03-26T05:21:45Z)
• ERNIE 5.0 Technical Report [244.36480708815316]
  ERNIE 5.0 is a unified autoregressive foundation model for unified multimodal understanding and generation across text, image, video, and audio.<n>To address practical challenges in large-scale deployment under diverse resource constraints, ERNIE 5.0 adopts a novel elastic training paradigm.<n>We show that ERNIE 5.0 achieves strong and balanced performance across multiple modalities.
  arXiv  Detail & Related papers  (2026-02-04T16:18:15Z)
• Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models [71.9060068259379]
  We propose cascaded domain-wise reinforcement learning to build general-purpose reasoning models.<n>Our 14B model, after RL, outperforms its SFT teacher, DeepSeek-R1-0528, on LiveCodeBench v5/v6 Pro and silver-medal performance in the 2025 International Olympiad in Informatics (IOI)
  arXiv  Detail & Related papers  (2025-12-15T18:02:35Z)
• Towards a Physics Foundation Model [2.109902626434734]
  We present the General Physics Transformer (GPhyT), trained on 1.8 TB of diverse simulation data.<n>GPhyT achieves superior performance across multiple physics domains, outperforming specialized architectures by up to 29x.<n>By establishing that a single model can learn general physical principles from data alone, this work opens the path toward a universal Physics Foundation Model.
  arXiv  Detail & Related papers  (2025-09-17T08:19:57Z)
• Holistic Evaluation of Multimodal LLMs on Spatial Intelligence [81.2547965083228]
  We propose EASI for holistic Evaluation of multimodAl LLMs on Spatial Intelligence.<n>We conduct the study across eight key benchmarks, at a cost exceeding ten billion total tokens.<n>Our empirical study then reveals that GPT-5 demonstrates unprecedented strength in spatial intelligence (SI), yet (2) still falls short of human performance significantly across a broad spectrum of SI-tasks.
  arXiv  Detail & Related papers  (2025-08-18T17:55:17Z)
• Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning [20.515599491717442]
  We introduce textbfMetis-RISE (textbfRL textbfSFT textbfEnhances) for multimodal reasoning model learning.
  arXiv  Detail & Related papers  (2025-06-16T02:56:13Z)
• Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining [74.83412846804977]
  Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models.<n>We present a systematic end-to-end study of RL fine-tuning for mathematical reasoning by training models entirely from scratch.
  arXiv  Detail & Related papers  (2025-04-10T17:15:53Z)
• MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning [55.82649731348012]
  We introduce the MMK12 dataset and MM-EUREKA with 7B and 32B parameters.<n>The former is a high-quality multimodal mathematics reasoning dataset featuring diverse knowledge domains with human-verified answers and solution processes.<n>The latter is a multimodal model employing rule-based reinforcement learning utilizing online filtering and two-stage training strategy to enhance training stability.
  arXiv  Detail & Related papers  (2025-03-10T14:23:12Z)
• Specialized Foundation Models Struggle to Beat Supervised Baselines [60.23386520331143]
  We look at three modalities -- genomics, satellite imaging, and time series -- with multiple recent FMs and compare them to a standard supervised learning workflow.<n>We find that it is consistently possible to train simple supervised models that match or even outperform the latest foundation models.
  arXiv  Detail & Related papers  (2024-11-05T04:10:59Z)
• Uni-Mol2: Exploring Molecular Pretraining Model at Scale [27.172011090947823]
  We present Uni-Mol2, an innovative molecular pretraining model that integrates features at the atomic level, graph level, and geometry structure level. We successfully scale Uni-Mol2 to 1.1 billion parameters through pretraining on 800 million conformations, making it the largest molecular pretraining model to date.
  arXiv  Detail & Related papers  (2024-06-21T08:28:54Z)
• InternLM2 Technical Report [159.70692271378581]
  This paper introduces InternLM2, an open-source Large Language Models (LLMs) that outperforms its predecessors in comprehensive evaluations across 6 dimensions and 30 benchmarks. The pre-training process of InternLM2 is meticulously detailed, highlighting the preparation of diverse data types. InternLM2 efficiently captures long-term dependencies, initially trained on 4k tokens before advancing to 32k tokens in pre-training and fine-tuning stages.
  arXiv  Detail & Related papers  (2024-03-26T00:53:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.