Innovator-VL: A Multimodal Large Language Model for Scientific Discovery

• URL: http://arxiv.org/abs/2601.19325v1
• Date: Tue, 27 Jan 2026 08:12:18 GMT
• Title: Innovator-VL: A Multimodal Large Language Model for Scientific Discovery
• Authors: Zichen Wen, Boxue Yang, Shuang Chen, Yaojie Zhang, Yuhang Han, Junlong Ke, Cong Wang, Yicheng Fu, Jiawang Zhao, Jiangchao Yao, Xi Fang, Zhen Wang, Henxing Cai, Lin Yao, Zhifeng Gao, Yanhui Hong, Nang Yuan, Yixuan Li, Guojiang Zhao, Haoyi Tao, Nan Wang, Han Lyu, Guolin Ke, Ning Liao, Xiaoxing Wang, Kai Chen, Zhiyu Li, Feiyu Xiong, Sihan Hu, Kun Chen, Yanfeng Wang, Weinan E, Linfeng Zhang, Linfeng Zhang,
• Abstract summary: We present Innovator-VL, a scientific multimodal large language model designed to advance understanding and reasoning across diverse scientific domains.<n>We show that principled training design and transparent methodology can yield strong scientific intelligence with substantially reduced data requirements.
• Score: 84.15264653078826
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Innovator-VL, a scientific multimodal large language model designed to advance understanding and reasoning across diverse scientific domains while maintaining excellent performance on general vision tasks. Contrary to the trend of relying on massive domain-specific pretraining and opaque pipelines, our work demonstrates that principled training design and transparent methodology can yield strong scientific intelligence with substantially reduced data requirements. (i) First, we provide a fully transparent, end-to-end reproducible training pipeline, covering data collection, cleaning, preprocessing, supervised fine-tuning, reinforcement learning, and evaluation, along with detailed optimization recipes. This facilitates systematic extension by the community. (ii) Second, Innovator-VL exhibits remarkable data efficiency, achieving competitive performance on various scientific tasks using fewer than five million curated samples without large-scale pretraining. These results highlight that effective reasoning can be achieved through principled data selection rather than indiscriminate scaling. (iii) Third, Innovator-VL demonstrates strong generalization, achieving competitive performance on general vision, multimodal reasoning, and scientific benchmarks. This indicates that scientific alignment can be integrated into a unified model without compromising general-purpose capabilities. Our practices suggest that efficient, reproducible, and high-performing scientific multimodal models can be built even without large-scale data, providing a practical foundation for future research.

Related papers

• Beyond Language Modeling: An Exploration of Multimodal Pretraining [125.34714978184638]
  We provide empirical clarity through controlled, from-scratch pretraining experiments.<n>We adopt the Transfusion framework, using next-token prediction for language and diffusion for vision.<n>We demonstrate that the MoE architecture harmonizes this scaling asymmetry by providing the high model capacity required by language.
  arXiv  Detail & Related papers  (2026-03-03T18:58:00Z)
• MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training Paradigm [25.7631608456086]
  MindGPT-4ov is a general post-training paradigm spanning data production, model training, and efficient deployment.<n>It achieves state-of-the-art performance across multiple benchmarks at low cost.<n>MindGPT-4ov also demonstrates superior user experience in vertical domain tasks.
  arXiv  Detail & Related papers  (2025-12-02T16:04:11Z)
• A Survey on Efficient Vision-Language-Action Models [153.11669266922993]
  Vision-Language-Action models (VLAs) represent a significant frontier in embodied intelligence, aiming to bridge digital knowledge with physical-world interaction.<n>Motivated by the urgent need to address these challenges, this survey presents the first comprehensive review of Efficient Vision-Language-Action models.
  arXiv  Detail & Related papers  (2025-10-27T17:57:33Z)
• Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models [63.69856480318313]
  AGILE formulates jigsaw solving as an interactive process, enabling the model to progressively engage with the environment.<n>We show that AGILE substantially boosts performance on jigsaw tasks of varying complexity.<n>We also demonstrate strong generalization across 9 general vision tasks, achieving an average improvement of 3.1%.
  arXiv  Detail & Related papers  (2025-10-01T17:58:05Z)
• Is Diversity All You Need for Scalable Robotic Manipulation? [50.747150672933316]
  We investigate the nuanced role of data diversity in robot learning by examining three critical dimensions-task (what to do), embodiment (which robot to use), and expert (who demonstrates)-challenging the conventional intuition of "more diverse is better"<n>We show that task diversity proves more critical than per-task demonstration quantity, benefiting transfer from diverse pre-training tasks to novel downstream scenarios.<n>We propose a distribution debiasing method to mitigate velocity ambiguity, the yielding GO-1-Pro achieves substantial performance gains of 15%, equivalent to using 2.5 times pre-training data.
  arXiv  Detail & Related papers  (2025-07-08T17:52:44Z)
• LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants [22.6701800159627]
  We introduce a unified framework and assess leading Vision models under zero-shot and fine-tuned settings.<n>Our results reveal that even advanced models like GPT-4o struggle with fine-grained assembly tasks, highlighting gaps in fine visual understanding.
  arXiv  Detail & Related papers  (2025-07-07T22:29:01Z)
• Remaining Useful Life Prediction: A Study on Multidimensional Industrial Signal Processing and Efficient Transfer Learning Based on Large Language Models [6.118896920507198]
  This paper introduces an innovative regression framework utilizing large language models (LLMs) for RUL prediction. Experiments on the Turbofan engine's RUL prediction task show that the proposed model surpasses state-of-the-art (SOTA) methods. With minimal target domain data for fine-tuning, the model outperforms SOTA methods trained on full target domain data.
  arXiv  Detail & Related papers  (2024-10-04T04:21:53Z)
• MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding [59.41495657570397]
  We present a comprehensive dataset compiled from Nature Communications articles covering 72 scientific fields.<n>We evaluated 19 proprietary and open-source models on two benchmark tasks, figure captioning and multiple-choice, and conducted human expert annotation.<n>Fine-tuning Qwen2-VL-7B with our task-specific data achieved better performance than GPT-4o and even human experts in multiple-choice evaluations.
  arXiv  Detail & Related papers  (2024-07-06T00:40:53Z)
• ORacle: Large Vision-Language Models for Knowledge-Guided Holistic OR Domain Modeling [41.30327565949726]
  We introduce ORacle, an advanced vision-language model designed for holistic OR domain modeling. It incorporates multi-view and temporal capabilities and can leverage external knowledge during inference, enabling it to adapt to previously unseen surgical scenarios. In rigorous testing, in scene graph generation, and downstream tasks on the 4D-OR dataset, ORacle not only demonstrates state-of-the-art performance but does so requiring less data than existing models.
  arXiv  Detail & Related papers  (2024-04-10T14:24:10Z)
• StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data [129.92449761766025]
  We propose a novel data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning. This approach harnesses the power of generative models, marrying the abilities of ChatGPT and text-to-image generative models. Our research includes comprehensive experiments conducted on various datasets.
  arXiv  Detail & Related papers  (2023-08-20T12:43:52Z)

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.