COMPACT: COMPositional Atomic-to-Complex Visual Capability Tuning

• URL: http://arxiv.org/abs/2504.21850v1
• Date: Wed, 30 Apr 2025 17:57:22 GMT
• Title: COMPACT: COMPositional Atomic-to-Complex Visual Capability Tuning
• Authors: Xindi Wu, Hee Seung Hwang, Polina Kirichenko, Olga Russakovsky,
• Abstract summary: Multimodal Large Language Models (MLLMs) excel at simple vision-language tasks but struggle when faced with complex tasks that require multiple capabilities.<n>Visual Instruction Tuning (VIT) has traditionally focused on scaling data volume, but not the compositional complexity of training examples.<n>We propose COMPACT, which generates a training dataset explicitly controlling for the compositional complexity of the training examples.
• Score: 27.554093258249704
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models (MLLMs) excel at simple vision-language tasks but struggle when faced with complex tasks that require multiple capabilities, such as simultaneously recognizing objects, counting them, and understanding their spatial relationships. This might be partially the result of the fact that Visual Instruction Tuning (VIT), a critical training step for MLLMs, has traditionally focused on scaling data volume, but not the compositional complexity of training examples. We propose COMPACT (COMPositional Atomic-to-complex visual Capability Tuning), which generates a training dataset explicitly controlling for the compositional complexity of the training examples. The data from COMPACT allows MLLMs to train on combinations of atomic capabilities to learn complex capabilities more efficiently. Across all benchmarks, COMPACT achieves comparable performance to the LLaVA-665k VIT while using less than 10% of its data budget, and even outperforms it on several, especially those involving complex multi-capability tasks. For example, COMPACT achieves substantial 83.3% improvement on MMStar and 94.0% improvement on MM-Vet compared to the full-scale VIT on particularly complex questions that require four or more atomic capabilities. COMPACT offers a scalable, data-efficient, visual compositional tuning recipe to improve on complex visual-language tasks.

Related papers

• Learning to Instruct for Visual Instruction Tuning [56.23557578405653]
  We propose LIT, an advancement of visual instruction tuning (VIT)<n>LIT adopts a simple yet effective approach by incorporating the loss function into both the instruction and response sequences.<n>Surprisingly, LIT attains exceptional fundamental visual capabilities, yielding up to an 18% improvement in captioning performance.
  arXiv  Detail & Related papers  (2025-03-28T08:04:51Z)
• MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale [66.73529246309033]
  multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks.<n>Existing instruction-tuning datasets only provide phrase-level answers without any intermediate rationales.<n>We introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate rationales.
  arXiv  Detail & Related papers  (2024-12-06T18:14:24Z)
• Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability [12.349247962800813]
  Large language models (LLMs) have emerged as powerful tools for many AI problems. They exhibit remarkable in-context learning (ICL) capabilities. How they approach composite tasks remains an open and largely underexplored question.
  arXiv  Detail & Related papers  (2024-07-22T15:22:34Z)
• In-Context Learning Improves Compositional Understanding of Vision-Language Models [2.762909189433944]
  compositional image understanding remains a rather difficult task due to the object bias present in training data. We compare contrastive models with generative ones and analyze their differences in architecture, pre-training data, and training tasks and losses. Our proposed approach outperforms baseline models across multiple compositional understanding datasets.
  arXiv  Detail & Related papers  (2024-07-22T09:03:29Z)
• AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning [93.96463520716759]
  Large language model (LLM) agents have demonstrated impressive capabilities in utilizing external tools and knowledge to boost accuracy and hallucinations. Here, we introduce AvaTaR, a novel and automated framework that optimize an LLM agent to effectively leverage provided tools, improving performance on a given task.
  arXiv  Detail & Related papers  (2024-06-17T04:20:02Z)
• How does Multi-Task Training Affect Transformer In-Context Capabilities? Investigations with Function Classes [6.652837942112205]
  Large language models (LLM) have recently shown the extraordinary ability to perform unseen tasks based on few-shot examples provided as text. We propose several effective curriculum learning strategies that allow ICL models to achieve higher data efficiency and more stable convergence. Our experiments reveal that ICL models can effectively learn difficult tasks by training on progressively harder tasks while mixing in prior tasks, denoted as mixed curriculum in this work.
  arXiv  Detail & Related papers  (2024-04-04T16:15:23Z)
• What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning [111.01953096869947]
  Visual instruction tuning is crucial for enhancing the zero-shot generalization capability of Multi-modal Large Language Models (MLLMs)<n>We develop a systematic approach to automatically create high-quality complex visual reasoning instructions.<n> Experimental results consistently demonstrate the enhanced performance of all compared MLLMs.
  arXiv  Detail & Related papers  (2023-11-02T15:36:12Z)
• TaskLAMA: Probing the Complex Task Understanding of Language Models [13.336015994186955]
  Structured Complex Task Decomposition (SCTD) is a problem of breaking down a complex real-world task into a directed acyclic graph over individual steps that contribute to achieving the task. We probe how accurately SCTD can be done with the knowledge extracted from Large Language Models (LLMs) Our experiments reveal that LLMs are able to decompose complex tasks into individual steps effectively, with a relative improvement of 15% to 280% over the best baseline.
  arXiv  Detail & Related papers  (2023-08-29T13:36:45Z)
• An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training [79.78201886156513]
  We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Our approach achieves comparable results to single-task state-of-the-art models and demonstrates strong generalization on downstream tasks.
  arXiv  Detail & Related papers  (2023-06-29T17:59:57Z)
• Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learners [74.92558307689265]
  We propose Mod-Squad, a new model that is Modularized into groups of experts (a 'Squad') We optimize this matching process during the training of a single model. Experiments on the Taskonomy dataset with 13 vision tasks and the PASCAL-Context dataset with 5 vision tasks show the superiority of our approach.
  arXiv  Detail & Related papers  (2022-12-15T18:59:52Z)

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.