MMFactory: A Universal Solution Search Engine for Vision-Language Tasks

• URL: http://arxiv.org/abs/2412.18072v1
• Date: Tue, 24 Dec 2024 00:59:16 GMT
• Title: MMFactory: A Universal Solution Search Engine for Vision-Language Tasks
• Authors: Wan-Cyuan Fan, Tanzila Rahman, Leonid Sigal,
• Abstract summary: We introduce MMFactory, a universal framework that acts like a solution search engine across various available models.<n>Based on a task description and few sample input-output pairs, MMFactory can suggest a diverse pool of programmatic solutions.<n> MMFactory also proposes metrics and benchmarks performance / resource characteristics, allowing users to pick a solution that meets their unique design constraints.
• Score: 35.262080125288115
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With advances in foundational and vision-language models, and effective fine-tuning techniques, a large number of both general and special-purpose models have been developed for a variety of visual tasks. Despite the flexibility and accessibility of these models, no single model is able to handle all tasks and/or applications that may be envisioned by potential users. Recent approaches, such as visual programming and multimodal LLMs with integrated tools aim to tackle complex visual tasks, by way of program synthesis. However, such approaches overlook user constraints (e.g., performance / computational needs), produce test-time sample-specific solutions that are difficult to deploy, and, sometimes, require low-level instructions that maybe beyond the abilities of a naive user. To address these limitations, we introduce MMFactory, a universal framework that includes model and metrics routing components, acting like a solution search engine across various available models. Based on a task description and few sample input-output pairs and (optionally) resource and/or performance constraints, MMFactory can suggest a diverse pool of programmatic solutions by instantiating and combining visio-lingual tools from its model repository. In addition to synthesizing these solutions, MMFactory also proposes metrics and benchmarks performance / resource characteristics, allowing users to pick a solution that meets their unique design constraints. From the technical perspective, we also introduced a committee-based solution proposer that leverages multi-agent LLM conversation to generate executable, diverse, universal, and robust solutions for the user. Experimental results show that MMFactory outperforms existing methods by delivering state-of-the-art solutions tailored to user problem specifications. Project page is available at https://davidhalladay.github.io/mmfactory_demo.

Related papers

• Training-free LLM Merging for Multi-task Learning [74.93025750111019]
  Hi-Merging is a training-free method for unifying different specialized LLMs into a single model.<n>Experiments on multiple-choice and question-answering tasks in both Chinese and English validate Hi-Merging's ability for multi-task learning.
  arXiv  Detail & Related papers  (2025-06-14T07:21:11Z)
• Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment [58.94611347128066]
  Task Preference Optimization (TPO) is a novel method that utilizes differentiable task preferences derived from typical fine-grained visual tasks. By leveraging rich visual labels during training, TPO significantly enhances the MLLM's multimodal capabilities and task-specific performance. Our instantiation of this approach with VideoChat and LLaVA demonstrates an overall 14.6% improvement in multimodal performance compared to baseline models.
  arXiv  Detail & Related papers  (2024-12-26T18:56:05Z)
• UniMEL: A Unified Framework for Multimodal Entity Linking with Large Language Models [0.42832989850721054]
  Multimodal Entities Linking (MEL) is a crucial task that aims at linking ambiguous mentions within multimodal contexts to referent entities in a multimodal knowledge base, such as Wikipedia. Existing methods overcomplicate the MEL task and overlook the visual semantic information, which makes them costly and hard to scale. We propose UniMEL, a unified framework which establishes a new paradigm to process multimodal entity linking tasks using Large Language Models.
  arXiv  Detail & Related papers  (2024-07-23T03:58:08Z)
• Arcee's MergeKit: A Toolkit for Merging Large Language Models [0.6374098147778188]
  MergeKit is a framework to efficiently merge models on any hardware. To date, thousands of models have been merged by the open-source community.
  arXiv  Detail & Related papers  (2024-03-20T02:38:01Z)
• LLMBind: A Unified Modality-Task Integration Framework [38.95771765322677]
  We introduce textbfLLMBind, a novel framework designed to unify a diverse array of multi-modal tasks. By harnessing a Mixture-of-Experts (MoE) Large Language Model (LLM), LLMBind processes multi-modal inputs and generates task-specific tokens, enabling the invocation of corresponding models to accomplish tasks.
  arXiv  Detail & Related papers  (2024-02-22T12:36:31Z)
• Merging Multi-Task Models via Weight-Ensembling Mixture of Experts [64.94129594112557]
  Merging Transformer-based models trained on different tasks into a single unified model can execute all the tasks concurrently. Previous methods, exemplified by task arithmetic, have been proven to be both effective and scalable. We propose to merge most of the parameters while upscaling the Transformer layers to a weight-ensembling mixture of experts (MoE) module.
  arXiv  Detail & Related papers  (2024-02-01T08:58:57Z)
• Small LLMs Are Weak Tool Learners: A Multi-LLM Agent [73.54562551341454]
  Large Language Model (LLM) agents significantly extend the capabilities of standalone LLMs. We propose a novel approach that decomposes the aforementioned capabilities into a planner, caller, and summarizer. This modular framework facilitates individual updates and the potential use of smaller LLMs for building each capability.
  arXiv  Detail & Related papers  (2024-01-14T16:17:07Z)
• Towards Robust Multi-Modal Reasoning via Model Selection [7.6621866737827045]
  LLM serves as the "brain" of the agent, orchestrating multiple tools for collaborative multi-step task solving. We propose the $textitM3$ framework as a plug-in with negligible runtime overhead at test-time. Our experiments reveal that our framework enables dynamic model selection, considering both user inputs and subtask dependencies.
  arXiv  Detail & Related papers  (2023-10-12T16:06:18Z)
• CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets [75.64181719386497]
  We present CRAFT, a tool creation and retrieval framework for large language models (LLMs) It creates toolsets specifically curated for the tasks and equips LLMs with a component that retrieves tools from these sets to enhance their capability to solve complex tasks. Our method is designed to be flexible and offers a plug-and-play approach to adapt off-the-shelf LLMs to unseen domains and modalities, without any finetuning.
  arXiv  Detail & Related papers  (2023-09-29T17:40:26Z)
• AutoML-GPT: Large Language Model for AutoML [5.9145212342776805]
  We have established a framework called AutoML-GPT that integrates a comprehensive set of tools and libraries. Through a conversational interface, users can specify their requirements, constraints, and evaluation metrics. We have demonstrated that AutoML-GPT significantly reduces the time and effort required for machine learning tasks.
  arXiv  Detail & Related papers  (2023-09-03T09:39:49Z)
• ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models [74.64651681052628]
  We introduce ModelScope-Agent, a customizable agent framework for real-world applications based on open-source LLMs as controllers. It provides a user-friendly system library, with customizable engine design to support model training on multiple open-source LLMs. A comprehensive framework has been proposed spanning over tool-use data collection, tool retrieval, tool registration, memory control, customized model training, and evaluation.
  arXiv  Detail & Related papers  (2023-09-02T16:50:30Z)

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.