paper-with-me

Papers

StarFlow: Generating Structured Workflow Outputs From Sketch Images

2025-03-27 · Patrice Bechard, Chao Wang, Amirhossein Abaskohi, Juan Rodriguez, Christopher Pal, David Vazquez, Spandana Gella, Sai Rajeswar, Perouz Taslakian

Workflows are a fundamental component of automation in enterprise platforms, enabling the orchestration of tasks, data processing, and system integrations. Despite being widely used, building workflows can be complex, often requiring manual configuration through low-code platforms or visual programming tools. To simplify this process, we explore the use of generative foundation models, particularly vision-language models (VLMs), to automatically generate structured workflows from visual inputs. Translating hand-drawn sketches or computer-generated diagrams into executable workflows is challenging due to the ambiguity of free-form drawings, variations in diagram styles, and the difficulty of inferring execution logic from visual elements. To address this, we introduce StarFlow, a framework for generating structured workflow outputs from sketches using vision-language models. We curate a diverse dataset of workflow diagrams -- including synthetic, manually annotated, and real-world samples -- to enable robust training and evaluation. We finetune and benchmark multiple vision-language models, conducting a series of ablation studies to analyze the strengths and limitations of our approach. Our results show that finetuning significantly enhances structured workflow generation, outperforming large vision-language models on this task.

📄 PDF Abstract BibTeX arXiv:2503.21889

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation

2026-05-08 · Ying Shen, Tianrong Chen, Yuan Gao, Yizhe Zhang 외 arxiv

Deep generative models have advanced rapidly across text and vision, motivating unified multimodal systems that can understand, reason over, and generate interleaved text-image sequences. Most existing approaches combine…

multimodal generationImage GenerationText Generation

ANPL: Towards Natural Programming with Interactive Decomposition

2023-05-29 · NeurIPS 2023 11 · Di Huang, Ziyuan Nan, Xing Hu, Pengwei Jin 외

Though LLMs are capable of generating plausible programs, it's challenging to interact with the LLMs further to revise the program, especially if the user's specific requirements are different from the initial proposal. …

ARCCode GenerationHumanEvalProgram Synthesis

STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows

2025-11-25 · Jiatao Gu, Ying Shen, Tianrong Chen, Laurent Dinh 외 arxiv

Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Yet in the video generation domain, where…

Video GenerationImage Generation

Teaching GANs to Sketch in Vector Format

2019-04-07 · Varshaneya V, S. Balasubramanian, Vineeth N. Balasubramanian

Sketching is more fundamental to human cognition than speech. Deep Neural Networks (DNNs) have achieved the state-of-the-art in speech-related tasks but have not made significant development in generating stroke-based sk…

Generative Adversarial NetworkReinforcement LearningReinforcement Learning (RL)

S3D: Sketch-Driven 3D Model Generation

2025-05-07 · Hail Song, Wonsik Shin, Naeun Lee, Soomin Chung 외

Generating high-quality 3D models from 2D sketches is a challenging task due to the inherent ambiguity and sparsity of sketch data. In this paper, we present S3D, a novel framework that converts simple hand-drawn sketche…

3D GenerationDecodermodel