arXiv AI
Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Aug 28
Chart2SVG: Editable SVG Generation from Raster Chart Images
Chart2SVG is a multimodal large language model that transforms static raster chart images into editable SVGs enriched with semantic structure. By embedding chart‑specific semantic tokens into a vision‑language framework and training on the Beagle+ dataset of 33K distilled chart samples, the model captures both geometric primitives and their functional roles. The resulting SVGs are visually accurate and structurally consistent, and the accompanying Chart Structure Graph (CSG) exposes visual dependencies for interactive exploration, chart repurposing, and layout reuse.
arXiv Computer Vision
Sep 1
Evaluating Constrained Iterative Refinement for Scalable Vector Graphics Generation with Off-the-Shelf VLMs
arXiv:2608.28678v1 Announce Type: new Abstract: Scalable Vector Graphics (SVGs) power much of the modern visual ecosystem, yet state-of-the-art generative models focus almost entirely on rasterized i...
arXiv Computation and Language
Sep 25
Multimodal Thinking with Renderable Programs
The paper introduces SVGLM, a framework that integrates scalable vector graphics (SVG) primitives into vision‑language models to enable image generation within reasoning tasks. By treating SVG both as image descriptions and text instructions, SVGLM offers a compact and interpretable method for connecting text and image reasoning. The authors provide a curated SVG‑based image editing dataset and demonstrate strong SVG generation and image‑aware reasoning performance on a mathematical benchmark.
arXiv AI
Sep 3
Bernini: Latent Semantic Planning for Video Diffusion
Bernini proposes a unified framework that separates semantic planning and pixel rendering for video generation and editing. An MLLM-based planner predicts target semantics in ViT embedding space, while a DiT-based renderer synthesizes pixels conditioned on this plan, text features, and source VAE features for editing. The approach introduces Segment-Aware 3D Rotary Positional Embedding and chain-of-thought reasoning, achieving state‑of‑the‑art performance on diverse video benchmarks.
arXiv AI
5d ago
PSGAgent: Enhancing MLLMs' Dynamic Visual Perception for Panoptic Scene Graph Generation via Agentic Reasoning
PSGAgent is an agentic framework that improves Multimodal Large Language Models’ performance on Panoptic Scene Graph generation by enabling dynamic visual perception. It introduces a think‑act‑observe loop with a Region Zoom‑In Tool for detailed local exploration and a Visual Highlight Tool for focused segmentation, reducing noise from irrelevant context. A two‑stage training pipeline—first building a high‑quality, error‑aware Multimodal Chain‑of‑Thought dataset, then applying a hierarchical reward mechanism with Group Sequence Policy Optimization—optimizes tool usage and achieves state‑of‑the‑art results on the PSG benchmark.
arXiv Computer Vision
Sep 16
Reasoning with Image Generation
The paper introduces ReImaGin, a method that uses image generation models as a flexible visual reasoning tool for multimodal large language models. Unlike traditional fixed-function vision tools, ReImaGin accepts natural language commands and can perform open-ended visual operations such as removing occlusions or creating floorplans from multiple views. Experiments on six diverse visual reasoning tasks show that ReImaGin outperforms both text-only reasoning and specialist vision-tool baselines, achieving up to a 25% improvement.