Helping Figures Tell their Story! Paper-Grounded Video Generation Explaining Complex Scientific Figures
Summary
Introduces MINARD, a pipeline for generating narrated, region-grounded walkthrough videos from scientific figures and their papers, along with the FigTalk benchmark and new grounding metrics.
View Cached Full Text
Cached at: 06/12/26, 08:50 AM
# Helping Figures Tell their Story! Paper-Grounded Video Generation Explaining Complex Scientific Figures Source: [https://arxiv.org/abs/2606.12576](https://arxiv.org/abs/2606.12576) [View PDF](https://arxiv.org/pdf/2606.12576) > Abstract:Scientific figures compress complex pipelines into a single canvas, yet understanding them requires paper\-grounded, step\-by\-step narration aligned with visual highlights a capability missing from current video generation systems and benchmarks\. To address this, we introduce paper\-grounded figure\-to\-video generation: generating narrated, region\-grounded walkthrough videos from a figure and its paper\. We propose MINARD \(Multimodal Interpretation of Narrated Architecture via Region Decomposition\), a pipeline that generates paper\-grounded narrations and sequentially grounds them to figure regions\. We also release FigTalk, a benchmark with new sequential and component\-level grounding metrics derived\. On FigTalk, MINARD generates humanlike, paper\-faithful narrations and outperforms narration\-conditioned figure spatial grounding compared to existing approaches in both automatic and human evaluation ## Submission history From: Ishani Mondal \[[view email](https://arxiv.org/show-email/70f8b856/2606.12576)\] **\[v1\]**Wed, 10 Jun 2026 18:25:10 UTC \(9,279 KB\)
Similar Articles
FigAct: Turning Scientific Figures into Active Canvases for Explanation
Brown University and Adobe Research introduce FigAct, a framework that turns static scientific figures into interactive visual presentations, where a trained model generates grounded narrations and applies visual actions to guide viewer attention. Their hierarchical search cuts token usage ~40x, and they train FigAct-8B with three task-specific rewards and release a human-verified benchmark for grounded visual explanation.
Thinking with Visual Grounding
This paper introduces visually grounded thinking, a method for vision-language models to interleave natural-language reasoning with explicit visual evidence grounding using points or boxes. A scalable synthesis pipeline and grounding-aware reinforcement learning improve reasoning accuracy, enabling a 4B model to match or surpass a 27B model on spatial and counting benchmarks.
ReGround: Grounding Reviewer Comments in Multimodal Evidence
ReGround is a large-scale dataset for grounding reviewer comments in multimodal evidence from scientific papers, revealing the challenges and importance of integrating text, tables, and figures in retrieval tasks.
Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding
Parallel Tube Decoding enables efficient simultaneous spatial and temporal video grounding by eliminating autoregressive dependencies, reducing latency and improving accuracy over standard methods.
VIS-Ground: Video Interactive Storytelling with Contextual Grounding
VIS-Ground 提出将异构输入上下文转化为可执行约束模型的上下文接地框架，通过结构化上下文抽象、生成约束归纳和约束化视频生成三个阶段，在三个视频生成骨干上平均取得 10.3 分的绝对提升。