Tag
A free, MIT-licensed open-source tool called Anima Agent skill that turns a single biology prompt into detailed, interactive scientific visualizations—such as switchable mechanisms, inspectable molecular structures, and animated processes—rendered as standalone HTML or SVG. The skill instructs Claude to research the biology before drawing, and includes a reusable rendering toolkit with working examples.
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.
The paper introduces ReFigBench, a benchmark for evaluating coding agents in reconstructing scientific figures into editable PowerPoint slides, showing that harnesses significantly affect performance across model families.
This paper introduces RENDEQ, a generator of render-equivalence sets for scientific figures, and measures how well model agreement across semantics-preserving re-renderings tracks correctness in open-weight VLMs. It finds that agreement certifies correctness only above a threshold and that fine-tuning on self-consensus can hurt accuracy.
This paper presents the ICDAR 2026 Competition on Information Extraction from ALD/E Scientific Figures, introducing the Sci-ImageMiner benchmark with four complementary tasks. Results show SOTA multimodal models perform well on classification and summarization but struggle with data extraction and scientific reasoning, especially visual question answering.
Introduces SciDraw-Bench, a benchmark for evaluating scientific figure generation by text-to-image and multimodal models, with a four-dimensional evaluation protocol. Findings show domain-specific systems outperform general-purpose models, with text fidelity remaining the hardest challenge.
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.
This is a tool that automatically converts scientific paper charts into executable Python plotting code, using the Qwen vision model and Codex agent for panel segmentation, code generation, and refinement.