Tikzo
PulseAugur coverage of Tikzo — every cluster mentioning Tikzo across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New benchmark tests AI's ability to digitize historical math diagrams
A new benchmark called HistGramBench has been developed to evaluate how well AI models can convert historical mathematical diagrams into searchable formats. The benchmark consists of 2,507 diagrams from books printed be…
-
New TriGeoBench benchmark tests multimodal LLMs on geometry reasoning
Researchers have introduced TriGeoBench, a new benchmark designed to evaluate the geometry-centric reasoning capabilities of multimodal large language models (MLLMs). This benchmark comprises 7,000 question-answer pairs…
-
New MathVis benchmark tests AI's ability to visualize and reason with math diagrams
A new benchmark called MathVis has been developed to assess the capabilities of large language models in generating mathematical figures and utilizing them for reasoning. The benchmark includes 512 tasks, each with a ma…
-
New AI systems tackle scientific figure generation and editing · 2 sources tracked
Two new research papers introduce novel approaches to generating and editing scientific figures. The first, "Figures as Programs," proposes a multi-agent system called FigTree that recursively constructs figures as SVG …
-
New framework synthesizes scientific graphics with TikZ code, outperforming major LLMs
Researchers have developed a new framework for synthesizing scientific graphics programmatically using TikZ code. This framework includes SciTikZ-230K, a large dataset designed for executable and visually aligned image-…
-
New Diagram-MMU benchmark tests MLLMs on scientific diagrams
A new benchmark called Diagram-MMU has been developed to evaluate the capabilities of Multi-Modal Large Language Models (MLLMs) in understanding and interacting with scientific diagrams. The benchmark assesses MLLMs on …
-
New benchmark Edit2TikZ reveals MLLMs struggle with scientific figure editing
Researchers have introduced Edit2TikZ, a new benchmark designed to evaluate the capabilities of multimodal large language models (MLLMs) in editing scientific figures using TikZ code. The benchmark includes 1,548 sample…
-
PairCoder++ uses AI pair programming to improve code-driven artifact generation
Researchers have introduced PairCoder++, a novel approach that leverages pair programming between two AI agents to improve the generation of structured artifacts from code. This method involves a Driver agent writing co…
-
New framework automates editable scientific figure generation
Researchers have developed SciFig, a novel multi-agent framework designed to automate the creation of editable methodology figures for scientific papers. This system addresses the common trade-off between visual quality…
-
Paper studies LLM code editing with imperfect visual verification
A new paper explores the effectiveness of iterative refinement in LLM-based code editing, particularly for tasks involving visual outputs like TikZ diagrams. The study investigates how imperfect verifiers, which are nec…