Utilizing Visualization-oriented Natural Language Interfaces (V-NLI) as a complementary
input modality to direct manipulation for visual analytics can provide an engaging user …

Visualizations themselves have become a data format. Akin to other data formats such as
text and images, visualizations are increasingly created, stored, shared, and (re-) used with …

Natural language descriptions sometimes accompany visualizations to better communicate
and contextualize their insights, and to improve their accessibility for readers with …

Charts are commonly used for exploring data and communicating insights. Generating
natural language summaries from charts can be very helpful for people in inferring key …

We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series
that builds upon InternVL 2.0, maintaining its core model architecture while introducing …

Captions that describe or explain charts help improve recall and comprehension of the
depicted data and provide a more accessible medium for people with visual disabilities …

We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs)
that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary …

Large Vision-Language Models (LVLMs) show significant strides in general-purpose
multimodal applications such as visual dialogue and embodied navigation. However …

Charts are very popular for analyzing data, visualizing key insights and answering complex
reasoning questions about data. To facilitate chart-based data analysis using natural …

Alternative text is critical in communicating graphics to people who are blind or have low
vision. Especially for graphics that contain rich information, such as visualizations, poorly …