AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Beyond 3 Million Tokens: A Multi-Modal Foundation Model for Full-Resolution Heliophysics

Sujit Roy, Johannes Schmude, Ata A Asanjan, Thorsten Kurth, Rohit Lal, Kshitiz Mandal, Vishal Gaur, Harris Abdul Majid, Nikolaos Dionelis, Berkay Aydin, Himanshu Patil, Andres Munoz-Jaramillo and 4 more

NeurIPS 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Medical vision-language models

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a multi-modal foundation model for heliophysics that handles full-resolution (4096x4096) solar imagery with contexts beyond 3 million tokens.

Problem

Vision foundation models rarely exceed 1M tokens, forcing downsampling of high-resolution heliophysics solar observations (native 4096x4096) and losing fine-grained spatial detail.

Approach

Scales context length beyond 3M tokens for vision foundation models so full-disk solar observations can be processed at native resolution without downsampling; details beyond the abstract are not available.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy