Home People Organizations Reports Fields Schools

Public Atlas People first, reports as evidence, organizations as context.

Atlas / Reports / Detail

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Vision-Language Models report from Shanghai AI Laboratory with 1 connected researcher in the LLMpeople atlas.

Shanghai AI Laboratory2025-04-141 researchers

Field: Vision-Language Models
Organization: Shanghai AI Laboratory
arXiv: 2504.10479

Canonical link

https://arxiv.org/abs/2504.10479

Connected researchers

Researcher 2 reports

Xiaohan Ding

ByteDance Seed

Xiaohan Ding is publicly credited as a coauthor on the Seed1.5-VL Technical Report and InternVL3 technical report, both focused on multimodal and vision-language models.

LLMpeople is a public atlas for discovering frontier AI researchers with context, provenance, and respect.

Privacy · Terms