Eagle 2.5: boosting long-context post-training for frontier vision-language models Oct 11, 2025· Guo Chen , Zhiqi Li , Shihao Wang , Jindong Jiang , Yicheng Liu , Lidong Lu , De-an Huang , Wonmin Byeon , Matthieu Le , Tuomas Rintamaki , Others · 0 min read Cite URL Type Conference paper Publication Proceedings of the Neural Information Processing Systems Last updated on Oct 11, 2025 ← 3D interaction geometric pre-training for molecular relational learning Oct 11, 2025 EgoExoBench: a benchmark for first-and third-person view video understanding in MLLMs Oct 11, 2025 →