Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models
This addresses limitations in long video comprehension and high-resolution image understanding for vision-language model applications, representing a strong specific gain.
The paper tackles the problem of long-context multimodal learning for vision-language models by introducing Eagle 2.5, which achieves 72.4% on Video-MME with 512 input frames, matching top-tier models like GPT-4o.
We introduce Eagle 2.5, a family of frontier vision-language models (VLMs) for long-context multimodal learning. Our work addresses the challenges in long video comprehension and high-resolution image understanding, introducing a generalist framework for both tasks. The proposed training framework incorporates Automatic Degrade Sampling and Image Area Preservation, two techniques that preserve contextual integrity and visual details. The framework also includes numerous efficiency optimizations in the pipeline for long-context data training. Finally, we propose Eagle-Video-110K, a novel dataset that integrates both story-level and clip-level annotations, facilitating long-video understanding. Eagle 2.5 demonstrates substantial improvements on long-context multimodal benchmarks, providing a robust solution to the limitations of existing VLMs. Notably, our best model Eagle 2.5-8B achieves 72.4% on Video-MME with 512 input frames, matching the results of top-tier commercial model such as GPT-4o and large-scale open-source models like Qwen2.5-VL-72B and InternVL2.5-78B.