paper-with-me

Papers

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

2025-04-21 · Guo Chen, Zhiqi Li, Shihao Wang, Jindong Jiang, Yicheng Liu, Lidong Lu, De-An Huang, Wonmin Byeon, Matthieu Le, Max Ehrlich, Tuomas Rintamaki, Tyler Poon, Tong Lu, LiMin Wang, Bryan Catanzaro, Jan Kautz, Andrew Tao, Zhiding Yu, Guilin Liu

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.

📄 PDF Abstract BibTeX arXiv:2504.15271

Code (1)

nvlabs/eagle pytorch

Tasks

MMEVideo MMEVideo Understanding

Similar Papers 제목 키워드 기반

P-EAGLE: Parallel-Drafting EAGLE with Scalable Training

2026-02-01 · Mude Hui, Xin Huang, Jaime Campos Salas, Yue Sun 외 arxiv

Reasoning LLMs produce longer outputs, requiring speculative decoding drafters trained on extended sequences. Parallel drafting - predicting multiple tokens per forward pass - offers latency benefits over sequential gene…

Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models

2025-01-20 · Zhiqi Li, Guo Chen, Shilong Liu, Shihao Wang 외

Recently, promising progress has been made by open-source vision-language models (VLMs) in bringing their capabilities closer to those of proprietary frontier models. However, most open-source models only publish their f…

Attention Drift: What Autoregressive Speculative Decoding Models Learn

2026-05-11 · Doğaç Eldenk, Payal Mohapatra, Yigitcan Comlek, Kaan Oktay 외 arxiv

Speculative decoding accelerates LLM inference by drafting future tokens with a small model, but drafter models degrade sharply under template perturbation and long-context inputs. We identify a previously-unreported phe…

OWL: Overcoming Window Length-Dependence in Speculative Decoding for Long-Context Inputs

2025-10-08 · Jaeseong Lee, seung-won hwang, Aurick Qiao, Gabriele Oliaro 외 arxiv

Speculative decoding promises faster inference for large language models (LLMs), yet existing methods fail to generalize to real-world settings. Benchmarks typically assume short contexts (e.g., 2K tokens), whereas pract…

Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations

2026-03-16 · Sumedha Chugh, Ranjitha Prasad, Nazreen Shah arxiv

Trust and ethical concerns due to the widespread deployment of opaque machine learning (ML) models motivating the need for reliable model explanations. Post-hoc model-agnostic explanation methods addresses this challenge…

Feature ImportanceActive Learning