# FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding

arXiv: https://arxiv.org/abs/2504.17447 · HTML: https://mlsanity.com/paper/2504.17447/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 42 of its 45 references that are in the map.
- First posted on arXiv 24 Apr 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 30 of 42)

- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [Long Context Transfer from Language to Vision](https://mlsanity.com/paper/2406.16852/) (2024)
- [LVBench: An Extreme Long Video Understanding Benchmark](https://mlsanity.com/paper/2406.08035/) (2024)
- [LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding](https://mlsanity.com/paper/2410.17434/) (2024)
- [VideoAgent: Long-form Video Understanding with Large Language Model as Agent](https://mlsanity.com/paper/2403.10517/) (2024)
- [Scene Text Visual Question Answering](https://mlsanity.com/paper/1905.13648/) (2019)
- [LongVILA: Scaling Long-Context Visual Language Models for Long Videos](https://mlsanity.com/paper/2408.10188/) (2024)
- [VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos](https://mlsanity.com/paper/2405.19209/) (2024)
- [MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding](https://mlsanity.com/paper/2404.05726/) (2024)
- [mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding](https://mlsanity.com/paper/2403.12895/) (2024)
- [Self-Chained Image-Language Model for Video Localization and Question Answering](https://mlsanity.com/paper/2305.06988/) (2023)
- [MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations](https://mlsanity.com/paper/2407.01523/) (2024)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [Building and better understanding vision-language models: insights and future directions](https://mlsanity.com/paper/2408.12637/) (2024)
- [Streaming Long Video Understanding with Large Language Models](https://mlsanity.com/paper/2405.16009/) (2024)
- [InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD](https://mlsanity.com/paper/2404.06512/) (2024)
- [LongVLM: Efficient Long Video Understanding via Large Language Models](https://mlsanity.com/paper/2404.03384/) (2024)
- [Tarsier: Recipes for Training and Evaluating Large Video Description Models](https://mlsanity.com/paper/2407.00634/) (2024)

## Built on by (most cited first, 27 of 27)

- [StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding](https://mlsanity.com/paper/2508.01875/) (2025)
- [VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding](https://mlsanity.com/paper/2507.13353/) (2025)
- [E-VRAG: Enhancing Long Video Understanding with Resource-Efficient Retrieval Augmented Generation](https://mlsanity.com/paper/2508.01546/) (2025)
- [Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding](https://mlsanity.com/paper/2510.15253/) (2025)
- [Symphony: A Cognitively-Inspired Multi-Agent System for Long-Video Understanding](https://mlsanity.com/paper/2603.17307/) (2026)
- [LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding](https://mlsanity.com/paper/2510.07233/) (2025)
- [Event-Anchored Frame Selection for Effective Long-Video Understanding](https://mlsanity.com/paper/2603.00983/) (2026)
- [Failures to Surface Harmful Contents in Video Large Language Models](https://mlsanity.com/paper/2508.10974/) (2025)
- [TimeScope: Towards Task-Oriented Temporal Grounding In Long Videos](https://mlsanity.com/paper/2509.26360/) (2025)
- [Towards Fast and Effective Long Video Understanding of Multimodal Large Language Models via Adaptive Quasi-Gaussian Sampling](https://mlsanity.com/paper/2606.24187/) (2026)
- [Poisoning Prompt-Guided Sampling in Video Large Language Models](https://mlsanity.com/paper/2509.20851/) (2025)
- [Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs](https://mlsanity.com/paper/2510.00705/) (2025)
- [AVIR: Adaptive Visual In-Document Retrieval for Efficient Multi-Page Document Question Answering](https://mlsanity.com/paper/2601.11976/) (2026)
- [3D-Layout-R1: Structured Reasoning for Language-Instructed Spatial Editing](https://mlsanity.com/paper/2603.22279/) (2026)
- [GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs](https://mlsanity.com/paper/2605.10762/) (2026)
- [HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes](https://mlsanity.com/paper/2508.13692/) (2025)
- [Towards Effective Long Video Understanding of Multimodal Large Language Models via One-shot Clip Retrieval](https://mlsanity.com/paper/2512.08410/) (2025)
- [Towards Sparse Video Understanding and Reasoning](https://mlsanity.com/paper/2602.13602/) (2026)
- [LensVLM: Selective Context Expansion for Compressed Visual Representation of Text](https://mlsanity.com/paper/2605.07019/) (2026)
- [QCA: Query- and Content-Aware Keyframe Selection for Long Video Understanding](https://mlsanity.com/paper/2607.00983/) (2026)
- [SagaQA: A Multi-hop Reasoning Benchmark for Long-form Narrative Understanding in TV Series](https://mlsanity.com/paper/2606.03301/) (2026)
- [Caved or Convinced: Temporal Sampling Gates Claim Deference in Video Large Language Models](https://mlsanity.com/paper/2608.03160/) (2026)
- [Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extraction](https://mlsanity.com/paper/2512.11399/) (2025)
- [ConsensusDrop: Fusing Visual and Cross-Modal Saliency for Efficient Vision Language Models](https://mlsanity.com/paper/2602.00946/) (2026)
- [QSVideo: Query-Conditioned Semantic Temporal Retrieval for Video Understanding](https://mlsanity.com/paper/2607.04559/) (2026)
- [Enhancing Localized Reasoning for Long Video Understanding via Efficient Segment-to-Video Supervision](https://mlsanity.com/paper/2608.20814/) (2026)
- [Do Input-Level Defenses Transfer to Observation-Level Attacks on VideoLLMs?](https://mlsanity.com/paper/2609.08331/) (2026)

## Abstract (arXiv)

There has been impressive progress in Large Multimodal Models (LMMs). Recent works extend these models to long inputs, including multi-page documents and long videos. However, the model size and performance of these long context models are still limited due to the computational cost in both training and inference. In this work, we explore an orthogonal direction and process long inputs without long context LMMs. We propose Frame Selection Augmented Generation (FRAG), where the model first selects relevant frames within the input, and then only generates the final outputs based on the selected frames. The core of the selection process is done by scoring each frame independently, which does not require long context processing. The frames with the highest scores are then selected by a simple Top-K selection. We show that this frustratingly simple framework is applicable to both long videos and multi-page documents using existing LMMs without any fine-tuning. We consider two models, LLaVA-OneVision and InternVL2, in our experiments and show that FRAG consistently improves the performance and achieves state-of-the-art performances for both long video and long document understanding. For videos, FRAG substantially improves InternVL2-76B by 5.8% on MLVU and 3.7% on Video-MME. For documents, FRAG achieves over 20% improvements on MP-DocVQA compared with recent LMMs specialized in long document understanding. Code is available at: https://github.com/NVlabs/FRAG