# ReWind: Understanding Long Videos with Instructed Learnable Memory

arXiv: https://arxiv.org/abs/2411.15556 · HTML: https://mlsanity.com/paper/2411.15556/

## Key facts

- Cited by 17 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 25 of its 31 references that are in the map.
- First posted on arXiv 23 Nov 2024.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding](https://mlsanity.com/paper/2312.02051/) (2023)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding](https://mlsanity.com/paper/2311.08046/) (2023)
- [LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment](https://mlsanity.com/paper/2310.01852/) (2023)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding](https://mlsanity.com/paper/2404.05726/) (2024)
- [GroundingGPT:Language Enhanced Multi-modal Grounding Model](https://mlsanity.com/paper/2401.06071/) (2024)
- [Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities](https://mlsanity.com/paper/2311.05698/) (2023)

## Built on by (most cited first, 17 of 17)

- [Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory](https://mlsanity.com/paper/2508.09736/) (2025)
- [FlexSelect: Flexible Token Selection for Efficient Long Video Understanding](https://mlsanity.com/paper/2506.00993/) (2025)
- [See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model](https://mlsanity.com/paper/2509.16087/) (2025)
- [Hierarchical Long Video Understanding with Audiovisual Entity Cohesion and Agentic Search](https://mlsanity.com/paper/2601.13719/) (2026)
- [FrameOracle: Learning What to See and How Much to See in Videos](https://mlsanity.com/paper/2510.03584/) (2025)
- [Personal Visual Context Learning in Large Multimodal Models](https://mlsanity.com/paper/2605.10936/) (2026)
- [MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering](https://mlsanity.com/paper/2606.05917/) (2026)
- [Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning](https://mlsanity.com/paper/2605.27318/) (2026)
- [Automated Procedural Analysis via Video-Language Models for AI-assisted Nursing Skills Assessment](https://mlsanity.com/paper/2509.16810/) (2025)
- [Stateful Visual Encoders for Vision-Language Models](https://mlsanity.com/paper/2606.04433/) (2026)
- [QSVideo: Query-Conditioned Semantic Temporal Retrieval for Video Understanding](https://mlsanity.com/paper/2607.04559/) (2026)
- [CAM: Question Answering on Entity-Centric Videos with Continuous Extraction and Adaptive Querying](https://mlsanity.com/paper/2609.06504/) (2026)
- [PREM: Prefix-Steered Recurrent Memory for Long-Video Understanding](https://mlsanity.com/paper/2609.23601/) (2026)
- [SPACE: Sparse Predictive Attractor via Counterfactual Eviction for Streaming Video Memory](https://mlsanity.com/paper/2609.32592/) (2026)
- [Simple Agentic Memory for Generalist Robot Policies](https://mlsanity.com/paper/2609.36595/) (2026)
- [EGSD: Event-Grounded Self-Distillation for Streaming Video Understanding](https://mlsanity.com/paper/2609.36803/) (2026)
- [VideoEvoHarness: Self Evolving Agent Harness from Unlabeled Videos for Video Understanding](https://mlsanity.com/paper/2610.15389/) (2026)

## Abstract (arXiv)

Vision-Language Models (VLMs) are crucial for applications requiring integrated understanding textual and visual information. However, existing VLMs struggle with long videos due to computational inefficiency, memory limitations, and difficulties in maintaining coherent understanding across extended sequences. To address these challenges, we introduce ReWind, a novel memory-based VLM designed for efficient long video understanding while preserving temporal fidelity. ReWind operates in a two-stage framework. In the first stage, ReWind maintains a dynamic learnable memory module with a novel read-perceive-write cycle that stores and updates instruction-relevant visual information as the video unfolds. This module utilizes learnable queries and cross-attentions between memory contents and the input stream, ensuring low memory requirements by scaling linearly with the number of tokens. In the second stage, we propose an adaptive frame selection mechanism guided by the memory content to identify instruction-relevant key moments. It enriches the memory representations with detailed spatial information by selecting a few high-resolution frames, which are then combined with the memory contents and fed into a Large Language Model (LLM) to generate the final answer. We empirically demonstrate ReWind's superior performance in visual question answering (VQA) and temporal grounding tasks, surpassing previous methods on long video benchmarks. Notably, ReWind achieves a +13% score gain and a +12% accuracy improvement on the MovieChat-1K VQA dataset and an +8% mIoU increase on Charades-STA for temporal grounding.