How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?

• URL: http://arxiv.org/abs/2506.16450v1
• Date: Thu, 19 Jun 2025 16:35:49 GMT
• Title: How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?
• Abstract summary: We investigate whether off-the-shelf Multimodal Large Language Models (MLLMs) can tackle Online Episodic-Memory Video Question Answering (OEM-VQA) without additional training.<n>Our pipeline converts a streaming egocentric video into a lightweight textual memory, only a few kilobytes per minute, via an MLLM descriptor module, and answers multiple-choice questions by querying this memory with an LLM reasoner module.
• Score: 11.937961684293672
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate whether off-the-shelf Multimodal Large Language Models (MLLMs) can tackle Online Episodic-Memory Video Question Answering (OEM-VQA) without additional training. Our pipeline converts a streaming egocentric video into a lightweight textual memory, only a few kilobytes per minute, via an MLLM descriptor module, and answers multiple-choice questions by querying this memory with an LLM reasoner module. On the QAEgo4D-Closed benchmark, our best configuration attains 56.0% accuracy with 3.6 kB per minute storage, matching the performance of dedicated state-of-the-art systems while being 10**4/10**5 times more memory-efficient. Extensive ablations provides insights into the role of each component and design choice, and highlight directions of improvement for future research.

Related papers

• Reasoning with Memory: A Temporal Granularity-Adaptive Framework for Training-Free Long Video Understanding [47.48582887762574]
  ReMem is a temporal granularity-adaptive selection framework for training-free LongVideoQA.<n>By explicitly preserving temporal information with memory mechanisms, ReMem suppresses redundancy and empowers MLLMs to perform robust multi-granular video reasoning.
  arXiv  Detail & Related papers  (2026-06-30T10:55:56Z)
• MeMo: Memory as a Model [96.54179792557863]
  Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates.<n>MeMo is a modular framework that encodes new knowledge into a dedicated memory model while keeping the LLM parameters unchanged.<n>MeMo achieves strong performance compared to existing methods across diverse settings.
  arXiv  Detail & Related papers  (2026-05-14T17:51:34Z)
• Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanism [82.67996027633986]
  Long video understanding is a key challenge that plagues the advancement of emphMultimodal Large language Models (MLLMs)<n>In this paper, we study this problem from the perspective of visual memory mechanism, and proposed a novel and training-free approach, termed emphFlexible Memory (textbfFlexMem)<n>In principle, FlexMem aims to mimic human behavior of video watching, emphi.e., continually watching video content and recalling the most relevant memory fragments to answer the question.
  arXiv  Detail & Related papers  (2026-03-31T04:23:33Z)
• Towards Effective and Efficient Long Video Understanding of Multimodal Large Language Models via One-shot Clip Retrieval [57.88666884515147]
  We propose One-shot video-Clip based Retrieval AuGmentation (OneClip-RAG)<n>OneClip-RAG makes full use of the merits of video clips for augmented video understanding.<n>It is also equipped with a novel query-guided video chunking algorithm.
  arXiv  Detail & Related papers  (2025-12-09T09:40:20Z)
• MemLoRA: Distilling Expert Adapters for On-Device Memory Systems [71.32550994522738]
  Memory-augmented Large Language Models (LLMs) have demonstrated remarkable consistency during dialogues.<n>MemLoRA is a novel memory system that integrates small Vision-Language Models.<n>VLM-integrated MemLoRA-V shows massive improvements in caption-based approaches.
  arXiv  Detail & Related papers  (2025-12-04T12:56:30Z)
• video-SALMONN S: Streaming Audio-Visual LLMs Beyond Length Limits via Memory [51.03819128505358]
  Video-SALMONN S is first to process 3-hour videos at 1 FPS and 360p resolution under a fixed memory budget.<n>A test-time-training memory module continually updates token representations to capture long-range dependencies.<n>A prompt-dependent memory reader retrieves context-relevant content from fixed-size memory.
  arXiv  Detail & Related papers  (2025-10-13T08:20:15Z)
• Free-MoRef: Instantly Multiplexing Context Perception Capabilities of Video-MLLMs within Single Inference [88.57742986765238]
  Free-MoRef is a training-free approach to multiplex the context perception capabilities of Video-MLLMs.<n>Experiments show that Free-MoRef achieves full perception of 2$times$ to 8$times$ longer input frames without compression on a single A100 GPU.
  arXiv  Detail & Related papers  (2025-08-04T07:31:10Z)
• Flash-VStream: Efficient Real-Time Understanding for Long Video Streams [64.25549822010372]
  Flash-VStream is a video language model capable of processing extremely long videos and responding to user queries in real time.<n>Compared to existing models, Flash-VStream achieves significant reductions in inference latency.
  arXiv  Detail & Related papers  (2025-06-30T13:17:49Z)
• ReWind: Understanding Long Videos with Instructed Learnable Memory [8.002949551539297]
  Vision-Language Models (VLMs) are crucial for applications requiring integrated understanding textual and visual information.<n>We introduce ReWind, a novel memory-based VLM designed for efficient long video understanding while preserving temporal fidelity.<n>We empirically demonstrate ReWind's superior performance in visual question answering (VQA) and temporal grounding tasks, surpassing previous methods on long video benchmarks.
  arXiv  Detail & Related papers  (2024-11-23T13:23:22Z)
• AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction [10.579335027350263]
  AdaCM$2$ is an adaptive cross-modality memory reduction approach to video-text alignment on video streams.<n>It achieves a 4.5% improvement across multiple tasks in the LVU dataset with a GPU memory consumption reduction of up to 65%.
  arXiv  Detail & Related papers  (2024-11-19T18:04:13Z)
• Needle in the Haystack for Memory Based Large Language Models [31.885539843977472]
  Current large language models (LLMs) often perform poorly on simple fact retrieval tasks. We investigate if coupling a dynamically adaptable external memory to a LLM can alleviate this problem. We demonstrate that the external memory of Larimar, which allows fast write and read of an episode of text samples, can be used at test time to handle contexts much longer than those seen during training.
  arXiv  Detail & Related papers  (2024-07-01T16:32:16Z)
• Streaming Long Video Understanding with Large Language Models [83.11094441893435]
  VideoStreaming is an advanced vision-language large model (VLLM) for video understanding. It capably understands arbitrary-length video with a constant number of video streaming tokens encoded and propagatedly selected. Our model achieves superior performance and higher efficiency on long video benchmarks.
  arXiv  Detail & Related papers  (2024-05-25T02:22:09Z)
• MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding [66.56100008577134]
  This study focuses on designing an efficient and effective model for long-term video understanding. We propose to process videos in an online manner and store past video information in a memory bank. Our model can achieve state-of-the-art performances across multiple datasets.
  arXiv  Detail & Related papers  (2024-04-08T17:59:24Z)
• A Simple LLM Framework for Long-Range Video Question-Answering [63.50439701867275]
  We present LLoVi, a language-based framework for long-range video question-answering (LVQA) Our approach uses a frame/clip-level visual captioner coupled with a Large Language Model (GPT-3.5, GPT-4) Our method achieves 50.3% accuracy, outperforming the previous best-performing approach by 18.1% (absolute gain)
  arXiv  Detail & Related papers  (2023-12-28T18:58:01Z)
• LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos [15.127197238628396]
  LifelongMemory is a new framework for accessing long-form egocentric videographic memory through natural language question answering and retrieval. Our approach achieves state-of-the-art performance on the benchmark for question answering and is highly competitive on the natural language query (NLQ) challenge of Ego4D.
  arXiv  Detail & Related papers  (2023-12-07T19:19:25Z)
• Augmenting Language Models with Long-Term Memory [142.04940250657637]
  Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit. We propose a framework, Language Models Augmented with Long-Term Memory (LongMem), which enables LLMs to memorize long history.
  arXiv  Detail & Related papers  (2023-06-12T15:13:39Z)
• SCM: Enhancing Large Language Model with Self-Controlled Memory Framework [54.33686574304374]
  Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information.<n>We propose the Self-Controlled Memory (SCM) framework to enhance the ability of LLMs to maintain long-term memory and recall relevant information.
  arXiv  Detail & Related papers  (2023-04-26T07:25:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.