EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
Summary
EM^2Mem proposes an event-centric multimodal memory framework that binds heterogeneous evidence to event anchors for compact, generation-ready memory in long-video question answering, improving accuracy and reducing latency.
View Cached Full Text
Cached at: 09/02/26, 03:46 AM
Paper page - EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
Source: https://huggingface.co/papers/2609.00551 Authors:
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
EM²Mem binds multimodal evidence to event anchors for compact, generation-ready memory in long-video question answering.
Multimodal memoryoffers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, summaries, or graph facts as isolated fragments. Although searchable, such fragments are not generation-ready: language models must reconstruct cross-modal and temporal alignments at inference time, when context is limited and attribution is difficult. We propose EM^2Mem, an event-centricmultimodal memoryframework that binds heterogeneous evidence to event anchors during memory construction. Each event-indexed memory cell aligns multimodal records,temporal context,graph-linked relations, semantic facts, andprovenance, enabling compact evidence readout over grounded multimodal events rather than modality-specific fragments. Across threelong-video QAbenchmarks, EM^2Mem improves average accuracy over the strongest memory baseline by 2.0, 2.4, and 3.7 points, improves strict event-level Top-5evidence recallby 7.0 points, and reduces per-query latency by 4.67 times and total inference tokens by 63.66% (The code will be integrated into https://github.com/zjunlp/LightMem).
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2609\.00551
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2609.00551 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2609.00551 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2609.00551 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
MemLens is a new benchmark for evaluating memory capabilities in large vision-language models through multi-session conversations. It compares long-context and memory-augmented approaches, revealing limitations in both and motivating hybrid architectures.
S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering
S3Mem proposes a structured spatiotemporal scene-event memory framework for long-horizon interactive question answering, using anchor-sensitive retrieval and token-budget-aware evidence interface to outperform standard RAG in multiple environments.
One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA
Latent Memory introduces a compressed representation approach for external memory in question answering, reducing token consumption and storage requirements while maintaining competitive performance across text-only and multimodal benchmarks.
Parametric Multimodal User Memory: Storing What Captions Cannot Carry
This research paper introduces a parametric multimodal user memory system that improves AI agents' ability to recall users by integrating perceptual data like voice and appearance, using vision-language models and dedicated encoders to surpass text-based methods.
δ-mem: Efficient Online Memory for Large Language Models
The paper introduces δ-mem, a lightweight memory mechanism that enhances large language models by augmenting a frozen attention backbone with a compact associative memory state. It demonstrates improved performance on memory-heavy benchmarks with minimal computational overhead.