[KongchangAI]
ConceptHiVe-Mem框架

HiVe-Mem

A memory framework for multimodal agents that improves the coverage of memory retrieval and the efficiency of evidence use in long-term interaction through two dimensions: horizontal memory expansion (neighbor expansion based on a relational graph) and vertical evidence composition (query-adaptive selection of evidence subsets).

Timeline (last 90 days)

Nov 10

HiVe-Mem is a multimodal memory framework that interleaves horizontal memory expansion with vertical evidence composition.

Unverified50%
Nov 10

HiVe-Mem organizes memory segments into a relational graph, with nodes connected through textual anchors and visual anchors.

Unverified50%
Nov 10

Horizontal expansion refers to that, after semantic retrieval hits initial seed memories, the system expands along the graph structure to their neighboring nodes, bringing semantically related memories that were not directly retrieved into the candidate set.

Unverified50%
Nov 10

In the vertical dimension, HiVe-Mem lets each retrieved memory retain multiple forms of evidence, including compact summaries, descriptive text, visual-grounding-based views, raw images, and interaction history.

Unverified50%
Nov 10

A lightweight trainable selector independently composes an evidence subset for each memory, thereby adaptively exploiting heterogeneous multimodal information according to the specific query.

Unverified50%
Nov 10

The researchers conducted experiments on three multimodal memory benchmarks, and the results show that HiVe-Mem can consistently improve task performance across different base models.

Unverified50%
Nov 10

Compared with the most efficient competitive multimodal baseline, HiVe-Mem reduces token consumption by about 90%.

Unverified50%
Nov 10

Horizontal expansion broadens the recall coverage of memories, while vertical composition optimizes how each memory's evidence contributes, and the two work in concert.

Unverified50%

All Facts (8)

Source Articles