Search papers, labs, and topics across Lattice.
5
0
5
10
Native memory in foundation models can significantly enhance efficiency and performance, as shown by the innovative Metis architecture.
LLM agents can achieve state-of-the-art performance in dynamic environments by treating memory as a continuously evolving graph, rather than a static repository.
LLMs can automatically generate hierarchical concept-attribute knowledge that significantly boosts image clustering performance, even surpassing zero-shot CLIP in many cases.
Forget fixed Top-k retrieval: HingeMem's query-adaptive retrieval dynamically decides *what* and *how much* to retrieve from long-term memory, boosting dialogue performance by 20% while slashing token costs.
A Scene-Aware Memory Discrimination method, which comprises two key components: the Gating Unit Module (GUM) and the Cluster Prompting Module (CPM), which significantly enhances both the efficiency and quality of memory construction, leading to better organization of personal knowledge.
