latent-memory

Tag

Cards List
#latent-memory

MemDefrag: Latent Memory Defragmentation for Large Language Models

arXiv cs.CL · 2026-07-08 Cached

Proposes MemDefrag, a training-free framework that uses a middle-layer tracing signal to defragment latent memory in LLMs, achieving significantly better knowledge retention than existing methods like MemoryLLM and M+.

0 favorites 0 likes
#latent-memory

Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation

Hugging Face Daily Papers · 2026-07-08 Cached

LaMem-VLA proposes a latent-memory-native framework that integrates short-term and long-term historical experience directly into Vision-Language-Action reasoning, enabling better performance on long-horizon robotic manipulation tasks.

0 favorites 0 likes
#latent-memory

EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory

Hugging Face Daily Papers · 2026-06-19 Cached

EvoEmbedding is a dynamic embedding model that maintains a continuously updated latent memory to generate adaptive representations for long-context retrieval, outperforming larger specialist models and improving agentic workflows.

0 favorites 0 likes
#latent-memory

One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA

Hugging Face Daily Papers · 2026-06-09 Cached

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.

0 favorites 0 likes
#latent-memory

ElasticMem: Latent Memory as a Learnable Resource for LLM Agents

arXiv cs.CL · 2026-06-01 Cached

ElasticMem introduces a learnable latent memory mechanism for LLM agents that adaptively allocates variable budgets to retrieved memories, improving performance on memory-intensive QA and embodied agent tasks while reducing token costs.

0 favorites 0 likes
#latent-memory

Joint Agent Memory and Exploration Learning via Novelty Signals

Hugging Face Daily Papers · 2026-06-01 Cached

This paper introduces JAMEL, a framework that jointly trains agentic memory and exploration policies using novelty signals, enabling efficient exploration in open-ended environments with reduced computational costs.

0 favorites 0 likes
#latent-memory

Context Distillation as Latent Memory Management

arXiv cs.LG · 2026-05-29 Cached

This paper formulates context distillation as a latent memory management problem, proposing a framework that stores distilled contexts as independent LoRA adapters with retrieval, routing, and self-gating to improve robustness and efficiency.

0 favorites 0 likes
← Back to home

Submit Feedback