How MemWeaver Combines Behavioral and Cognitive Memory to Rebuild LLM Personalization

MemWeaver introduces a hierarchical memory that fuses behavior‑level and cognition‑level user signals, enabling large language models to generate more personalized content across multiple tasks, with extensive experiments, ablations, and an efficient incremental update mechanism demonstrating superior performance over strong baselines.

LLM personalizationLaMP benchmarkbehavioral memory

0 likes · 12 min read

How MemWeaver Combines Behavioral and Cognitive Memory to Rebuild LLM Personalization

Sohu Tech Products

May 21, 2024 · Artificial Intelligence

OPPO Multimodal Pretrained Model Deployment in Cloud-Edge Scenarios: Practices and Optimizations

OPPO details how it deploys multimodal pretrained models on resource‑constrained edge devices by compressing CLIP‑based image‑text retrieval, adapting Chinese text‑to‑image generation with LoRA and adapters, and lightweighting diffusion models through layer pruning and progressive distillation, achieving sub‑3‑second generation while preserving cloud‑level quality.

CLIPDistillationLoRA

0 likes · 18 min read

OPPO Multimodal Pretrained Model Deployment in Cloud-Edge Scenarios: Practices and Optimizations