Hybrid Ai

Fields Medalist helps build hybrid mobile-cloud AI system for ARC-AGI: A new hybrid AI system combining a local 4B Qwen model on a mobile device with a cloud-based GLM model has been developed to tackle the ARC-AGI benchmark. The project involves collaboration with a Fields Medalist.

AI Models • 量子位

Researchers introduce HeadWiseKV to compress hybrid language model caches: Researchers have introduced HeadWiseKV, a training-free framework designed to compress the residual global key-value (KV) caches of hybrid language models. It assigns each physical KV head a static, multilevel history window to make cache demand predictable before serving.

LLM • arXiv

Perplexity launches hybrid compute to process sensitive data locally: Perplexity has launched hybrid compute for its Computer agentic platform, allowing a single AI agent to split tasks between cloud-based frontier models and local open-weight models on Apple silicon Macs. This system routes confidential data to the local machine without restarting the job or losing context.

Perplexity • VentureBeat