Search

Few direct matches — filled in with the latest updates.

Tag: #memory-augmented1 results

LightMem Slashes LLM Memory Costs

LightMem Slashes LLM Memory Costs

LightMem is a lightweight memory system for LLMs that reduces token usage, API calls, and latency without sacrificing accuracy in long conversations and multi-task agents. It addresses redundancy in dialogues, rigid segmentation, and costly online updates by mimicking human hierarchical memory mechanisms. The paper is accepted to ICLR 2026 with open-source code available.

机器之心MediaFeb 26#memory-augmented#llm-agents#efficiency
📰

When AI Diagnoses Clash With Doctors

Patients are increasingly bringing answers from Doubao and other AI assistants into hospitals, sometimes challenging doctors' diagnoses and requesting unnecessary tests. The article documents how AI hallucinations, incomplete symptom interpretation, and misplaced patient trust are increasing consultation time and worsening doctor-patient friction.

Kling AI Becomes Kuaishou’s Growth Engine

Kling AI Becomes Kuaishou’s Growth Engine

Kling AI generated more than RMB 850 million in Q2 revenue, up 240% year over year, making it the standout growth driver in Kuaishou’s otherwise slowing business. Kuaishou is prioritizing AI investment, spinning Kling AI out for independent financing at an implied valuation of US$18 billion despite near-term profit pressure.

Rapidus Bets on 2nm Without Fighting TSMC

Rapidus Bets on 2nm Without Fighting TSMC

Rapidus is pursuing mass production of advanced 2nm semiconductors through a large-scale Japanese national project. Instead of matching TSMC’s scale, the company plans to compete with RUMS, an integrated one-building production model designed for diverse, lower-volume manufacturing.

ITmedia AI+ (日本)Media2h ago#2nm#semiconductors#chip-manufacturing