DeepSeek’s conditional memory fixes silent LLM waste: GPU cycles lost to static lookups

Through systematic experiments DeepSeek found the optimal balance between computation and memory with 75% of sparse model ...
GitHub

PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-forward Planar Splatting

[Oct 22, 2025] An improved new model, PLANA3Rv2, which outputs 3D planes without requiring image camera intrinsics, has been released and achieves improved results. [Oct 22, 2025] Code and pre-trained ...
IEEE

LLM-based PID controller optimization

Abstract: This study explores the application of Large Language Models (LLMs) to optimize Proportional-Integral-Derivative (PID) controller parameters, aiming to automate a process traditionally ...
InfoQ

Microsoft Research Develops Novel Approaches to Enforce Privacy in AI Models

A monthly overview of things you need to know as an architect or aspiring architect. Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with ...
IEEE

MORA-LLM: Enhancing Multi-Objective Optimization Recommendation Algorithm by Integrating Large Language Models

Abstract: Multi-objective evolutionary algorithms (MOEAs) have achieved notable success in recommendation systems (RSs) by meeting diverse user needs. However, existing MOEAs lack effective methods to ...
InfoQ

Cactus v1: Cross-Platform LLM Inference on Mobile with Zero Latency and Full Privacy

A monthly overview of things you need to know as an architect or aspiring architect. Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with ...