InfoQ

Enhancing A/B Testing at DoorDash with Multi-Armed Bandits

While experimentation is essential, traditional A/B testing can be excessively slow and expensive, according to DoorDash engineers Caixia Huang and Alex Weinstein. To address these limitations, they ...
InfoQ

MIT's Recursive Language Models Improve Performance on Long-Context Tasks

Researchers at MIT's CSAIL published a design for Recursive Language Models (RLM), a technique for improving LLM performance on long-context tasks. RLMs use a programming environment to recursively ...
IEEE

Vehicle Routing Incorporating Implicit Preferences: An Omnidimensional Human–Algorithm Collaboration Approach

Due to the complexity and dynamism of real-world needs, traditional vehicle routing solutions usually do not sufficiently consider implicit user preferences, leading to low acceptance and reduced ...
IEEE

Toward the Age in Forwarding: A Deep Reinforcement Learning Enabled Routing Mechanism for Large-Scale Satellite Networks via Spatial–Temporal Graph Neural Networks

Abstract: In large-scale satellite networks, end-to-end data delivery confronts long propagation latency and dynamical connectivity, heavily challenging current routing strategies due to the ...
GitHub

dynamic-moe-router-kit

dynamic-moe-router-kit implements adaptive expert routing for Mixture-of-Experts (MoE) models, dynamically selecting the optimal number of experts per token based on input complexity. Based on the ...