Research
BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
The Mixture of Experts (MoE) framework has become a popular architecture for large language models due to its superior performance over dense models.
ResearchNexus: Specialization meets Adaptability for Efficiently Training Mixture of ExpertsCohere
ResearchRewardBench 2: Advancing Reward Model EvaluationCohere
ResearchNo Need for Explanations: LLMs can implicitly learn from mistakes in-contextCohere
ResearchThe Multilingual Divide and Its Impact on Global AI SafetyCohere
ResearchHere's a Free Lunch: Sanitizing Backdoored Models with Model MergeCohere
ResearchDiversify and Conquer: Diversity-Centric Data Selection with Iterative RefinementCohere
BlogsCan open models carry readable silent signals before they speak? Reproducing J-Lens Readouts on KimiFireworks
BlogsFireworks Nexus: Drop-in Open Frontier Intelligence for Teams with BudgetsFireworks
BlogsDockerCon 2022: What You Missed, and What Attendees LovedDocker
BlogsMemgraph Docker Extension: Empowering Real-Time Analytics with High PerformanceDocker
BlogsSupporting Open Source Projects at DockerDocker
BlogsDocker Networking Design PhilosophyDocker
BlogsThe Docker Dashboard Welcomes Hub and Local ImagesDocker
BlogsKitematic a Docker GUI joins the Docker family | DockerDocker
BlogsPackaging Supabase with NixSupabase
BlogsYour Complete Guide to KubeCon + CloudNativeCon North America 2025Cncf
BlogsMortgage Social Media Marketing: A Practical GuideHeygen
LearnAI Elements | Vercel AcademyVercel
BlogsWhat is MCP and how to get startedMintlify
BlogsAI can write your docs, but should it?Mintlify
