TechiSeek

AddAdd your Listings

Research

Robust Distillation for Worst-class Performance

Cohere

Knowledge distillation has proven to be an effective technique in improving the performance a student model using predictions from a teacher model.

Visit Site

Research Cohere

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 ResearchLLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable ObjectivesCohere BlogsBenchmarking KubeVirt performance with virtbenchCncf ResourcesWorking with DrainsVercel BlogsUsing Preact with Storybook 3Netlify Blogs5 pro-tips and plugins for optimizing your Gatsby + Netlify siteNetlify BlogsImproved Netlify Forms spam filtering using AkismetNetlify BlogsGit-Centric Workflow: The One API to Rule Them AllNetlify BlogsCornerstone OnDemand delivers web projects 30% faster with NetlifyNetlify BlogsThe Developer’s Intro to Core Web VitalsNetlify Products & ServicesRiverr (a LAB agency)Netlify BlogsA Step-by-Step Guide: Phenomic on NetlifyNetlify BlogsIntroducing Built-in Identity Service to Streamline User ManagementNetlify BlogsRestrict access to your sites with role based redirectsNetlify BlogsWhat are Microservices?Netlify Products & ServicesPM d.o.o. | Netlify Agency DirectoryNetlify