TechniqueAgents6 recent entries13 Apr 2026EinsteinArena: Harnessing the collective intelligence of agents in the wild to advance scienceEinsteinArena is a platform where AI agents collaborate and compete on open math problems. AI agents on EinsteinArena have already set 11 new state-of-the-art results on open math problems — including→24 Apr 2026Accelerate RL rollouts by up to 50% with distribution-aware speculative decodingThis article describes a technique for accelerating reinforcement learning (RL) rollouts using distribution-aware speculative decoding, which can achieve up to 50% speedup improvements. The method lik
TechniqueFine-tuning3 recent entries23 Jul 2026The production platform for open-weight AI inferenceOpenAI has updated its inference platform to give users full control over performance, cost, and quality without building their own stack—models go live in minutes and support multiple deployments beh→11 Sept 2026Together AI expands fine-tuning service with more models, live metrics, and finer controlsTogether Fine-Tuning adds the latest open-weight models, live experiment tracking, Expert LoRA, early stopping, tokenized dataset previews, pre-flight validation, and lower training prices on selected→23 Sept 2026How to train your own Jev for $17We just launched our own Jev-like classifier, together/Tev1-4B-experimental, on top of Qwen3.5 4B on Together’s serverless platform. In this blog post we’ll show you how to fine-tune your own version!
TechniqueMultimodal4 recent entries24 Apr 2026Accelerate RL rollouts by up to 50% with distribution-aware speculative decodingThis article describes a technique for accelerating reinforcement learning (RL) rollouts using distribution-aware speculative decoding, which can achieve up to 50% speedup improvements. The method lik→28 Apr 2026Together AI Brings NVIDIA Nemotron 3 Nano Omni to Developers on Day 0Together AI announced immediate availability of NVIDIA's Nemotron 3 Nano Omni model to developers through its platform on the day of its release. The Nemotron 3 Nano Omni is a lightweight multimodal m→2 Jun 2026Serving MiniMax-M3 for efficient inference: Unlocking 1M-Token Context and Multimodality Without RegretsMiniMax-M3 is a large language model capable of handling 1 million token contexts and multimodal inputs while maintaining efficient inference performance. Together AI's blog post discusses techniques →29 Jul 2026Configuring Dedicated Model InferenceThe Together AI platform’s dedicated inference architecture consists of three immutable entities: **configs** (engine, GPU type/count, parallelism and optimization profile), **deployments** (a specifi