Kyutai Releases Voice of Reason: A Speech-Native Model that Solves Spoken Math with Reinforcement Learning

Kyutai Releases Voice of Reason: A Speech-Native Model that Solves Spoken Math with Reinforcement Learning Kyutai has released Voice of Reason, a set of 2 open-weight speech-to-speech models built on GLM-4-Voice-9B. According to the release, supervised fine-tuning and reinforcement learning lift spoken GSM8K accuracy from 27.3% to 77.1%. Key Highlights [...]

Read More

Hierarchical NeRF with JAX3D for Volumetric Rendering, Novel-View Synthesis, and 3D Reconstruction

Hierarchical NeRF with JAX3D for Volumetric Rendering, Novel-View Synthesis, and 3D Reconstruction In this tutorial, we build an end-to-end hierarchical Neural Radiance Field (NeRF) using JAX, Flax, Optax, and the volume-rendering primitives provided by jax3d. Building a Synthetic Multi-View Dataset We first construct a synthetic multi-view dataset from an analytic [...]

Read More

Cohere Releases North Small Translate: A 218B MoE Translation Model That Scores 83.6 on WMT26 Across 50 Languages

Cohere Releases North Small Translate: A 218B MoE Translation Model That Scores 83.6 on WMT26 Across 50 Languages Cohere has released North Small Translate, an open-weight Mixture-of-Experts model built for machine translation across 50 languages. Model Architecture and Scale The model uses 25B of its 218B parameters per token, reflecting [...]

Read More
Mi
Mi
AI Assistant
Mi
Hi! 👋 How can I help you today?
Mi
Powered by MAKER-ai