An independent developer has released DeepSeek-V4-Flash-0731-Latent-Reasoning, a 284B-parameter MoE model with a 35.7M-parameter reasoning head that performs latent reasoning in a 1024-dimensional spa…
Nicholai Mitchko, InterSystems' director of AI enablement, released DeepSeek-V4-Flash-0731-Latent-Reasoning, a self-hosted latent-reasoning model built on DeepSeek-V4-Flash that requires Blackwell-cla…
Developer Nick Mitchko released DeepSeek-V4-Flash-0731-Latent-Reasoning, a self-contained model that performs reasoning in latent space via a trained CoLaR head, with all weights in one Hugging Face r…
Nick Mitchko added a CoLaR (Compressed Latent Reasoning) head to DeepSeek Flash v4, enabling the model to reason in latent space with a learned stop criterion. In tests, the standard model pattern-mat…