“Impressive level of openness”: Xiaomi goes way beyond the usual open-weight playbook with MiMo-V2.6

The New Stack (AI)
Read the full article
Xiaomi launched MiMo-V2.6-Pro, a trillion-parameter open-weight AI model with a one-million-token context window supporting text, images, audio, and video. The company publicly livestreamed its reinforcement learning training, revealing $3.5 million in RL costs, highlighting unprecedented transparency.

More on this story


More in LLM & Text Generation

PyTorch Conference 2026: Google and Meta Open-Source TorchTPU for Native PyTorch on TPUs

InfoQ (AI, ML & Data)

Researchers from Stanford and UC Berkeley Introduce TokenGate: Token-Gated Attention Makes Long-Context Prefill Up to 11.3x Faster

MarkTechPost

From overeliciting to undereliciting LLM propensities in just a few months

LessWrong