Search papers, labs, and topics across Lattice.
EHV Power Transmission Company, China Southern Power Grid Co
2
3
5
The DeepSeek-V4.1-Flash model, a multimodal Mixture-of-Experts model with 552B backbone parameters and support for contexts of up to one million tokens, is introduced, substantially improving cost efficiency for agentic workloads and pushing the limits of KV cache compression.
