The MiMo-V2.6 series is introduced, an omni-modal family that pushes the frontier of model intelligence by scaling RL compute by building infrastructure for mixed-task agentic RL, including a unified trajectory representation, high-concurrency multi-framework rollout, decoupled control and data planes, and training-inf...
Xiao-Zhen Qiao, Zi-Yue Hua, Zi-Rui Ou et al.· 10 citations
On an 80B-A3B MoE model, HySparse2 outperforms HySparse and Hybrid SWA on long-context retrieval and multi-turn agentic tasks, while substantially reducing prefill computation and KV-cache storage.
This work presents TileSight, a tile-centric performance-modeling tool that elevates the tile from a programming primitive to an analysis primitive, and selects tile configurations competitive with strong vendor and expert baselines.
Zhiwen Mo, Yu Cheng, Lei Wang et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.