LongCat 2.0 is Meituan's 1.6T-parameter MoE model with a native 1M-token context, trained entirely on domestic AI ASIC ...
KokkosKernels implements local computational kernels for linear algebra and graph operations, using the Kokkos shared-memory parallel programming model. "Local" means not using MPI, or running within ...
M3 demonstrates that the next phase of agent development will not just be driven by larger datasets, but by efficient architectural choices.
a mobile phone's screen showing the logo of Chinese AI MiniMax in Beijing on January 21, 2026. WANG Zhao/Getty Images Shanghai-based MiniMax launched its M3 foundation model on Monday, June 1, 2026, ...
Abstract: This letter addresses the problem of robust adaptive beamforming for linear arrays impaired by gain-phase errors. We propose a joint calibration and estimation method based on block sparse ...
President Donald Trump’s newly released plan to shield voters from rising electricity costs tied to the data center boom faces a host of questions — most fundamentally: Does it have any chance of ...
SpaSM is a software library devoted to sparse gaussian elimination modulo a small prime p. It is available under the General Public License Version 3 or later (GPLv3+). This is "research-quality" ...
Abstract: Block compressed sensing (or sparse recovery) and its performance bound, i.e., conditions that guarantee reconstruction of the original sparse vector, have been widely studied. Most ...
The range at which predators detect prey strongly influences prey encounter rates and therefore the energy gained from foraging: predators with small sensory volumes require denser prey to meet their ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results