:
4 articles on SOTA Papers
Hybrid Mamba MoE Trades Dense Scale for Throughput
Soofi S activates 3B of 30B parameters per token and matches larger open models while reaching 4.8k TPS/GPU at 40K context.
Jul 29, 20265 min2607.09424
OmniDreams Runs Generative AV Simulation in Real Time
A Cosmos-derived causal diffusion model uses simulator state, action cues, and a streaming KV cache to render 704×1280 rollouts at 68–105 FPS.
Jul 28, 20265 min2606.03159 Code available
ACE-Brain Extends Spatial Models Into Closed-Loop Robot Agents
An 8B backbone couples perception, planning, action, and progress estimation, improving 14 of 18 spatial benchmarks over ACE-Brain-0.
Jul 12, 20265 min2607.04426