Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini Paper • 2605.27295 • Published 4 days ago • 17
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence Paper • 2605.26494 • Published 4 days ago • 31
FastKernels: Benchmarking GPU Kernel Generation in Production Paper • 2605.23215 • Published 8 days ago • 5
TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks Paper • 2605.22535 • Published 9 days ago • 9
Nautilus Compass: Black-box Persona Drift Detection for Production LLM Agents Paper • 2605.09863 • Published 19 days ago • 1