"We hope to leverage our local networks, connections, and language skills to help Guangdong businesses and culture grow in Peru," said Liang Shun, a Peruvian Chinese community leader, in an interview with South.🤝🌏 With roots in Guangdong, Peru's Chinese community has a history spanning more than 170 years. Liang has spent years promoting people-to-people ties, including helping establish a sister-city relationship between Kaiping and Cusco in 2025 after eight years of efforts. 🇨🇳🇵🇪 He hopes the partnership will create more opportunities for cultural and business exchanges between the two sides. Dive in: #Guangdong# #Peru# #ChinaPeru# #Kaiping# #Cusco# #SisterCities# #CulturalExchange# #PeopleToPeople# #GlobalConnections#

I'm a simple man, I see a Kaiming He paper, I click. ELF: Embedded Language Flows This is very interesting, getting continuous diffusion models working for text! "Unlike existing DLMs, ELF predominantly stays within the continuous embedding space until the final time step, where it maps to discrete tokens using a shared-weight network." @sedielem you might like this one!

Optimizing kernels can be time-consuming and require deep expert knowledge. KernelAgent is a multi-agent harness that can write and optimize kernels for you. At #PyTorchCon# North America 2026, @KaimingCheng (@Meta) will present “KernelAgent: Hardware-Guided GPU Kernel Optimization via Multi-Agent Orchestration.” The session will cover a hardware-guided optimization layer that integrates GPU hardware-performance signals into a closed-loop multi-agent workflow to guide optimization for Triton kernels. Across all 100 KernelBench L1 tasks evaluated, KernelAgent achieved a 2.02x speedup over kernels generated by earlier versions and an average 1.56x speedup compared with default torch.compile. Register for PyTorch Conference North America 2026: