Back to AI Lab
Running
Research papers, repositories, and articles about running
Showing 2 of 2 items
OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
OmniMem adds an external memory system to long-video generators so they can re-use past details instead of re-encoding full histories. It adapts which frames to keep, letting models generate longer, more coherent clips under fixed compute. If you’re chasing hour-scale video worlds, this is a template for managing context.
Lin Zhao, Yushu Wu
Kernel Foundry: A Diagnosis-Driven Evolutionary Kernel Optimizer with Multi-Experts
Kernel Foundry evolves GPU kernels using feedback from correctness checks and performance diagnostics instead of blind search. It reaches 100% correctness on a benchmark and beats hand-tuned baselines. If you’re fighting GPU bottlenecks, this hints that AI-guided kernel search is starting to work in practice.
Zixuan Huang, Da Chen