JavaScript 2025
Premiere 2025-10-30
Ensuring reliability in LLM predictions is challenging due to their probabilistic nature. This talk presents a fast, mathematically sound approach to evaluate model confidence in real-time using C++ compile-time numerical integration, optimizing AI inference reliability with minimal overhead.
Samsung Research
Tree ensemble methods (Random Forest, Gradient Boosting) are widely used in ML but can be inefficient in cloud-based, multi-threaded environments due to uneven workload distribution across heterogeneous CPU cores. This talk analyzes performance trade-offs in existing ONNX-based implementations, introduces a custom C++ wrapper for optimized task scheduling, and demonstrates a 4x speedup in...
Learn for free, join the best tech learning community
Event notifications, weekly newsletter
Access to all content
