GPU-Based Global Optimization for Large-Scale Nonlinear Problems
Discover a GPU-powered method for rigorous global optimization of large-scale nonlinear functions, ensuring accurate minima in high-dimensional spaces.
Optimized AI Model Partitioning for Faster Edge Split Learning
Discover efficient AI model partitioning methods to reduce training delays and boost split learning performance over edge networks.
HSG-12M: Large-Scale Spatial Multigraphs Dataset for Quantum Physics
Discover HSG-12M, a vast dataset of spatial multigraphs from non-Hermitian crystal energy spectra, enabling advanced AI-driven quantum physics research.
SpecBranch: Boosting LLM Speed with Hybrid Speculative Decoding
Discover SpecBranch, a novel hybrid speculative decoding method that improves large language model inference speed by up to 4.5× with rollback-aware branch...
Boost Text-to-Image Diffusion with Split-Text Conditioning
Improve text-to-image diffusion transformers using split-text conditioning for better semantic understanding and image generation accuracy.