lunes, 16 de noviembre de 2026

Heat-kernel context compression for transformer representations using graph diffusion Shashank Reddy Vadyala, Sai Nethra Betgeri

https://www.academia.edu/journals/academia-ai-and-applications/articles?source=journal-top-nav Introduction: Long contexts often contain geometrically redundant internal representations. Heat Kernel Context Compression (HKCC) is a training-free representation–compression method for transformer systems in which internal embeddings and attention logits can be modified.

No hay comentarios: