K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling

arXiv:2606.10820v2 Announce Type: replace-cross Abstract: Autoregressive (AR) language modeling is the dominant paradigm for text generation, yet its sequential token-by-token decoding makes inference memory-bound and inefficient. Existing acceleration approaches, such as speculative decoding and diffusion language models, can yield speedups...

Läs hela artikeln hos källan.