3 accepted papers
We present Cacheback Decoding, a training-free and model-agnostic speculative decoding method that exploits the locality in language to accelerate Large Language Model (LLM) inference.Cacheback leverages only Least Recently Used (LRU) cache tables of token n-grams to generate draft sequences.Cacheba
Cross-domain sequential recommendation (CSR) has garnered significant attention. Current federated frameworks for CSR leverage information across multiple domains but often rely on user alignment, which increases communication costs and privacy risks. In this work, we propose FedCSR, a novel federat…
The Southeast Asia frog (Euphlyctis hexadactylus), a natural jumping expert in water, demonstrates exceptional jumping capability by contracting its leg muscles and coordinating its flippers to propel itself out of water, significantly aiding its hunting activities. This bionic behavior serves as a