3 accepted papers
As larger language models deliver stronger capabilities, their autoregressive inference becomes increasingly expensive. *Speculative decoding* accelerates generation by letting a fast draft propose tokens that the target model verifies in parallel. Yet under sampling ($T>0$), observed speedups consi…
Recent advancements in Audio-Video Large Language Models (AV-LLMs) have enhanced their capabilities in tasks like audio-visual question answering and multimodal dialog systems. Video and audio introduce an extended temporal dimension, resulting in a larger key-value (KV) cache compared to static ima
Scaling up visual autoregressive models improves generation quality but incurs substantial inference costs. Mixture-of-Experts (MoE) architectures mitigate this issue through sparse activation and have proven effective in large language models. However, training MoE models from scratch remains prohi…