WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive

arXiv:2603.22300v1 Announce Type: cross Abstract: Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce

arXiv:2603.18567v1 Announce Type: cross Abstract: Large language models incur high inference latency due to sequential autoregressive decoding. Speculative decoding alleviates

arXiv:2607.13330v1 Announce Type: cross Abstract: Diffusion-based text-to-audio generative models such as AudioLDM achieve high perceptual quality and strong semantic consistency;

arXiv:2604.05887v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have advanced unified reasoning over text, images, and videos, but their inference is

arXiv:2604.00004v1 Announce Type: cross Abstract: The extension of context windows in Large Language Models is typically facilitated by scaling positional encodings followed by

<!-- SC_OFF --><div class="md"><p>Abstract: </p> <p>Modern Large Language Models (LLMs) rely on Transformer self-attention, which scales quadratically with sequence length. Recent