Diffusion large language models (dLLMs) generate tokens in parallel via iterative denoising, but their bidirectional attention prevents the KV caching used by autoregressive models and recomputes the full attention map at every step, incurring quadratic per-step cost. Existing sparse attention methods for dLLMs constru...
Zhi-Chen Zeng, Xi-Chong Zhang, Jun-Pan Wu et al.· 0 citations
It is argued that, in dynamic long-horizon interactions, memory is not a static collection of facts but a lifecycle of explicit operations, including remembering, forgetting, updating, reflecting, and their compositions, which reveal that current systems remain far from uniformly reliable.
Xixuan Hao, Zeyu Zhang, Zehao Lin et al.· arXiv.org· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.