2 papers
cs.AI2026
SMat-Attention: Structured Long-Context Sequence Modeling
Emile Anand, Abdullah Ateyeh, Archer Wang +1
Long-context sequence models face a fundamental tradeoff: softmax attention uses flexible token-level interactions at quadratic cost, whereas linear attention obtains linear-time t…
cs.LG2026
Continuous Latent Contexts Enable Efficient Online Learning in Transformers
Emile Anand, Abdullah Ateyeh, Xinyuan Cao +1
Large language models (LLMs) exhibit a strong capacity for in-context learning: Given labeled examples, they can generate good predictions without parameter updates. However, many…