2 papers
cs.LG2026
BF1: A Causal Dyadic Sparse-Attention Retrofit for Efficient Long-Context Transformers
Hina Dixit
Dense causal attention remains expensive at long context even when implemented with highly optimized exact kernels. We study BF1, a deterministic block-aligned dyadic sparse-attent…
cs.CR2026
Echelon: Auditable Aggregate-Only Language-Model Adaptation Across Privacy Boundaries
Hina Dixit, Punit Kumar, Irene Tenison +1
Cross-organization language-model adaptation increasingly faces hard governance constraints: in many deployments, device-level model state-parameters, activations, optimizer state,…