2 papers
cs.LG2026
CRISP: Cliff-awaRe Input-adaptive Sparse Prefilling with Structural-Mass-Motivated Routing
Huu Huy Nguyen, Chien Van Nguyen, Franck Dernoncourt +4
The attention prefilling phase of long-context LLM inference scales quadratically, making self-attention a severe computational bottleneck. Traditional sparse attention methods mit…
cs.LG2026
Synthetic Persona Pretraining: Alignment from Token Zero
Julian Minder, Viktor Moskvoretskii, Raghav Singhal +12
As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today, alignment, and the assistant…