Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Active Causal Experimentalist (ACE): Learning Intervention Strategies via Direct Preference Optimization
Patrick Cooper, Alvaro Velasquez
Discovering causal relationships requires controlled experiments, but experimentalists face a sequential decision problem: each intervention reveals information that should inform…
cs.LG2026
KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference
Alireza Nadali, Patrick Cooper, Ashutosh Trivedi +1
We introduce KV-Fold, a simple, training-free long-context inference protocol that treats the key-value (KV) cache as the accumulator in a left fold over sequence chunks. At each s…