4 citations · 6 across the 11 of their papers we have counts for
4 papers · 1 filter
EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory
Hongru Cai, Ran Wei, Wenjie Wang +4
Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language models (LLMs) with limited additi…
Kobayashi visibility of strictly convex domains
Nikolai Nikolov, Amar Deep Sarkar
We show that any bounded strictly convex domain in , endowed with the Kobayashi distance, is visible.
A Canonical Positive Definite Kernel Associated with the -Bergman Kernel
Sahil Gehlawat, Aakanksha Jain, Amar Deep Sarkar
Let and . The -Bergman kernel , introduced by Bao and Guan, generalizes the classical Bergman kernel by replacing the point ev…
On the exponential convergence of Kobayashi geodesics in strongly convex domains
Kingshook Biswas, Sanjoy Chatterjee, Amar Deep Sarkar
In this paper, we have proved a quantitative version of the approaching geodesic property for certain convex domains. We have proved that that if is a bou…