2 papers
cs.DS2026
How to Train Your Filter: Should You Learn, Stack or Adapt?
Diandre Miguel Sabale, Wolfgang Gatterbauer, Prashant Pandey
Filters are ubiquitous in computer science, enabling space-efficient approximate membership testing. Since Bloom filters were introduced in 1970, decades of work improved their spa…
cs.LG2025
KV Cache Recycling to Expand Usable Context Capacity in Low Parameter LLMs
Prashant Pandey
Whether attention key value (KV) states computed for one prompt for a small LLM can be reused to accelerate inference on a new similar prompt, giving an increase to the space to it…