43 citations · 52 across the 8 of their papers we have counts for
Showing 2025Show all
2 papers · 1 filter
cs.CL2025
Capacity Matters: a Proof-of-Concept for Transformer Memorization on Real-World Data
Anton Changalidis, Aki Härmä
This paper studies how the model architecture and data configurations influence the empirical memorization capacity of generative transformers. The models are trained using synthet…
cs.AI2025★ 6 cited
Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models
Anastasiia Grishina, Vadim Liventsev, Aki Härmä +1
Program synthesis with Large Language Models (LLMs) suffers from a "near-miss syndrome": the generated code closely resembles a correct solution but fails unit tests due to minor e…