3 papers
cs.SE2026
SemChunk-C: Semantic Segmentation for C Code
Boris Nazarov, Darya Frolova, Shaked Leibzirer +1
Semantic segmentation of code written in a C-family language remains a challenging problem, due to the language's complex syntax, macro expansion, and irregular structural patterns…
cs.CL2025
Attention Condensation via Sparsity Induced Regularized Training
Eli Sason, Darya Frolova, Boris Nazarov +1
As the context window expands, self-attention increasingly dominates the transformer's inference time. Therefore, accelerating attention computation while minimizing performance de…
cs.CL2025
Rethinking Data: Towards Better Performing Domain-Specific Small Language Models
Boris Nazarov, Darya Frolova, Yackov Lubarsky +2
Fine-tuning of Large Language Models (LLMs) for downstream tasks, performed on domain-specific data has shown significant promise. However, commercial use of such LLMs is limited b…