2 papers
cs.AI2026
SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation
Soumia Bouyahiaoui, Manel Kara laouar, Aicha Boutorh +1
Large Language Models (LLMs) generate text autoregressively, relying on a key-value (KV) cache whose memory footprint grows linearly with context length, creating a major bottlenec…
cs.LG2025
DuaDeep-SeqAffinity: Dual-Stream Deep Learning Framework for Sequence-Only Antigen-Antibody Affinity Prediction
Aicha Boutorh, Soumia Bouyahiaoui, Sara Belhadj +2
Predicting the binding affinity between antigens and antibodies is fundamental to drug discovery and vaccine development. Traditional computational approaches often rely on experim…