Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
LoRA-Squeeze: Simple and Effective Post-Tuning and In-Tuning Compression of LoRA Modules
Ivan VuliÄ, Adam Grycner, Quentin de Laroussilhe +1
Despite its huge number of variants, standard Low-Rank Adaptation (LoRA) is still a dominant technique for parameter-efficient fine-tuning (PEFT). Nonetheless, it faces persistent…
cs.CL2025
Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching
Benjamin Minixhofer, Ivan VuliÄ, Edoardo Maria Ponti
Distillation has shown remarkable success in transferring knowledge from a Large Language Model (LLM) teacher to a student LLM. However, current distillation methods require simila…