AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

MoLoRA: Boosting LLM-based End-to-end Speech Translation with Mixture of Low-rank Experts

Hao Zhang, Yaqi Chen, Nianwen Si, XuKui Yang, Wenlin Zhang, Dan Qu

AAAI 2026 · Large language models › Instruction and fine-tuning · approach: Low-rank adaptation variants · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace single LoRA with mixture of low-rank experts (ablation)LoRA · MuST-C 8 pairs avgBLEU: 27.9 -> 32.2Improved
replace full fine-tuning with MoLoRA (ablation)Full fine-tuning · MuST-C 8 pairs avgBLEU: 31.9 -> 32.2Improved
add sentence-level representation (MGRF) (ablation)MoLoRA · MuST-C En-DeBLEU: 30.4 -> 30.8Improved
use cross-attention multi-granularity fusion instead of simple summation (ablation)MoLoRA · MuST-C En-DeBLEU: 30.5 -> 30.8Improved
add shared expert (ablation)MoLoRA · MuST-C En-DeBLEU: 30.6 -> 30.8Improved
add load balancing loss (ablation)MoLoRA · MuST-C En-DeBLEU: 30.6 -> 30.8Improved
increase LoRA rank r (ablation)LoRA · MuST-C En-DeBLEUNo clear effect
increase number of routed experts N' up to 4 (ablation)MoLoRA · MuST-C En-DeBLEUImproved
increase routed experts beyond 4 (ablation)MoLoRA · MuST-C En-DeBLEUHurt
use end-to-end MoLoRA instead of cascaded ST (ablation)MoLoRA · MuST-C En-DeBLEU: 29.5 -> 30.8Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy