EfficientXpert: Efficient Domain Adaptation for Large Language Models via Propagation-Aware Pruning

Name: EfficientXpert: Efficient Domain Adaptation for Large Language Models via Propagation-Aware Pruning
Uploaded: 2026-10-10T12:18:28.011753+00:00
Duration: 260 s
Description: EfficientXpert proposes a lightweight framework combining propagation-aware pruning with an efficient adapter update algorithm for LLMs. It creates sparse, domain-adapted models that maintain near-dense performance at low sparsity levels by reducing memory and computation during inference.

EfficientXpert proposes a lightweight framework combining propagation-aware pruning with an efficient adapter update algorithm for LLMs. It creates sparse, domain-adapted models that maintain near-dense performance at low sparsity levels by reducing memory and computation during inference.

Open the full episode