#parameter-pruning News & Analysis

3 articles tagged with #parameter-pruning. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AIBullisharXiv – CS AI · Jun 117/10

🧠

Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering

Researchers present a novel compression technique for speech foundation models using parameter clustering and k-means pruning without requiring training data or fine-tuning. The method demonstrates significant performance improvements over traditional magnitude-based pruning on HuBERT-large and Whisper-large-v3, with 27-59% relative WER reductions at various sparsity levels.

AINeutralarXiv – CS AI · Feb 277/106

🧠

RaPA: Enhancing Transferable Targeted Attacks via Random Parameter Pruning

Researchers propose Random Parameter Pruning Attack (RaPA), a new method that improves targeted adversarial attacks by randomly pruning model parameters during optimization. The technique achieves up to 11.7% higher attack success rates when transferring from CNN to Transformer models compared to existing methods.

AINeutralarXiv – CS AI · Jun 26/10

🧠

ProbeScale: Probing Analysis to Optimize Neural Scaling Laws for Efficient Small Language Model Inference

Researchers introduce ProbScale, a framework that combines neural scaling laws with probing analysis to identify parameter-efficient subnetworks in Small Language Models. The method achieves 5-10x parameter reduction while maintaining 95-98% performance on downstream tasks, addressing deployment challenges for resource-constrained environments.