5 papers
GeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression
Baher Mohammad, Ammar Ali, Stamatios Lefkimmiatis
Transformer architectures exhibit cross-layer redundancies, yet post-training compression pipelines typically optimize layers in isolation or rely on heuristic grouping strategies…
COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression
Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip +3
Post-training compression of transformer models commonly relies on truncated singular value decomposition (SVD) strategies leading to low-rank approximations of the original model…
ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression
Ammar Ali, Baher Mohammad, Denis Makhov +3
We present ROCKET, a training-free model compression method that achieves state-of-the-art performance in comparison with factorization, structured-sparsification and dynamic compr…
Speak, Edit, Repeat: High-Fidelity Voice Editing and Zero-Shot TTS with Cross-Attentive Mamba
Baher Mohammad, Magauiya Zhussip, Stamatios Lefkimmiatis
We introduce MAVE (Mamba with Cross-Attention for Voice Editing and Synthesis), a novel autoregressive architecture for text-conditioned voice editing and high-fidelity text-to-spe…
Cross-level Requirement Traceability: A Novel Approach Integrating Bag-of-Words and Word Embedding for Enhanced Similarity Functionality
Baher Mohammad, Riad Sonbol, Ghaida Rebdawi
Requirement traceability is the process of identifying the inter-dependencies between requirements. It poses a significant challenge when conducted manually, especially when dealin…