Sequential Functional Structured Tucker Compression for Large Language Model Attentions
cs.CL, cs.AI, stat.ML
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models
- AdaSVD: Adaptive Singular Value Decomposition for Large Language Models
- Accelerating Sparse Deep Neural Networks
- COALA: Numerically Stable and Efficient Framework for Context-Aware Low-Rank Approximation
- AA-SVD : Anchored and Adaptive SVD for Large Language Model Compression
- QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models
- TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition
- ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models
- Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression
- Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models
- Large Language Model Compression with Global Rank and Sparsity Optimization
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering