Tensor decompositions face practical limits in large-scale LLM compression due to mismatch between assumed shared subspaces and heterogeneous model representations.
SoLA: Leveraging soft activation sparsity and low-rank decomposition for large language model compression
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression
Tensor decompositions face practical limits in large-scale LLM compression due to mismatch between assumed shared subspaces and heterogeneous model representations.