arXiv:2012. 01982v3 Announce Type: replace Abstract: This paper proposes a standard way to represent sparse tensors.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
arXiv:2606. 08565v1 Announce Type: cross Abstract: Tensor networks provide efficient representations for compressing large neural networks.
arXiv:2604. 09558v2 Announce Type: replace-cross Abstract: With the widening gap between compute and memory operation latencies, data movement optimizations have become increasingly important for DNN compilation.
arXiv:2608. 17135v1 Announce Type: cross Abstract: Tensor networks are powerful formats for compressing large-scale data.
arXiv:2606. 03465v1 Announce Type: cross Abstract: Post-training compression is essential for deploying large language models (LLMs) under tight resource constraints.
Post-training compression is essential for deploying large language models (LLMs) under tight resource constraints. Tensor decompositions have emerged as a promising direction, offering compact parameterizations well suited to Transformer weight structures.
The paper investigates the block-sparse featurizer (BSF), a model that uses small subspaces as atomic units instead of single directions, aiming to capture features on low-dimensional manifolds common in vision. It identifies that BSF still exhibits classic sparse autoencoder failure modes such as feature splitting and composition. The authors propose architectural improvements, notably a Tournament Top‑K selection rule, which markedly reduces feature splitting, and they extend the block concept to a crosscoder framework.