Applications
TensorHub: Rethinking AI Model Hub with Tensor-Centric Compression
arXiv:2604.17104v1 Announce Type: cross Abstract: Modern AI models are growing rapidly in size and redundancy, leading to significant storage and distribution challenges in model hubs. We present Tens
arXiv:2604.17104v1 Announce Type: cross Abstract: Modern AI models are growing rapidly in size and redundancy, leading to significant storage and distribution challenges in model hubs. We present TensorHub, a tensor-centric system for reducing storage overhead through fine-grained deduplication and compression. TensorHub leverages tensor-level fingerprinting and clustering to identify redundancy across models without requiring annotations. Our design enables efficient storage reduction while preserving model usability and performance. Experiments on real-world model repositories demonstrate substantial storage savings with minimal overhead.
Related
- Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation
- Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes
- deCIFer: Crystal Structure Prediction from Powder Diffraction Data using Autoregressive Language Models
Source: arXiv cs.LG | 2026-04-21