pith. sign in

Neurlz: An online neural learning-based method to enhance scientific lossy compression

3 Pith papers cite this work. Polarity classification is still indexing.

3 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 2 cs.DC 1

years

2026 3

verdicts

UNVERDICTED 3

roles

background 1

polarities

background 1

representative citing papers

A Geometric Lens on Physics-Aligned Data Compression

cs.LG · 2026-06-02 · unverdicted · novelty 6.0

Develops a local tangent-space rate-distortion theory and eigenspace-overlap diagnostic showing when physics-aligned compression necessarily degrades standard fidelity due to misaligned sensitivity directions.

ANTIC: Adaptive Neural Temporal In-situ Compressor

cs.LG · 2026-04-10 · unverdicted · novelty 6.0 · 3 refs

ANTIC reduces storage for large-scale PDE simulations by orders of magnitude through adaptive temporal snapshot selection combined with continual neural-field residual compression while preserving physics accuracy.

citing papers explorer

Showing 3 of 3 citing papers.

  • PackSELL: A Sparse Matrix Format for Precision-Agnostic High-Performance SpMV cs.DC · 2026-04-15 · unverdicted · none · ref 14

    PackSELL packs delta-encoded indices and values into single words with tunable bit allocation, delivering up to 1.63x faster FP16 SpMV and FP32-accurate performance exceeding FP16 cuSPARSE while reducing memory traffic.

  • A Geometric Lens on Physics-Aligned Data Compression cs.LG · 2026-06-02 · unverdicted · none · ref 23

    Develops a local tangent-space rate-distortion theory and eigenspace-overlap diagnostic showing when physics-aligned compression necessarily degrades standard fidelity due to misaligned sensitivity directions.

  • ANTIC: Adaptive Neural Temporal In-situ Compressor cs.LG · 2026-04-10 · unverdicted · none · ref 41 · 3 links

    ANTIC reduces storage for large-scale PDE simulations by orders of magnitude through adaptive temporal snapshot selection combined with continual neural-field residual compression while preserving physics accuracy.