pith. sign in

arXiv preprint arXiv:2505.21895 , year=

Compressing Sine-Activated Low-Rank Adapters through Post-Training Quantization , author= · arXiv 2505.21895

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
read on arXiv browse 1 citing papers

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

clear filters

representative citing papers

ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression

cs.LG · 2026-05-30 · unverdicted · novelty 6.0

ProjQ constrains post-training quantization noise to a low-rank manifold through orthogonal subspace projection, enabling better compensation by LoRA adapters and preserving greater model plasticity than standard PTQ.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression cs.LG · 2026-05-30 · unverdicted · none · ref 48

    ProjQ constrains post-training quantization noise to a low-rank manifold through orthogonal subspace projection, enabling better compensation by LoRA adapters and preserving greater model plasticity than standard PTQ.