pith. sign in

Available: https://arxiv.org/abs/2411.06084

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

2 Pith papers citing it

years

2026 2

verdicts

UNVERDICTED 2

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.

The Thermodynamic Costs of Simple Linear Regression

cond-mat.stat-mech · 2026-05-18 · unverdicted · novelty 5.0

Thermodynamic lower bounds are approximated for exact and SGD linear regression, producing energy-aware scaling laws for optimal training dataset size given a target generalization error.

citing papers explorer

Showing 2 of 2 citing papers.

  • ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression cs.LG · 2026-05-30 · unverdicted · none · ref 35

    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.

  • The Thermodynamic Costs of Simple Linear Regression cond-mat.stat-mech · 2026-05-18 · unverdicted · none · ref 82

    Thermodynamic lower bounds are approximated for exact and SGD linear regression, producing energy-aware scaling laws for optimal training dataset size given a target generalization error.