← Back to all news
arXiv Machine Learning By Kabir Dev Paul Baghel, Radu Timofte, Dmitry Ignatov

Curating Same-Family Neural Networks for LLM-Guided Model Improvement: A Controlled Case Study

Read the original on arXiv Machine Learning →

The study investigates whether a curated same-family neural network experiment can guide large language model (LLM)-based improvements for a low-performing target model under equal generation and evaluation budgets. Using TuneNNGen, an extension of NNGPT, the authors compare source-guided generation with target-only generation on CIFAR-10, SVHN, Imagenette, and CIFAR-100 datasets, achieving significant accuracy gains across these benchmarks. The results demonstrate that the benefits depend on source-target compatibility and LLM adaptation, rather than merely on stored source accuracy.

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.

Related stories

arXiv Machine Learning
Aug 19

Data-DPO: Direct Preference Optimization for Target Model Data Selection in LLM Post-Training

Data-DPO is a target model‑oriented supervised fine‑tuning data selection method that uses one‑step probing of the target model to generate pairwise data preferences, trains a lightweight reward model to capture these preferences, and then selects a training subset by combining target‑model preference, external quality scores, and marginal diversity. Experiments on Vision‑Flan and LLaVA‑CoT demonstrate that Data‑DPO consistently outperforms existing data selection baselines across multiple data budgets and even surpasses full data training performance.

By Peng Sun, Yi Yang, Antong Zhang, Chunxiao Li, Yanbo Wang, Dianbo Liu, xin chen, Kai Yu, Lu Chen, Tianfan Fu
llmsreinforcement-learningfine-tuning
More like this →
Hugging Face Trending Papers
Jul 13

Similarity-Guided Curriculum Fine-Tuning of LLMs for Neural Architecture Synthesis

Introduce a MinHash-based similarity scheduling framework that constructs a progressive curriculum over neural architecture code for LLM-based neural architecture search (NAS). Using 128-permutation MinHash signatures over normalised 7-gram source code shingles, we partition the reference pool into similarity bands and present them in increasing architectural heterogeneity, with the best LoRA adapter from each stage merged cumulatively into the backbone.

llmscomputer-visionfine-tuningbenchmarks
More like this →