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. We evaluate the framework on OlympicCoder-7B within the LEMUR benchmark on CIFAR-10 image classification, generating N =15 candidate architec
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 50%sunrainyg/RandOpt →
- PossiblePossibly related (embedding) · 47%remete618/widemem-ai →
- PossiblePossibly related (embedding) · 47%deepset-ai/haystack →
- LinkedLinked via arxiv author · 85%Anujaya Vijayakumar →
“Similarity-Guided Curriculum Fine-Tuning of LLMs for Neural Architecture Synthesis”
- LinkedLinked via arxiv author · 85%Radu Timofte →
“Similarity-Guided Curriculum Fine-Tuning of LLMs for Neural Architecture Synthesis”
- LinkedLinked via arxiv author · 85%Dmitry Ignatov →
“Similarity-Guided Curriculum Fine-Tuning of LLMs for Neural Architecture Synthesis”