Iterative LLM-NAS is equivalent to a parametric cross-entropy method with proven monotonic quality improvement, geometric convergence of elite probability, and a closed-form proxy reliability rho_S = (6/pi) arcsin(rho_P(SNR)/2), partially confirmed on 3300 architectures.
hub Canonical reference
arXiv preprint arXiv:2301.08727 (2023)
Canonical reference. 80% of citing Pith papers cite this work as background.
14
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 4
method 1
citation-polarity summary
representative citing papers
Meta-learning a Convolutional Neural Process to infer neural architecture performance from context-target splits on synthesized tasks improves top-K ranking and achieves state-of-the-art selection on NAS-Bench-101 and NAS-Bench-201 with limited samples.
SWAP-Score evaluates neural networks without training by quantifying sample-wise activation patterns, achieving high correlation with true performance on CIFAR-10 for CNNs and GLUE for Transformers while enabling fast NAS.
Fine-tuned 7B LLMs generating unified diffs for neural architecture refinement achieve 66-75% valid rates and 64-66% mean first-epoch accuracy, outperforming full-generation baselines by large margins while cutting output length by 75-85%.
SDTI lets models identify the correct target variable in datasets in a zero-shot setting using standard neural networks, beating baselines by 14% F1 on synthetic benchmarks.
OPT-BENCH and OPT-Agent evaluate LLM self-optimization in large search spaces, showing stronger models improve via feedback but stay constrained by base capacity and below human performance.
PBT-NCA evolves populations of Petri Dish NCAs under novelty-plus-diversity pressure, yielding sustained lifelike waves, spore-like colonization, and migrating macro-structures at the edge of chaos.
Module-switching defense disrupts backdoors more effectively than weight averaging with fewer models and remains robust even when some models share the same backdoors.
A HW-NAS framework executable on resource-limited embedded devices generates optimized CNNs for low-end MCUs and reports state-of-the-art human-recognition accuracy on the Visual Wake Word dataset.
A genetic-algorithm framework searches 19 photonic hybrid-network design choices and reports 99.44% (Digits) and 98.78% (MNIST) validation accuracy in simulation.
A survey that proposes a taxonomy for universal time-series representation learning and reviews existing deep learning studies along with experimental setups.
A literature review that categorizes and compares NAS techniques for GANs, noting benefits of evolutionary and gradient-based methods along with needs for better metrics and diverse datasets.
A survey of Spiking Neural Network architecture search techniques viewed through a hardware/software co-design lens.
citing papers explorer
-
Convergence Theory for Iterative LLM-Based Neural Architecture Search: A Parametric Cross-Entropy Framework with Closed-Form Proxy Reliability
Iterative LLM-NAS is equivalent to a parametric cross-entropy method with proven monotonic quality improvement, geometric convergence of elite probability, and a closed-form proxy reliability rho_S = (6/pi) arcsin(rho_P(SNR)/2), partially confirmed on 3300 architectures.
-
From Regression to Inference: Meta-Learning Predictors for Neural Architecture Search
Meta-learning a Convolutional Neural Process to infer neural architecture performance from context-target splits on synthesized tasks improves top-K ranking and achieves state-of-the-art selection on NAS-Bench-101 and NAS-Bench-201 with limited samples.
-
Zero-Shot Neural Network Evaluation with Sample-Wise Activation Patterns
SWAP-Score evaluates neural networks without training by quantifying sample-wise activation patterns, achieving high correlation with true performance on CIFAR-10 for CNNs and GLUE for Transformers while enabling fast NAS.
-
Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs
Fine-tuned 7B LLMs generating unified diffs for neural architecture refinement achieve 66-75% valid rates and 64-66% mean first-epoch accuracy, outperforming full-generation baselines by large margins while cutting output length by 75-85%.
-
Self-Directed Task Identification
SDTI lets models identify the correct target variable in datasets in a zero-shot setting using standard neural networks, beating baselines by 14% F1 on synthetic benchmarks.
-
OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces
OPT-BENCH and OPT-Agent evaluate LLM self-optimization in large search spaces, showing stronger models improve via feedback but stay constrained by base capacity and below human performance.
-
Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training
PBT-NCA evolves populations of Petri Dish NCAs under novelty-plus-diversity pressure, yielding sustained lifelike waves, spore-like colonization, and migrating macro-structures at the edge of chaos.
-
Defending against Backdoor Attacks via Module Switching
Module-switching defense disrupts backdoors more effectively than weight averaging with fewer models and remains robust even when some models share the same backdoors.
-
Running hardware-aware neural architecture search on embedded devices under 512MB of RAM
A HW-NAS framework executable on resource-limited embedded devices generates optimized CNNs for low-end MCUs and reports state-of-the-art human-recognition accuracy on the Visual Wake Word dataset.
-
Q-PhotoNAS: Hybrid Quantum Neural Architecture Search Framework on Photonic Devices
A genetic-algorithm framework searches 19 photonic hybrid-network design choices and reports 99.44% (Digits) and 98.78% (MNIST) validation accuracy in simulation.
-
Universal Time-Series Representation Learning: A Survey
A survey that proposes a taxonomy for universal time-series representation learning and reviews existing deep learning studies along with experimental setups.
-
Neural Architecture Search for Generative Adversarial Networks: A Comprehensive Review and Critical Analysis
A literature review that categorizes and compares NAS techniques for GANs, noting benefits of evolutionary and gradient-based methods along with needs for better metrics and diverse datasets.
-
Spiking Neural Network Architecture Search: A Survey
A survey of Spiking Neural Network architecture search techniques viewed through a hardware/software co-design lens.
- On Efficient Variants of Segment Anything Model: A Survey