arXiv subjects

Dmitry Ignatov

Publications and source records attributed to Dmitry Ignatov.

At least 19 recordsLinked to original sources

arXiv2026

Device-First Feedback: Toward Mobile-Native LLM-Driven Neural Architecture Search

Deploying convolutional neural networks generated by large language models (LLMs) on real mobile hardware requires more than GPU validation accuracy: INT8 TensorFlow Lite export, delegate selection, and on-device latency jointly determine whether a model is usable. We present an automated mobile deployment pipeline that closes the loop from QLoRA fine-tuning of an architecture-generating LLM through GPU evaluation, INT8 export, and physical-device benchmarking to gated augmentation of the training corpus. The pipeline is fully scripted and runs cycle-by-cycle without manual intervention, with resume support after interruptions. We evaluate the same frozen protocol on two benchmarks, CIFAR-10 and CIFAR-100, on a Samsung SM-P613 tablet (seed 42, 20 models per cycle, cycles 0-6). On CIFAR-10, cycle 1 is gate-accepted and improves the mobile deployment score approximately 25.6x over the baseline with a mean quantized accuracy of 46.9%; later cycles raise GPU accuracy but fail the non-decreasing mobile gate. On CIFAR-100, the pre-QLoRA baseline retains the best mobile score; iterative rounds improve GPU accuracy (up to 26.2%) yet cannot surpass cycle 0 on-device, and the training pool stalls at 19 examples after the first accepted round. Together, the two studies show that closed-loop GPU fine-tuning does not guarantee monotonic mobile gains, especially on harder classification tasks, and that multi-dataset, on-device measurement is needed to stress-test deployment objectives. We release per-cycle metrics with 95% confidence intervals, all figures, and complete reproduction commands.

cs.CV↗

arXiv2026

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 architectures per epoch across six progressive fine-tuning steps. The curriculum achieves 60% peak success rate at the high-similarity level without post-processing repair. A 2*2 ablation at the most diverse level curriculum versus base model, with versus without partial interface repair reveals that without repair the base model (47% peak SR) substantially outperforms the curriculum model (7% SR), while adding partial repair brings both to 53% SR. This pattern is consistent with merge-level weight drift progressively erasing evaluator-interface priors, and suggests that interface repair and curriculum scheduling target distinct failure modes. We further report a cross-dataset transfer observation on SVHN, where direct base-model generation without curriculum warmup yields 27% peak SR at substantially lower accuracy (60.5%) than the CIFAR-10 equivalent, consistent with the increased synthesis difficulty of the unq-family anchor architecture.

cs.CV↗

arXiv2026

Systematic Evaluation of Learning Rate Scheduling Strategies Across Heterogeneous Architectures

Choosing a learning rate scheduling strategy is critical to neural network training, but manual selection is costly and rarely exhaustive. While classical AutoML approaches often treat the scheduler as a secondary hyperparameter, we systematically investigate its impact on classification accuracy across a diverse pool of architectures. We evaluated 30 representative architectures from convolutional and transformer families within the LEMUR neural network dataset. Through automated source-code injection, we applied 25 scheduler configurations across nine PyTorch families, evaluating a total of 3,938 model variants on CIFAR-10. Our best configuration achieved a top-1 accuracy of 86.45%, with 237 variants exceeding 80%. The results show that the choice of scheduler depends heavily on the architecture: CosineAnnealingWarmRestarts and CyclicLR consistently outperform basic decay strategies. The resulting accuracy landscape, contributed to the LEMUR nn-dataset, provides a practical reference for principled scheduler selection.

cs.LG↗

arXiv2026

LEMUR 2: Unlocking Neural Network Diversity for AI

Existing NAS benchmarks (e.g., NAS-Bench, NATS-Bench) cover only narrow, task-specific regions of the architectural design space and lack cross-domain or deployment-aware evaluation. LEMUR 2 introduces a large-scale, extensible framework unifying generative, evaluative, and deployment pipelines to unlock neural-network diversity. It comprises over 14,000 distinct architectures and more than 750,000 structured training records documenting model performance, hyperparameters, and task outcomes. These models were produced through AST-based code mutation, genetic and reinforcement-learning evolution, generation of fractal architectures, and synthesis guided by a Large Language Model (LLM). This includes deep models generated with the retrieval-augmented system NN-RAG, which derived and used architectural motifs from over 900 PyTorch modules extracted from public repositories. LEMUR 2 further employs NN-VR and NN-Lite pipelines for automated deployment and latency benchmarking on heterogeneous mobile and Unity-based VR platforms, providing real-device performance metadata. It spans multimodal tasks, image captioning, text-to-image synthesis, and language modeling, supporting cross-domain analysis of architectural transferability. By linking diverse architectures, tasks, and deployment data, LEMUR 2 provides the data foundation for LLM fine-tuning and coupling diverse architectural origins with large-scale, cross-platform empirical validation. This dataset defines a new basis for reproducible and data-driven AI design, advancing the emerging paradigm of LLM-driven AutoML and architectural generalization across modalities and hardware.

cs.LG↗

arXiv2026

Scaling Closed-Loop Feature Channel Configuration with LLMs

Promising initial results in closed-loop large-language-model-based channel-configuration search demonstrated that neural-network widths can be optimized directly through executable code generation and accuracy feedback. However, those results were obtained from a relatively sparse set of valid evaluations, leaving open whether the observed optimization behavior transfers to a denser sampling regime and whether additional architectural regularities emerge when more generated networks are evaluated. To test this, the same search setting is scaled to 250 candidate networks per fine-tuning cycle. The analysis covers 2000 generated candidates from 8 complete cycles, yielding 462 verified CIFAR-100 evaluations after task and metadata filtering. Per-cycle mean accuracy exhibits a positive linear trend with slope 9.87e-4 (p=0.043), while the high-performing frontier improves more strongly: the best observed accuracy increases from 0.3144 to 0.3676, and both the top-5 and top-10 cycle-level means exhibit positive trends. The scaled run also reveals improved parameter efficiency. The best model reaches 0.3676 with 11.8M parameters, compared with an early high-performing model at 0.3144 with 166.5M parameters. Beyond accuracy, the larger sample exposes architectural regularities that were difficult to assess from sparse observations. Non-power-of-two channel widths occur in 41.8% of verified candidates, and the strongest models share structured channel-allocation patterns characterized by moderate early widths and expanded middle or later blocks. These findings indicate that the channel-search signal observed in the initial study transfers

cs.LG↗

arXiv2026

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

Neural-network repositories contain executable models, recipes, input transformations, and measured accuracies. We study whether one same-family experiment can be curated as prompt guidance for LLM-based improvement of a low-performing target under equal generation and evaluation budgets. TuneNNGen extends NNGPT with a source-guided route and compares it with target-only generation on one CIFAR-10 target, two fixed source-selection rules, three code LLMs, and an additional SVHN target. Under the historical one-epoch search protocol, best-of-budget accuracy on the available evaluation split rises from 23.98% to 50.49% on CIFAR-10 and from 22.54% to 78.80% on SVHN. Selected five-epoch, three-seed means on train-derived validation splits retain gains of 40.94 points on CIFAR-10, 18.83 on Imagenette, and 7.27 on CIFAR-100. Direct-copy and negative-control analyses show that gains depend on source-target compatibility and LLM adaptation; stored source accuracy alone does not predict transferability.

cs.LG↗

arXiv2026

Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search

We present an automated large-scale search pipeline for heterogeneous 4-Expert Mixture-of-Experts (MoE4) architectures within the LEMUR neural network dataset ecosystem. Building on a hand-crafted heterogeneous MoE reference model, we replace manual design with a deterministic code-assembly generator that systematically combines base architecture families drawn from the LEMUR database into MoE4 ensembles, each governed by a convolutional gating network with temperature scaling, mixup augmentation, and cosine-annealed learning rate scheduling. Over a 28-day campaign on an NVIDIA RTX 4090, the pipeline generated 4,463 candidate models across 197 batches, of which 1,021 were evaluated successfully. A critical finding emerged from the campaign: due to alphabetical enumeration via itertools.combinations, the entire explored search space (4.8% of the theoretical 23,751 possible 4-family combinations) is anchored to a single family, AirNet. We characterise this coverage bias precisely, identify the root cause in the generator, and propose a stratified random sampling fix. Within the AirNet anchored scope, ShuffleNet and MobileNetV3 consistently co-produce the highest-accuracy ensembles (mean accuracy up to 0.632), while FractalNet and MNASNet are identified as low-yield families warranting exclusion in future campaigns. The pipeline, analysis artefacts, and corrected generator are released as part of the open-source NNGPT project at https://github.com/ABrain-One/nn-gpt

cs.LG↗

arXiv2026

Towards Robust Training in NNGPT AutoML Pipeline: A Loss-Optimizer Pairing Selection Study

The choice of loss function and optimizer is an important decision, that shapes further model training. Yet automated architecture search pipelines (AutoML) benefits significantly more from the optimal pairing selection and vice versa. This paper investigates whether a single recipe is sufficient for heterogeneous architecture pools, or whether the optimal pairing varies across structurally diverse models. We conduct a systematic empirical study of all $3 \times 6 = 18$ combinations of six optimizers (SGD+Momentum, Adam, AdamW, RMSprop, Adagrad, Adadelta), paired with three loss functions: Cross-Entropy (CEL), Negative Log-Likelihood (NLL), and the recently introduced genetically evolved NGL loss across the base models presented in LEMUR heterogeneous architecture pool on six image classification datasets (CelebA-Gender, CIFAR-10, CIFAR-100, ImageNette, MNIST, SVHN). The 18 loss-optimizer configurations are applied to each of the 33 compatible base architectures taken from the LEMUR pool, resulting in 594 variants that were generated fully automatically by a source-level injection pipeline and evaluated under fixed hyperparameters, ensuring that observed accuracy differences are attributable solely to the loss-optimizer pairing. Our results confirm that no single pairing is universally optimal. Cross-Entropy with Adam or AdamW is the most robust choice across architecture families and datasets. NGL is a competitive alternative to CEL on standard convolutional classifiers, but only when paired with adaptive optimizers; it degrades substantially with SGD or accumulation-based methods. Adagrad and Adadelta consistently underperform under fixed hyperparameters regardless of loss function, highlighting their sensitivity to learning rate tuning. These findings provide actionable guidance for loss-optimizer selection within NNGPT Framework.

cs.LG↗

arXiv2026

Convergence Theory for Iterative LLM-Based Neural Architecture Search: A Parametric Cross-Entropy Framework with Closed-Form Proxy Reliability

Large language models (LLMs) are increasingly used as generators in iterative neural architecture search (NAS), yet no formal convergence theory exists for this class of algorithms. We model iterative LLM-NAS as a parametric Cross-Entropy (CE) method over executable programs and prove six results: (1) iterative LLM fine-tuning on elite architectures is equivalent to the CE update restricted to the LLM parametric family; (2) expected architecture quality is monotonically non-decreasing across cycles; (3) elite-set probability converges to a fixed point at a geometric rate C_t >= 1-(1-rho_0)^t; (4) delta-based generation achieves a strictly higher valid-generation rate than full-code generation under a first-order Markov token-error model; (5) the MinHash-Jaccard novelty filter prevents mode collapse; (6) proxy reliability admits the closed-form rho_S = (6/pi) arcsin(rho_P(SNR)/2), yielding the practical diagnostic sigma^2_arch >> sigma^2_noise as a necessary condition for trustworthy proxy-based rankings. Testing against a 22-cycle, three-LLM, six-dataset experiment with 3,300 generated architectures confirms two predictions quantitatively, two at direction-of-effect level, and explains the proxy-reliability ceiling effect previously reported empirically but left unexplained.

cs.LG↗

arXiv2026

Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs

Large language models (LLMs) show strong potential for neural architecture generation, yet existing approaches produce complete model implementations from scratch -- computationally expensive and yielding verbose code. We propose Delta-Code Generation, where fine-tuned LLMs generate compact unified diffs (deltas) to refine baseline architectures rather than synthesizing entire models. Our pipeline iteratively fine-tunes the LLM via LoRA on curated architectures from the LEMUR dataset, with MinHash-Jaccard novelty filtering for structural diversity. We evaluate three 7B-class LLMs -- DeepSeek-Coder-7B, Qwen2.5-Coder-7B, and Mistral-7B -- across six datasets (CIFAR-10, CIFAR-100, MNIST, SVHN, ImageNette, CelebA) using a 22-cycle protocol (1,100 candidates per LLM). All three substantially surpass the full-generation baseline (50.6% valid rate, 42.3% mean first-epoch accuracy): DeepSeek-Coder reaches 75.3% valid rate and 65.8% mean accuracy; Qwen2.5-Coder 72.1%/64.6%; Mistral 66.6%/66.1%. On CIFAR-10, best first-epoch accuracies reach 85.5% (Mistral), 85.2% (DeepSeek), 80.6% (Qwen) -- well above 63.98% full generation and 71.5% for the concurrent approach of Gu et al. Output lengths are 30-50 lines versus 200+ for full generation (75-85% reduction). A 50-epoch study confirms the 1-epoch proxy preserves rankings (Mistral: Spearman $\rho$ = 0.926). Delta-based generation is a token-efficient, multi-domain, LLM-agnostic alternative to full-model synthesis for LLM-driven NAS.

cs.LG↗

arXiv2026

Real Image Denoising with Knowledge Distillation for High-Performance Mobile NPUs

While deep-learning-based image restoration has achieved unprecedented fidelity, deployment on mobile Neural Processing Units (NPUs) remains bottlenecked by operator incompatibility and memory-access overhead. We propose an NPU-aware hardware-algorithm co-design approach for real-world image denoising on mobile NPUs. Our approach employs a high-capacity teacher to supervise a lightweight student network specifically designed to leverage the tiled-memory architectures of modern mobile SoCs. By prioritizing NPU-native primitives -- standard 3x3 convolutions, ReLU activations, and nearest-neighbor upsampling -- and employing a progressive context expansion strategy (up to 1024x1024 crops), the model achieves 37.66 dB PSNR / 0.9278 SSIM on the validation benchmark and 37.58 dB PSNR / 0.9098 SSIM on the held-out test benchmark at full resolution (2432x3200) in the Mobile AI 2026 challenge. Following the official challenge rules, the inference runtime is measured under a standardized Full HD (1088x1920) protocol, where it runs in 34.0 ms on the MediaTek Dimensity 9500 and 46.1 ms on the Qualcomm Snapdragon 8 Elite NPU. We further reveal an "Inference Inversion" effect, where strict adherence to NPU-compatible operations enables dedicated NPU execution up to 3.88x faster than the integrated mobile GPU. The 1.96M-parameter student recovers 99.8% of the teacher's restoration quality via high-alpha knowledge distillation (alpha = 0.9), achieving a 21.2x parameter reduction while closing the PSNR gap from 1.63 dB to only 0.05 dB. These results establish hardware-aware distillation as an effective strategy for unifying high-fidelity denoising with practical deployment across diverse mobile NPU architectures. The proposed lightweight student model (LiteDenoiseNet) and its training statistics are provided in the NN Dataset, available at https://github.com/ABrain-One/NN-Dataset.

cs.CV↗

arXiv2026

From Code to Prediction: Fine-Tuning LLMs for Neural Network Performance Classification in NNGPT

Automated Machine Learning (AutoML) frameworks increasingly leverage Large Language Models (LLMs) for tasks such as hyperparameter optimization and neural architecture code generation. However, current LLM-based approaches focus on generative outputs and evaluate them by training the produced artifacts. Whether LLMs can learn to reason about neural network performance across datasets remains underexplored. We present a classification task integrated into the NNGPT framework, in which a fine-tuned LLM predicts which of two image classification datasets a given neural network architecture achieves higher accuracy on. The task is built on the LEMUR dataset, which provides standardized PyTorch implementations with reproducible performance metrics. Three prompt configurations of increasing difficulty are evaluated: a normalized-accuracy baseline (trivially reaching 100%), a metadata-enriched prompt replacing accuracies with dataset properties, and a code-only prompt presenting only architecture source code and dataset names. Using DeepSeek-Coder-7B-Instruct fine-tuned with LoRA, the code-only prompt reaches 80% peak accuracy over 15 epochs, while the metadata prompt peaks at 70%. Perdataset analysis reveals complementary strengths: metadata excels for datasets with distinctive properties (CelebAGender at 90.9%) but degrades for overlapping characteristics, whereas the code-only prompt shows more balanced performance. A comparison with DeepSeek-Coder1.3B confirms that model capacity affects this form of architectural reasoning. The results establish that LLMs can be fine-tuned to predict cross-dataset suitability from neural network code, suggesting that architecture source code contains richer discriminative signal than dataset metadata alone.

cs.LG↗

arXiv2026

MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment

Mobile deployment of facial age estimation requires models that balance predictive accuracy with low latency and compact size. In this work, we present MobileAgeNet, a lightweight age-regression framework that achieves an MAE of 4.65 years on the UTKFace held-out test set while maintaining efficient on-device inference with an average latency of 14.4 ms measured using the AI Benchmark application. The model is built on a pretrained MobileNetV3-Large backbone combined with a compact regression head, enabling real-time prediction on mobile devices. The training and evaluation pipeline is integrated into the NN LEMUR Dataset framework, supporting reproducible experimentation, structured hyperparameter optimization, and consistent evaluation. We employ bounded age regression together with a two-stage fine-tuning strategy to improve training stability and generalization. Experimental results show that MobileAgeNet achieves competitive accuracy with 3.23M parameters, and that the deployment pipeline from PyTorch training through ONNX export to TensorFlow Lite conversion - preserves predictive behavior without measurable degradation under practical on-device conditions. Overall, this work provides a practical, deployment-ready baseline for mobile-oriented facial age estimation.

cs.CV↗

arXiv2026

Resource-Efficient Iterative LLM-Based NAS with Feedback Memory

Neural Architecture Search (NAS) automates network design, but conventional methods demand substantial computational resources. We propose a closed-loop pipeline leveraging large language models (LLMs) to iteratively generate, evaluate, and refine convolutional neural network architectures for image classification on a single consumer-grade GPU without LLM fine-tuning. Central to our approach is a historical feedback memory inspired by Markov chains: a sliding window of $K{=}5$ recent improvement attempts keeps context size constant while providing sufficient signal for iterative learning. Unlike prior LLM optimizers that discard failure trajectories, each history entry is a structured diagnostic triple -- recording the identified problem, suggested modification, and resulting outcome -- treating code execution failures as first-class learning signals. A dual-LLM specialization reduces per-call cognitive load: a Code Generator produces executable PyTorch architectures while a Prompt Improver handles diagnostic reasoning. Since both the LLM and architecture training share limited VRAM, the search implicitly favors compact, hardware-efficient models suited to edge deployment. We evaluate three frozen instruction-tuned LLMs (${\leq}7$B parameters) across up to 2000 iterations in an unconstrained open code space, using one-epoch proxy accuracy on CIFAR-10, CIFAR-100, and ImageNette as a fast ranking signal. On CIFAR-10, DeepSeek-Coder-6.7B improves from 28.2% to 69.2%, Qwen2.5-7B from 50.0% to 71.5%, and GLM-5 from 43.2% to 62.0%. A full 2000-iteration search completes in ${\approx}18$ GPU hours on a single RTX~4090, establishing a low-budget, reproducible, and hardware-aware paradigm for LLM-driven NAS without cloud infrastructure.

cs.LG↗

arXiv2026

Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models

Channel-configuration search, the optimization of layer specifications such as channel widths in deep neural networks, presents a combinatorial challenge constrained by tensor-shape compatibility and computational budgets. We investigate whether large language models (LLMs) can support neural architecture search (NAS) by reasoning over architectural code structures in ways that complement traditional search heuristics. We apply an LLM-driven NAS framework to channel-configuration search, formulating the task as conditional code generation in which the LLM refines architectural specifications using performance feedback. To address data scarcity, we generate a corpus of valid, shape-consistent architectures through abstract syntax tree (AST) mutations. Although these mutated networks are not necessarily optimized for performance, they provide structural examples that help the LLM learn executable architectural patterns and relate channel configurations to model performance. Experimental results on CIFAR-100 show that the closed-loop LLM improves upon the initial AST-generated architecture population under the same proxy-evaluation protocol. Our analysis further shows that the generated architectures reflect domain-specific design patterns, including non-standard channel widths and late-stage expansion, highlighting the potential of language-driven design for code-level NAS. The code and prompts are publicly available at https://github.com/ABrain-One/NN-GPT, and the generated deep neural networks are published at https://github.com/ABrain-One/NN-Dataset under model names with the prefix ast-dimension-.

cs.CV↗

arXiv2026

From Brute Force to Semantic Insight: Performance-Guided Data Transformation Design with LLMs

Large language models (LLMs) have achieved notable performance in code synthesis; however, data-aware augmentation remains a limiting factor, handled via heuristic design or brute-force approaches. We introduce a performance-aware, closed-loop solution in the NNGPT ecosystem of projects that enables LLMs to autonomously engineer optimal transformations by internalizing empirical performance cues. We fine-tune LLMs with Low-Rank Adaptation on a novel repository of more than 6,000 empirically evaluated PyTorch augmentation functions, each annotated solely by downstream model accuracy. Training uses pairwise performance ordering (better-worse transformations), enabling alignment through empirical feedback without reinforcement learning, reward models, or symbolic objectives. This reduces the need for exhaustive search, achieving up to 600x times fewer evaluated candidates than brute-force discovery while maintaining competitive peak accuracy and shifting generation from random synthesis to task-aligned design. Ablation studies show that structured Chain-of-Thought prompting introduces syntactic noise and degrades performance, whereas direct prompting ensures stable optimization in performance-critical code tasks. Qualitative and quantitative analyses demonstrate that the model internalizes semantic performance cues rather than memorizing syntax. These results show that LLMs can exhibit task-level reasoning through non-textual feedback loops, bypassing explicit symbolic rewards.

cs.CV↗

arXiv2026

From Memorization to Creativity: LLM as a Designer of Novel Neural Architectures

Large language models (LLMs) excel in program synthesis, yet their capacity for neural architecture design -- balancing syntactic reliability, performance, and structural novelty -- remains underexplored. We present a closed-loop architecture synthesis pipeline within the NNGPT framework, in which a code-oriented LLM evolves over 22 supervised fine-tuning cycles. At each cycle, the LLM synthesizes PyTorch convolutional networks, validated via low-fidelity performance signals and filtered via a MinHash--Jaccard criterion to prevent structural redundancy before being incorporated into the LEMUR dataset. High-performing candidates with novel architectures are converted into prompt--code pairs for parameter-efficient LoRA fine-tuning. This feedback loop drives a measurable distributional shift, progressively internalizing empirical architectural priors such that valid and high-performing outputs evolve from scarce to dominant across cycles. On CIFAR-10, the valid generation rate stabilizes at 50.6% (peaking at 74.5%), mean first-epoch accuracy rises from 28.1% to 51.0%, and candidates exceeding 40% accuracy grow from 2.0% to 96.8%. Cross-dataset transfer to CIFAR-100 and SVHN confirms that improved validity, shifted accuracy distributions, and sustained novelty generalize across benchmarks of varying difficulty and visual domain. Across 22 cycles, 455 unique architectures absent from the original corpus are admitted under the novelty filter. By grounding synthesis in execution feedback and novelty filtering, we demonstrate that iterative self-supervised fine-tuning reshapes an LLM into a task-specialized architectural prior -- improving generation reliability, proxy performance, and structural diversity -- offering a reproducible, annotation-free alternative to hand-crafted search spaces.

cs.LG↗

arXiv2025

Enhancing LLM-Based Neural Network Generation: Few-Shot Prompting and Efficient Validation for Automated Architecture Design

Automated neural network architecture design remains a significant challenge in computer vision. Task diversity and computational constraints require both effective architectures and efficient search methods. Large Language Models (LLMs) present a promising alternative to computationally intensive Neural Architecture Search (NAS), but their application to architecture generation in computer vision has not been systematically studied, particularly regarding prompt engineering and validation strategies. Building on the task-agnostic NNGPT/LEMUR framework, this work introduces and validates two key contributions for computer vision. First, we present Few-Shot Architecture Prompting (FSAP), the first systematic study of the number of supporting examples (n = 1, 2, 3, 4, 5, 6) for LLM-based architecture generation. We find that using n = 3 examples best balances architectural diversity and context focus for vision tasks. Second, we introduce Whitespace-Normalized Hash Validation, a lightweight deduplication method (less than 1 ms) that provides a 100x speedup over AST parsing and prevents redundant training of duplicate computer vision architectures. In large-scale experiments across seven computer vision benchmarks (MNIST, CIFAR-10, CIFAR-100, CelebA, ImageNette, SVHN, Places365), we generated 1,900 unique architectures. We also introduce a dataset-balanced evaluation methodology to address the challenge of comparing architectures across heterogeneous vision tasks. These contributions provide actionable guidelines for LLM-based architecture search in computer vision and establish rigorous evaluation practices, making automated design more accessible to researchers with limited computational resources.

cs.CV↗