Applying machine learning to sensitive time-series data is often bottlenecked by the iteration loop: Performance depends strongly on preprocessing and architecture, yet training often has to run on-premise under strict data-local constraints. This is a common problem in healthcare and other privacy-constrained domains (e.g., a hospital developing deep learning models on patient EEG). This bottleneck is particularly challenging in multimodal fusion, where sensor modalities must be individually preprocessed and then combined. LLM-guided neural architecture search (NAS) can automate this exploration, but most existing workflows assume cloud execution or access to data-derived artifacts that cannot be exposed. We present a novel data-local, LLM-guided search framework that handles candidate pipelines remotely while executing all training and evaluation locally under a fixed protocol. The controller observes only trial-level summaries, such as pipeline descriptors, metrics, learning-curve statistics, and failure logs, without ever accessing raw samples or intermediate feature representations. Our framework targets multiclass, multimodal learning via one-vs-rest binary experts per class and modality, a lightweight fusion MLP, and joint search over expert architectures and modality-specific preprocessing. We evaluate our method on two regimes: UEA30 (public multivariate time-series classification dataset) and SleepEDFx sleep staging (heterogeneous clinical modalities such as EEG, EOG, and EMG). The results show that the modular baseline model is strong, and the LLM-guided NAS further improves it. Notably, our method finds models that perform within published ranges across most benchmark datasets. Across both settings, our method reduces manual intervention by enabling unattended architecture search while keeping sensitive data on-premise.
https://arxiv.org/abs/2603.15939
When LLM agents autonomously design ML experiments, do they perform genuine architecture search -- or do they default to hyperparameter tuning within a narrow region of the design space? We answer this question by analyzing 10,469 experiments executed by two LLM agents (Claude Opus and Gemini 2.5 Pro) across a combinatorial configuration space of 108,000 discrete cells for dashcam collision detection over 27 days. Through ANOVA decomposition, we find that \textbf{architectural choices explain 94\% of performance variance} ($F = 1324$, $\eta^2 = 0.94$), while hyperparameter variation within a fixed architecture explains only 6\%. Cross-task validation on a second collision dataset confirms this finding (75\% architecture-explained variance) with a \emph{different} winning backbone, confirming genuine architecture discovery. The agents' key contribution is discovering that V-JEPA\,2 video features with Zipformer temporal encoders achieve 0.9245 AP -- a configuration no human proposed -- and concentrating search on productive architectural regions: at $N = 50$, LLM-guided search reaches AP $= 0.985$ versus $0.965$ for from-scratch random search. Post-bugfix convergence follows a power law ($c = 0.11$, $R^2 = 0.93$); the low exponent reflects the cost of broad exploration, not inefficiency, since the LLM discovers qualitatively better regions than random or Bayesian baselines. We characterize multi-agent search dynamics via entropy cycles and Jensen--Shannon specialization, providing the first large-scale empirical framework for LLM-guided combinatorial ML experiment design.
https://arxiv.org/abs/2603.15916
Enabling efficient deep neural network (DNN) inference on edge devices with different hardware constraints is a challenging task that typically requires DNN architectures to be specialized for each device separately. To avoid the huge manual effort, one can use neural architecture search (NAS). However, many existing NAS methods are resource-intensive and time-consuming because they require the training of many different DNNs from scratch. Furthermore, they do not take the resource constraints of the target system into account. To address these shortcomings, we propose PrototypeNAS, a zero-shot NAS method to accelerate and automate the selection, compression, and specialization of DNNs to different target microcontroller units (MCUs). We propose a novel three-step search method that decouples DNN design and specialization from DNN training for a given target platform. First, we present a novel search space that not only cuts out smaller DNNs from a single large architecture, but instead combines the structural optimization of multiple architecture types, as well as optimization of their pruning and quantization configurations. Second, we explore the use of an ensemble of zero-shot proxies during optimization instead of a single one. Third, we propose the use of Hypervolume subset selection to distill DNN architectures from the Pareto front of the multi-objective optimization that represent the most meaningful tradeoffs between accuracy and FLOPs. We evaluate the effectiveness of PrototypeNAS on 12 different datasets in three different tasks: image classification, time series classification, and object detection. Our results demonstrate that PrototypeNAS is able to identify DNN models within minutes that are small enough to be deployed on off-the-shelf MCUs and still achieve accuracies comparable to the performance of large DNN models.
https://arxiv.org/abs/2603.15106
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.
神经架构搜索(NAS)自动化了网络设计,但传统方法需要大量的计算资源。我们提出了一种闭环流水线,利用大型语言模型(LLMs)在单个消费级GPU上无需对LLM进行微调的情况下,迭代生成、评估和优化卷积神经网络架构以进行图像分类。我们的方法的核心是一种受马尔可夫链启发的历史反馈记忆:一个宽度为$K=5$的滑动窗口保持上下文大小恒定,同时提供足够的信号来进行迭代学习。与之前的LLM优化器丢弃失败路径不同,每个历史条目都是一个结构化的诊断三元组——记录识别的问题、建议的修改以及结果——将代码执行失败视为首要的学习信号。双LLM专业化减少了每次调用的认知负荷:一个代码生成器生产可执行的PyTorch架构,而提示改进者处理诊断推理。由于LLM和架构训练共享有限的VRAM资源,搜索过程隐式地倾向于紧凑、硬件高效的模型,适合边缘部署。 我们在约束最少的开放代码空间中评估了三个冻结指令调优的LLMs(≤70亿参数),最多进行2000次迭代,并使用CIFAR-10、CIFAR-100和ImageNette上一个epoch的代理准确度作为快速排名信号。在CIFAR-10数据集上,DeepSeek-Coder-6.7B从28.2%提高到了69.2%,Qwen2.5-7B从50.0%提升到71.5%,而GLM-5从43.2%升至62.0%。一个完整的2000次迭代搜索在单个RTX 4090 GPU上大约需要18小时,从而建立了低成本、可重复和硬件感知的LLM驱动NAS范式,无需云基础设施。 这种方法提供了显著的成本效益,并且为在边缘设备上部署高效的神经网络架构开辟了新的可能性。
https://arxiv.org/abs/2603.12091
Neural Architecture Search (NAS) for object detection is severely bottlenecked by high evaluation cost, as fully training each candidate YOLO architecture on COCO demands days of GPU time. Meanwhile, existing NAS benchmarks largely target image classification, leaving the detection community without a comparable benchmark for NAS evaluation. To address this gap, we introduce YOLO-NAS-Bench, the first surrogate benchmark tailored to YOLO-style detectors. YOLO-NAS-Bench defines a search space spanning channel width, block depth, and operator type across both backbone and neck, covering the core modules of YOLOv8 through YOLO12. We sample 1,000 architectures via random, stratified, and Latin Hypercube strategies, train them on COCO-mini, and build a LightGBM surrogate predictor. To sharpen the predictor in the high-performance regime most relevant to NAS, we propose a Self-Evolving Mechanism that progressively aligns the predictor's training distribution with the high-performance frontier, by using the predictor itself to discover and evaluate informative architectures in each iteration. This method grows the pool to 1,500 architectures and raises the ensemble predictor's R2 from 0.770 to 0.815 and Sparse Kendall Tau from 0.694 to 0.752, demonstrating strong predictive accuracy and ranking consistency. Using the final predictor as the fitness function for evolutionary search, we discover architectures that surpass all official YOLOv8-YOLO12 baselines at comparable latency on COCO-mini, confirming the predictor's discriminative power for top-performing detection architectures.
神经架构搜索(NAS)在目标检测领域由于评估成本高昂而面临严重瓶颈,因为完全训练每个候选YOLO架构需要大量的GPU时间。同时,现有的NAS基准测试主要针对图像分类问题,导致目标检测社区缺乏一个相应的NAS性能评估基准。为解决这一差距,我们引入了 YOLO-NAS-Bench,这是第一个专为目标检测(特别是类似YOLO的模型)设计的替代性基准。 **YOLO-NAS-Bench** 定义了一个搜索空间,包括通道宽度、块深度和操作类型等参数,这些覆盖了从YOLOv8到YOLO12的核心模块。我们通过随机采样、分层抽样以及拉丁超立方体(Latin Hypercube)策略生成了一千个架构,并在COCO-mini数据集上进行训练,从而构建了一个LightGBM替代预测器。 为了提高该预测器的精度,特别是在高性能区间内——这对于NAS来说是最相关的部分,我们提出了一种自我进化机制。通过使用现有的预测器来发现并评估具有信息量的架构,在每个迭代中逐步将预测器的训练分布与高性能前沿对齐,这种机制使得预测更加准确和可靠。 采用该方法后,我们将架构池增加到了1500个,并且整个集合的R2系数从0.770提高到0.815,而稀疏肯德尔τ(Sparse Kendall Tau)也从0.694提升至0.752。这表明最终预测器不仅具有强大的预测准确性,而且在排名一致性方面表现良好。 最后,我们利用该预测器作为进化搜索的适应度函数,以发现可以在COCO-mini上与官方YOLOv8-YOLO12基准模型相媲美的架构,并且其延迟相当。这证实了我们的替代预测器能够区分出高性能的目标检测架构的能力。 简而言之,通过这些创新和改进,我们为神经网络架构搜索在目标检测领域的应用提供了新的工具和策略。
https://arxiv.org/abs/2603.09405
GPU design space exploration (DSE) for modern AI workloads, such as Large-Language Model (LLM) inference, is challenging because of GPUs' vast, multi-modal design spaces, high simulation costs, and complex design optimization objectives (e.g. performance, power and area trade-offs). Existing automated DSE methods are often prohibitively expensive, either requiring an excessive number of exploration samples or depending on intricate, manually crafted analyses of interdependent critical paths guided by human heuristics. We present LUMINA, an LLM-driven GPU architecture exploration framework that leverage AI to enhance the DSE efficiency and efficacy for GPUs. LUMINA extracts architectural knowledge from simulator code and performs sensitivity studies to automatically compose DSE rules,which are auto-corrected during exploration. A core component of LUMINA is a DSE Benchmark that comprehensively evaluates and enhances LLMs' capabilities across three fundamental skills required for architecture optimization, which provides a principled and reproducible basis for model selection and ensuring consistent architectural reasoning. In the design space with 4.7 million possible samples, LUMINA identifies 6 designs of better performance and area than an A100 GPU efficiently, using only 20 steps via LLM-assisted bottleneck analysis. In comparison, LUMINA achieves 17.5x higher than design space exploration efficiency, and 32.9% better designs (i.e. Pareto Hypervolume) than Machine-Learning baselines, showcasing its ability to deliver high-quality design guidance with minimal search cost.
GPU 设计空间探索(DSE)对于现代人工智能工作负载,例如大型语言模型(LLM)推理来说是一项挑战。这是因为GPU具有庞大的、多模式的设计空间,高昂的模拟成本以及复杂的优化目标(如性能、功耗和面积之间的权衡)。现有的自动化设计空间探索方法往往过于昂贵,要么需要过多的探索样本数量,要么依赖于复杂的人工构建分析,这些分析基于人类直觉来追踪相互依存的关键路径。 我们提出了LUMINA框架,这是一个由LLM驱动的GPU架构探索框架,利用AI技术提高GPU DSE的效率和效果。LUMINA从模拟器代码中提取架构知识,并执行敏感性研究以自动组合DSE规则,在探索过程中这些规则会自动校正。LUMINA的一个关键组件是一个设计空间探索基准测试,该基准可以全面评估并增强LLM在优化架构所需的三个基本技能方面的功能,为模型选择提供原则性和可复现的基础,并确保一致的架构推理。 在一个包含470万个可能样本的设计空间中,通过使用20步(借助LLM辅助瓶颈分析),LUMINA能够高效地识别出6种性能和面积优于A100 GPU的设计。相比之下,与机器学习基线相比,LUMINA实现了17.5倍更高的设计空间探索效率,并且设计质量提高了32.9%(即帕累托超体积指标)。这展示了其在最小化搜索成本的同时提供高质量设计指导的能力。 总之,LUMINA通过智能利用AI技术显著提升了GPU架构探索的效率和效果,在有限资源内实现了更优的设计。
https://arxiv.org/abs/2603.05904
Siamese visual trackers have recently advanced through increasingly sophisticated fusion mechanisms built on convolutional or Transformer architectures. However, both struggle to deliver pixel-level interactions efficiently on resource-constrained hardware, leading to a persistent accuracy-efficiency imbalance. Motivated by this limitation, we redesign the Siamese neck with a simple yet effective Multilayer Perception (MLP)-based fusion module that enables pixel-level interaction with minimal structural overhead. Nevertheless, naively stacking MLP blocks introduces a new challenge: computational cost can scale quadratically with channel width. To overcome this, we construct a hierarchical search space of carefully designed MLP modules and introduce a customized relaxation strategy that enables differentiable neural architecture search (DNAS) to decouple channel-width optimization from other architectural choices. This targeted decoupling automatically balances channel width and depth, yielding a low-complexity architecture. The resulting tracker achieves state-of-the-art accuracy-efficiency trade-offs. It ranks among the top performers on four general-purpose and three aerial tracking benchmarks, while maintaining real-time performance on both resource-constrained Graphics Processing Units (GPUs) and Neural Processing Units (NPUs).
最近,暹罗视觉跟踪器通过基于卷积或Transformer架构的日益复杂的融合机制得到了改进。然而,这两种方法都在资源受限的硬件上难以高效地实现像素级别的交互,导致了持久存在的精度与效率之间的不平衡问题。鉴于这一局限性,我们重新设计了暹罗颈部,采用了一种简单而有效的多层感知器(MLP)融合模块,该模块能够以最少的结构开销实现像素级互动。然而,直接堆叠MLP块会带来一个新的挑战:计算成本可能会随着通道宽度呈二次方增长。为了解决这个问题,我们构建了一个精心设计的MLP模块层次搜索空间,并引入了一种定制化的松弛策略,使可微神经架构搜索(DNAS)能够将通道宽度优化与其他架构选择解耦。这种有目标的解耦可以自动平衡通道宽度与深度,从而产生低复杂度的架构。由此产生的跟踪器在精度和效率之间的权衡上达到了最先进的水平,在四个通用目的和三个空中追踪基准测试中表现出顶级性能,并且能够在资源受限的图形处理器(GPU)和神经处理单元(NPU)上保持实时性能。
https://arxiv.org/abs/2603.01706
Numerous lines of aim to control $\textit{model disagreement}$ -- the extent to which two machine learning models disagree in their predictions. We adopt a simple and standard notion of model disagreement in real-valued prediction problems, namely the expected squared difference in predictions between two models trained on independent samples, without any coordination of the training processes. We would like to be able to drive disagreement to zero with some natural parameter(s) of the training procedure using analyses that can be applied to existing training methodologies. We develop a simple general technique for proving bounds on independent model disagreement based on $\textit{anchoring}$ to the average of two models within the analysis. We then apply this technique to prove disagreement bounds for four commonly used machine learning algorithms: (1) stacked aggregation over an arbitrary model class (where disagreement is driven to 0 with the number of models $k$ being stacked) (2) gradient boosting (where disagreement is driven to 0 with the number of iterations $k$) (3) neural network training with architecture search (where disagreement is driven to 0 with the size $n$ of the architecture being optimized over) and (4) regression tree training over all regression trees of fixed depth (where disagreement is driven to 0 with the depth $d$ of the tree architecture). For clarity, we work out our initial bounds in the setting of one-dimensional regression with squared error loss -- but then show that all of our results generalize to multi-dimensional regression with any strongly convex loss.
许多研究工作旨在控制**模型分歧**,即两个机器学习模型在预测中不一致的程度。我们采用了一种关于实值预测问题中的模型分歧的简单且标准的概念:这是指训练过程中,在独立样本上训练的两个模型之间预测结果的期望平方差(无需协调各自的训练过程)。 我们的目标是能够通过调整一些自然参数来将这种分歧降至零,这些参数可以应用于现有的训练方法。为此,我们开发了一种基于**锚定到两个模型平均值**来进行独立模型分歧界限证明的基本技术。然后,我们将此技术应用到四种常用的机器学习算法中以证明分歧界限: 1. **堆叠聚合(stacked aggregation)**:针对任意模型类别的堆叠聚合方法,在该方法中,随着被堆叠的模型数量 $k$ 的增加,分歧趋向于零。 2. **梯度提升(gradient boosting)**:在梯度提升算法中,通过迭代次数 $k$ 的增加来使分歧减少直至趋近于零。 3. **神经网络训练与架构搜索**:对于使用架构搜索进行的神经网络训练,在优化目标为特定大小 $n$ 架构的情况下,随着架构规模的增长,分歧也趋向于减小直到接近于零。 4. **回归树训练(regression tree training)**:当对所有固定深度 $d$ 的回归树进行训练时,随着树的深度增加,模型之间的分歧将减少至趋于零。 为了解释清晰,我们首先在单变量回归和平方误差损失的情况下推导出了初始界限,然后展示了我们的结果可以推广到具有任意强凸损失函数的多维回归问题中。
https://arxiv.org/abs/2602.23360
This paper proposes a novel medical image segmentation framework, MNAS-Unet, which combines Monte Carlo Tree Search (MCTS) and Neural Architecture Search (NAS). MNAS-Unet dynamically explores promising network architectures through MCTS, significantly enhancing the efficiency and accuracy of architecture search. It also optimizes the DownSC and UpSC unit structures, enabling fast and precise model adjustments. Experimental results demonstrate that MNAS-Unet outperforms NAS-Unet and other state-of-the-art models in segmentation accuracy on several medical image datasets, including PROMISE12, Ultrasound Nerve, and CHAOS. Furthermore, compared with NAS-Unet, MNAS-Unet reduces the architecture search budget by 54% (early stopping at 139 epochs versus 300 epochs under the same search setting), while achieving a lightweight model with only 0.6M parameters and lower GPU memory consumption, which further improves its practical applicability. These results suggest that MNAS-Unet can improve search efficiency while maintaining competitive segmentation accuracy under practical resource constraints.
本文提出了一种新颖的医学图像分割框架MNAS-Unet,该框架结合了蒙特卡洛树搜索(MCTS)和神经架构搜索(NAS)。MNAS-Unet通过MCTS动态探索有前景的网络结构,从而显著提高架构搜索的效率和准确性。此外,它还优化了DownSC和UpSC单元结构,使其能够快速准确地调整模型。 实验结果表明,在多个医学图像数据集上(包括PROMISE12、超声神经和CHAOS),MNAS-Unet在分割精度方面超越了NAS-Unet及其他最先进的模型。与NAS-Unet相比,在相同的搜索设置下,MNAS-Unet将架构搜索预算减少了54%(提前停止于139个时期而其他情况是300个时期),同时获得了仅包含0.6M参数的轻量级模型,并且降低了GPU内存消耗,从而进一步提升了其实用性。 这些结果表明,在实际资源约束条件下,MNAS-Unet能够在提高搜索效率的同时保持竞争力的分割精度。
https://arxiv.org/abs/2602.22361
Reinforcement learning fine-tuning has proven effective for steering generative diffusion models toward desired properties in image and molecular domains. Graph diffusion models have similarly been applied to combinatorial structure generation, including neural architecture search (NAS). However, neural architectures are directed acyclic graphs (DAGs) where edge direction encodes functional semantics such as data flow-information that existing graph diffusion methods, designed for undirected structures, discard. We propose Directed Graph Policy Optimization (DGPO), which extends reinforcement learning fine-tuning of discrete graph diffusion models to DAGs via topological node ordering and positional encoding. Validated on NAS-Bench-101 and NAS-Bench-201, DGPO matches the benchmark optimum on all three NAS-Bench-201 tasks (91.61%, 73.49%, 46.77%). The central finding is that the model learns transferable structural priors: pretrained on only 7% of the search space, it generates near-oracle architectures after fine-tuning, within 0.32 percentage points of the full-data model and extrapolating 7.3 percentage points beyond its training ceiling. Bidirectional control experiments confirm genuine reward-driven steering, with inverse optimization reaching near random-chance accuracy (9.5%). These results demonstrate that reinforcement learning-steered discrete diffusion, once extended to handle directionality, provides a controllable generative framework for directed combinatorial structures.
强化学习微调已被证明在引导生成扩散模型朝向图像和分子领域所需的特性方面是有效的。图扩散模型也已经被应用于组合结构生成,包括神经架构搜索(NAS)。然而,神经架构是由有向无环图(DAG)组成的,其中边的方向编码了功能语义,如数据流信息——这种信息现有的针对非定向结构设计的图扩散方法会忽略掉。 我们提出了有向图策略优化(DGPO),这是一种通过拓扑节点排序和位置编码来将离散图扩散模型的强化学习微调扩展到DAG的方法。在NAS-Bench-101和NAS-Bench-201上的验证显示,DGPO在所有三个NAS-Bench-201任务上达到了基准最优值(91.61%,73.49%,46.77%)。主要发现是模型学习到了可迁移的结构先验:仅在搜索空间的7%进行预训练后,在微调阶段就生成了接近Oracle架构,其性能几乎与完全数据模型相当,并且还在训练上限之上额外提升了7.3个百分点。双向控制实验确认了真正的奖励驱动引导,逆向优化达到了接近随机机会准确度(9.5%)。这些结果表明,一旦强化学习引导的离散扩散方法能够处理方向性问题,它就能为有向组合结构提供一个可控的生成框架。
https://arxiv.org/abs/2602.19261
Neural architecture search (NAS) automates the discovery of neural networks that meet specified criteria, yet its evaluation procedures are often hardcoded, limiting the ability to introduce new metrics. This issue is especially pronounced in hardware-aware NAS, where objectives depend on target devices such as edge hardware. To address this limitation, we propose SEval-NAS, a metric-evaluation mechanism that converts architectures to strings, embeds them as vectors, and predicts performance metrics. Using NATS-Bench and HW-NAS-Bench, we evaluated accuracy, latency, and memory. Kendall's $\tau$ correlations showed stronger latency and memory predictions than accuracy, indicating the suitability of SEval-NAS as a hardware cost predictor. We further integrated SEval-NAS into FreeREA to evaluate metrics not originally included. The method successfully ranked FreeREA-generated architectures, maintained search time, and required minimal algorithmic changes. Our implementation is available at: this https URL
神经架构搜索(NAS)自动发现了符合特定标准的神经网络,但其评估过程通常是硬编码的,限制了引入新度量指标的能力。在硬件感知型NAS中,目标设备如边缘计算硬件的具体需求使得这一问题更加突出。 为了解决这个问题,我们提出了SEval-NAS,这是一种将架构转换为字符串、嵌入向量并预测性能指标的度量评估机制。使用NATS-Bench和HW-NAS-Bench进行了准确性、延迟和内存的评估。根据肯德尔的$\tau$相关性分析,对于延迟和内存的预测结果比准确性的预测更强,这表明SEval-NAS可以作为硬件成本预测的有效工具。 我们进一步将SEval-NAS集成到了FreeREA中,以评估原本未包含在内的度量指标。该方法成功地对FreeREA生成的架构进行了排序,并保持了搜索时间的同时只需要进行少量算法修改。 我们的实现代码可在以下链接获取:this https URL
https://arxiv.org/abs/2603.00099
Traditional methods for automating recommender system design, such as Neural Architecture Search (NAS), are often constrained by a fixed search space defined by human priors, limiting innovation to pre-defined operators. While recent LLM-driven code evolution frameworks shift fixed search space target to open-ended program spaces, they primarily rely on scalar metrics (e.g., NDCG, Hit Ratio) that fail to provide qualitative insights into model failures or directional guidance for improvement. To address this, we propose Self-EvolveRec, a novel framework that establishes a directional feedback loop by integrating a User Simulator for qualitative critiques and a Model Diagnosis Tool for quantitative internal verification. Furthermore, we introduce a Diagnosis Tool - Model Co-Evolution strategy to ensure that evaluation criteria dynamically adapt as the recommendation architecture evolves. Extensive experiments demonstrate that Self-EvolveRec significantly outperforms state-of-the-art NAS and LLM-driven code evolution baselines in both recommendation performance and user satisfaction. Our code is available at this https URL.
https://arxiv.org/abs/2602.12612
Vision-Language-Action Models (VLAs) have emerged as a key paradigm of Physical AI and are increasingly deployed in autonomous vehicles, robots, and smart spaces. In these resource-constrained on-device settings, selecting an appropriate large language model (LLM) backbone is a critical challenge: models must balance accuracy with strict inference latency and hardware efficiency constraints. This makes hardware-software co-design a game-changing requirement for on-device LLM deployment, where each hardware platform demands a tailored architectural solution. We propose a hardware co-design law that jointly captures model accuracy and inference performance. Specifically, we model training loss as an explicit function of architectural hyperparameters and characterise inference latency via roofline modelling. We empirically evaluate 1,942 candidate architectures on NVIDIA Jetson Orin, training 170 selected models for 10B tokens each to fit a scaling law relating architecture to training loss. By coupling this scaling law with latency modelling, we establish a direct accuracy-latency correspondence and identify the Pareto frontier for hardware co-designed LLMs. We further formulate architecture search as a joint optimisation over precision and performance, deriving feasible design regions under industrial hardware and application budgets. Our approach reduces architecture selection from months to days. At the same latency as Qwen2.5-0.5B on the target hardware, our co-designed architecture achieves 19.42% lower perplexity on WikiText-2. To our knowledge, this is the first principled and operational framework for hardware co-design scaling laws in on-device LLM deployment. We will make the code and related checkpoints publicly available.
视觉语言行动模型(VLAs)已作为物理人工智能的关键范式而出现,并且越来越多地被部署在自主车辆、机器人和智能空间中。在这种资源受限的设备环境中,选择合适的大型语言模型(LLM)骨干是一个关键挑战:模型必须在严格的推理延迟和硬件效率限制下平衡准确性和性能。这使得软硬件协同设计成为设备上部署LLM的关键需求,每个硬件平台都要求定制的架构解决方案。我们提出了一项软硬件协同设计法则,该法则同时捕捉模型精度和推理性能。具体而言,我们将训练损失建模为架构超参数的显式函数,并通过顶点模型来表征推理延迟。我们在NVIDIA Jetson Orin上对1,942个候选架构进行了实证评估,每个选择了170种模型进行10B代币的训练,以拟合从架构到训练损失的关系。通过将这种扩展法则与延迟建模相结合,我们建立了一个直接的精度-延迟对应关系,并识别出软硬件协同设计LLM的帕累托前沿。进一步地,我们将架构搜索形式化为对精度和性能的同时优化,在工业硬件和应用预算下导出了可行的设计区域。我们的方法将架构选择的时间从数月缩短到了几天。在目标硬件上的相同延迟条件下,我们所提出的协同设计架构相比Qwen2.5-0.5B模型在WikiText-2上实现了19.42%更低的困惑度。据我们所知,这是首个系统且可操作的软硬件协同设计扩展法则框架,用于设备上LLM部署。我们将公开发布代码及相关检查点。
https://arxiv.org/abs/2602.10377
Spiking Neural Networks (SNNs) are increasingly studied as energy-efficient alternatives to Convolutional Neural Networks (CNNs), particularly for edge intelligence. However, prior work has largely emphasized large-scale models, leaving the design and evaluation of lightweight CNN-to-SNN pipelines underexplored. In this paper, we present the first systematic benchmark of lightweight SNNs obtained by converting compact CNN architectures into spiking networks, where activations are modeled with Leaky-Integrate-and-Fire (LIF) neurons and trained using surrogate gradient descent under a unified setup. We construct spiking variants of ShuffleNet, SqueezeNet, MnasNet, and MixNet, and evaluate them on CIFAR-10, CIFAR-100, and TinyImageNet, measuring accuracy, F1-score, parameter count, computational complexity, and energy consumption. Our results show that SNNs can achieve up to 15.7x higher energy efficiency than their CNN counterparts while retaining competitive accuracy. Among these, the SNN variant of SqueezeNet consistently outperforms other lightweight SNNs. To further optimize this model, we apply a structured pruning strategy that removes entire redundant modules, yielding a pruned architecture, SNN-SqueezeNet-P. This pruned model improves CIFAR-10 accuracy by 6% and reduces parameters by 19% compared to the original SNN-SqueezeNet. Crucially, it narrows the gap with CNN-SqueezeNet, achieving nearly the same accuracy (only 1% lower) but with an 88.1% reduction in energy consumption due to sparse spike-driven computations. Together, these findings establish lightweight SNNs as practical, low-power alternatives for edge deployment, highlighting a viable path toward deploying high-performance, low-power intelligence on the edge.
脉冲神经网络(SNN)作为卷积神经网络(CNN)的节能替代方案,特别是在边缘智能领域中得到了越来越多的关注。然而,先前的研究主要集中在大规模模型上,忽略了轻量级 CNN 到 SNN 转换管道的设计和评估。在这篇论文中,我们介绍了首次系统性地对通过将紧凑型 CNN 架构转换为脉冲网络获得的轻量级 SNN 进行基准测试的结果。在这些转换后的 SNN 中,激活被建模为使用泄露积分放电(LIF)神经元,并采用统一设置下的替代梯度下降法进行训练。 我们构建了 ShuffleNet、SqueezeNet、MnasNet 和 MixNet 的脉冲版本,并针对 CIFAR-10、CIFAR-100 和 TinyImageNet 数据集进行了评估,包括准确率、F1 分数、参数数量、计算复杂性以及能耗等指标。我们的结果显示,在保持竞争力的准确性的前提下,SNN 可以比其 CNN 对应模型高 15.7 倍的能量效率。在这其中,SqueezeNet 的 SNN 变体在所有轻量级 SNN 中表现最优。 为了进一步优化这个模型,我们应用了一种结构化剪枝策略,删除了整个冗余模块,从而得到了一个剪枝架构:SNN-SqueezeNet-P。相比原始的 SNN-SqueezeNet,此剪枝模型将 CIFAR-10 准确率提高了 6%,参数减少了 19%。尤为重要的是,它缩小了与 CNN-SqueezeNet 的差距,在几乎相同的准确度(低仅 1%)下,由于稀疏脉冲驱动的计算,能量消耗降低了 88.1%。 这些发现共同证明轻量级 SNN 在边缘部署中是实用且低能耗的选择,并为在边缘部署高性能、低功耗智能提供了一条可行路径。
https://arxiv.org/abs/2602.09717
Differentiable Neural Architecture Search (NAS) provides efficient, gradient-based methods for automatically designing neural networks, yet its adoption remains limited in practice. We present MIDAS, a novel approach that modernizes DARTS by replacing static architecture parameters with dynamic, input-specific parameters computed via self-attention. To improve robustness, MIDAS (i) localizes the architecture selection by computing it separately for each spatial patch of the activation map, and (ii) introduces a parameter-free, topology-aware search space that models node connectivity and simplifies selecting the two incoming edges per node. We evaluate MIDAS on the DARTS, NAS-Bench-201, and RDARTS search spaces. In DARTS, it reaches 97.42% top-1 on CIFAR-10 and 83.38% on CIFAR-100. In NAS-Bench-201, it consistently finds globally optimal architectures. In RDARTS, it sets the state of the art on two of four search spaces on CIFAR-10. We further analyze why MIDAS works, showing that patchwise attention improves discrimination among candidate operations, and the resulting input-specific parameter distributions are class-aware and predominantly unimodal, providing reliable guidance for decoding.
可微神经架构搜索(NAS)提供了一种自动设计神经网络的高效、基于梯度的方法,但其在实践中应用仍然有限。我们提出了MIDAS,这是一种通过用自注意力计算出的动态且特定于输入的参数来替换静态架构参数,从而对DARTS进行了现代化改进的新方法。为了提高鲁棒性,MIDAS(i)通过对激活图中的每个空间补丁分别进行架构选择来进行局部化,并(ii)引入了一种无参数、拓扑感知的搜索空间,该空间建模节点连接并简化了每个节点选择两个输入边的过程。 我们在DARTS、NAS-Bench-201和RDARTS搜索空间上评估了MIDAS。在DARTS中,它在CIFAR-10数据集上的顶级准确率为97.42%,在CIFAR-100数据集上的准确率为83.38%。在NAS-Bench-201中,它始终能找到全局最优架构。在RDARTS上,它在四个搜索空间中的两个中为CIFAR-10设定了最新的技术水平。 我们进一步分析了MIDAS为何有效:补丁级注意力提高了对候选操作的区分能力,并且生成的特定于输入的参数分布是类别感知的并且主要是单峰的,这为解码提供了可靠的指导。
https://arxiv.org/abs/2602.17700
Structured pruning is essential for efficient deployment of Large Language Models (LLMs). The varying sensitivity of LLM sub-blocks to pruning necessitates the identification of optimal non-uniformly pruned models. Existing methods evaluate the importance of layers, attention heads, or weight channels in isolation. Such localized focus ignores the complex global structural dependencies that exist across the model. Training-aware structured pruning addresses global dependencies, but its computational cost can be just as expensive as post-pruning training. To alleviate the computational burden of training-aware pruning and capture global structural dependencies, we propose TraceNAS, a training-free Neural Architecture Search (NAS) framework that jointly explores structured pruning of LLM depth and width. TraceNAS identifies pruned models that maintain a high degree of loss landscape alignment with the pretrained model using a scale-invariant zero-shot proxy, effectively selecting models that exhibit maximal performance potential during post-pruning training. TraceNAS is highly efficient, enabling high-fidelity discovery of pruned models on a single GPU in 8.5 hours, yielding a 10$\times$ reduction in GPU-hours compared to training-aware methods. Evaluations on the Llama and Qwen families demonstrate that TraceNAS is competitive with training-aware baselines across commonsense and reasoning benchmarks.
结构化剪枝对于大型语言模型(LLM)的高效部署至关重要。由于LLM子模块对剪枝敏感度不同,因此需要识别最优的非均匀剪枝模型。现有的方法分别评估层、注意力头或权重通道的重要性,这种局部关注忽略了模型内部复杂的全局结构性依赖关系。训练感知结构化剪枝可以解决这一问题,但其计算成本可能与后剪枝训练一样昂贵。为了减轻训练感知剪枝的计算负担并捕获全局结构性依赖关系,我们提出了TraceNAS,这是一种无需训练的神经架构搜索(NAS)框架,它同时探索LLM深度和宽度的结构化剪枝。TraceNAS通过使用比例不变的零样本代理来识别与预训练模型损失景观高度对齐的剪枝模型,有效地选择在后剪枝训练中表现出最大性能潜力的模型。TraceNAS效率极高,在单个GPU上仅需8.5小时即可发现高质量的剪枝模型,相比训练感知方法减少了10倍的GPU时间消耗。在Llama和Qwen家族上的评估表明,TraceNAS在常识和推理基准测试方面与训练感知基线具有竞争力。
https://arxiv.org/abs/2602.02891
Lightweight models are essential for real-time speech enhancement applications. In recent years, there has been a growing trend toward developing increasingly compact models for speech enhancement. In this paper, we propose an Ultra-Lightweight U-net optimized by Network Architecture Search (UL-UNAS), which is suitable for implementation in low-footprint devices. Firstly, we explore the application of various efficient convolutional blocks within the U-Net framework to identify the most promising candidates. Secondly, we introduce two boosting components to enhance the capacity of these convolutional blocks: a novel activation function named affine PReLU and a causal time-frequency attention module. Furthermore, we leverage neural architecture search to discover an optimal architecture within our carefully designed search space. By integrating the above strategies, UL-UNAS not only significantly outperforms the latest ultra-lightweight models with the same or lower computational complexity, but also delivers competitive performance compared to recent baseline models that require substantially higher computational resources. Source code and audio demos are available at this https URL.
https://arxiv.org/abs/2503.00340
Early-exit neural networks have become popular for reducing inference latency by allowing intermediate predictions when sufficient confidence is achieved. However, standard approaches typically rely on single-model confidence thresholds, which are frequently unreliable due to inherent calibration issues. To address this, we introduce SQUAD (Scalable Quorum Adaptive Decisions), the first inference scheme that integrates early-exit mechanisms with distributed ensemble learning, improving uncertainty estimation while reducing the inference time. Unlike traditional methods that depend on individual confidence scores, SQUAD employs a quorum-based stopping criterion on early-exit learners by collecting intermediate predictions incrementally in order of computational complexity until a consensus is reached and halting the computation at that exit if the consensus is statistically significant. To maximize the efficacy of this voting mechanism, we also introduce QUEST (Quorum Search Technique), a Neural Architecture Search method to select early-exit learners with optimized hierarchical diversity, ensuring learners are complementary at every intermediate layer. This consensus-driven approach yields statistically robust early exits, improving the test accuracy up to 5.95% compared to state-of-the-art dynamic solutions with a comparable computational cost and reducing the inference latency up to 70.60% compared to static ensembles while maintaining a good accuracy.
https://arxiv.org/abs/2601.22711
Many challenges arising in Quantum Technology can be successfully addressed using a set of machine learning algorithms collectively known as reinforcement learning (RL), based on adaptive decision-making through interaction with the quantum device. After a concise and intuitive introduction to RL aimed at a broad physics readership, we discuss the key ideas and core concepts in reinforcement learning with a particular focus on quantum systems. We then survey recent progress in RL in all relevant areas. We discuss state preparation in few- and many-body quantum systems, the design and optimization of high-fidelity quantum gates, and the automated construction of quantum circuits, including applications to variational quantum eigensolvers and architecture search. We further highlight the interactive capabilities of RL agents, emphasizing recent progress in quantum feedback control and quantum error correction, and briefly discuss quantum reinforcement learning as well as applications to quantum metrology. The review concludes with a discussion of open challenges -- such as scalability, interpretability, and integration with experimental platforms -- and outlines promising directions for future research. Throughout, we highlight experimental implementations that exemplify the increasing role of reinforcement learning in shaping the development of quantum technologies.
https://arxiv.org/abs/2601.18953
Current quantum neural networks suffer from extreme sensitivity to both adversarial perturbations and hardware noise, creating a significant barrier to real-world deployment. Existing robustness techniques typically sacrifice clean accuracy or require prohibitive computational resources. We propose a hybrid quantum-classical Differentiable Quantum Architecture Search (DQAS) framework that addresses these limitations by jointly optimizing circuit structure and robustness through gradient-based methods. Our approach enhances traditional DQAS with a lightweight Classical Noise Layer applied before quantum processing, enabling simultaneous optimization of gate selection and noise parameters. This design preserves the quantum circuit's integrity while introducing trainable perturbations that enhance robustness without compromising standard performance. Experimental validation on MNIST, FashionMNIST, and CIFAR datasets shows consistent improvements in both clean and adversarial accuracy compared to existing quantum architecture search methods. Under various attack scenarios, including Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), Basic Iterative Method (BIM), and Momentum Iterative Method (MIM), and under realistic quantum noise conditions, our hybrid framework maintains superior performance. Testing on actual quantum hardware confirms the practical viability of discovered architectures. These results demonstrate that strategic classical preprocessing combined with differentiable quantum architecture optimization can significantly enhance quantum neural network robustness while maintaining computational efficiency.
https://arxiv.org/abs/2601.18058