arXiv:2206.13646v2 Announce Type: replace 
Abstract: It is an elementary fact in the scientific literature that the Lipschitz norm of the realization function of a feedforward fully-connected rectified linear unit (ReLU) artificial neural network (ANN) can, up to a multiplicative constant, be bounded from above by sums of powers of the norm of the ANN parameter vector. Roughly speaking, in this work we reveal in the case of shallow ANNs that the converse inequality is also true. More formally, we prove that the norm of the equivalence class of ANN parameter vectors with the same realization function is, up to a multiplicative constant, bounded from above by the sum of powers of the Lipschitz norm of the ANN realization function (with the exponents $ 1/2 $ and $ 1 $). Moreover, we prove that this upper bound only holds when employing the Lipschitz norm but does neither hold for H\"older norms nor for Sobolev-Slobodeckij norms. Furthermore, we prove that this upper bound only holds for sums of powers of the Lipschitz norm with the exponents $ 1/2 $ and $ 1 $ but does not hold for the Lipschitz norm alone.

تناقش دراسة حديثة نُشرت على arXiv الحدود الخاصة بمعايير معلمات الشبكات العصبية الاصطناعية (ANN) المعاد تشكيلها باستخدام وحدات خطية مُعالجة (ReLU). تُثبت الدراسة أن معيار ليبشيتز لدالة الإدراك لشبكة ANN متصلة بالكامل يمكن أن يُحد من الأعلى بواسطة مجموعات من قوى معيار متجه معلمات الشبكة. كما تكشف الدراسة أنه في حالة الشبكات العصبية السطحية، فإن عدم المساواة العكسية صحيح أيضًا، وأن الحد الأعلى ينطبق فقط عند استخدام معيار ليبشيتز، وليس لمعايير هولدر أو سوبوليف-سلو بوديكي.

Un estudio reciente publicado en arXiv aborda los límites para las normas de los parámetros de redes neuronales artificiales (ANN) ReLU reparametrizadas. Establece que la norma de Lipschitz de la función de realización de una ANN ReLU completamente conectada puede ser acotada desde arriba por sumas de potencias de la norma del vector de parámetros de la ANN. El estudio también revela que, en el caso de ANN superficiales, la desigualdad inversa también es cierta, y que el límite superior solo se mantiene al emplear la norma de Lipschitz, no para las normas de Hölder o Sobolev-Slobodeckij.

Une étude récente publiée sur arXiv traite des bornes pour les normes des paramètres des réseaux de neurones artificiels (ANN) ReLU reparamétrés. Elle établit que la norme de Lipschitz de la fonction de réalisation d'un ANN ReLU entièrement connecté peut être bornée par des sommes de puissances de la norme du vecteur de paramètres de l'ANN. L'étude révèle également que pour les ANN peu profonds, l'inégalité inverse est vraie, et que la borne supérieure n'est valable que pour la norme de Lipschitz, et non pour les normes de Hölder ou de Sobolev-Slobodeckij.

A recent study published on arXiv discusses the bounds for norms of reparameterized ReLU artificial neural network (ANN) parameters. It establishes that the Lipschitz norm of the realization function of a feedforward fully-connected ReLU ANN can be bounded from above by sums of powers of the ANN parameter vector norm. The study also reveals that for shallow ANNs, the converse inequality holds true, and the upper bound is valid only when using the Lipschitz norm, not for Hölder or Sobolev-Slobodeckij norms.

On bounds for norms of reparameterized ReLU artificial neural network parameters: sums of fractional powers of the Lipschitz norm control the network parameter vector

arXiv:1906.07172v5 Announce Type: replace-cross 
Abstract: Equivariant neural networks are a class of neural networks designed to preserve symmetries inherent in the data. In this paper, we introduce a general method for modifying a neural network to enforce equivariance, a process we refer to as equivarification. We further show that group convolutional neural networks (G-CNNs) arise as a special case of our framework.

Equivariant neural networks and equivarification

arXiv:2311.13745v4 Announce Type: replace-cross 
Abstract: Diffusion models have become the most popular approach to deep generative modeling of images, largely due to their empirical performance and reliability. From a theoretical standpoint, a number of recent works have studied the iteration complexity of sampling, assuming access to an accurate diffusion model. In this work, we focus on understanding the sample complexity of training such a model; how many samples are needed to learn an accurate diffusion model using a sufficiently expressive neural network? Prior work showed bounds polynomial in the dimension, desired Total Variation error, and Wasserstein error. We show an exponential improvement in the dependence on Wasserstein error and depth, along with improved dependencies on other relevant parameters.

Improved Sample Complexity Bounds for Diffusion Model Training

arXiv:2410.22995v2 Announce Type: replace-cross 
Abstract: A hallmark of advanced artificial intelligence is the capacity to progress from passive visual perception to the strategic modification of visual information to facilitate complex reasoning. This advanced capability, however, remains critically underdeveloped in current Large Multi-modal Models (LMMs). The deficiency is often masked by evaluation metrics that prioritize final-answer accuracy, creating an illusion of competence where genuine reasoning is absent. Using the domain of geometric problem-solving as a precise instrument, we probe this issue through tasks that require constructing visual aids. To this end, we introduce \textbf{VisAidMath}, a challenging benchmark, and our novel Three-Layered Funnel Evaluation Framework. This framework moves beyond simple accuracy (ACCU) to scrutinize the generation of valid visual aids (PVA) and the soundness of subsequent reasoning steps (SPRS). Our extensive experiments on state-of-the-art models, including Doubao-Seed-1.6 and o4, reveal a profound ``Reasoning Illusion''. We observe that high surface-level accuracy conceals a catastrophic failure in the models' ability to produce valid visual aids or to reason from them. Our findings expose a fundamental schism between visual perception and logical deduction in modern LMMs. We host an evaluation platform at CodaBench for testing publicly. Homepage: https://nlp2ct.github.io/VisAidMathHomepage/ Evaluation: https://www.codabench.org/competitions/7634/

VisAidMath: Benchmarking Visual-Aided Mathematical Reasoning

arXiv:2508.01249v3 Announce Type: replace-cross 
Abstract: Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces critical security risks, particularly in the presence of prompt injection attacks. In this work, we propose a novel insight that treats the agent runtime traces as structured programs with analyzable semantics. Thus, we present AgentArmor, a program analysis framework that converts agent traces into graph intermediate representation-based structured program dependency representations (e.g., CFG, DFG, and PDG) and enforces security policies via a type system. AgentArmor consists of three key components: (1) a graph constructor that reconstructs the agent's runtime traces as graph-based intermediate representations with control and data flow described within; (2) a property registry that attaches security-relevant metadata of interacted tools \& data, and (3) a type system that performs static inference and checking over the intermediate representation. By representing agent behavior as structured programs, AgentArmor enables program analysis for sensitive data flow, trust boundaries, and policy violations. We evaluate AgentArmor on the AgentDojo benchmark, the results show that AgentArmor can reduce the ASR to 3\%, with the utility drop only 1\%.

AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection

arXiv:2511.14691v1 Announce Type: cross 
Abstract: Attention is the brain's ability to selectively focus on a few specific aspects while ignoring irrelevant ones. This biological principle inspired the attention mechanism in modern Transformers. Transformers now underpin large language models (LLMs) such as GPT, but at the cost of massive training and inference energy, leading to a large carbon footprint. While brain attention emerges from neural circuits, Transformer attention relies on dot-product similarity to weight elements in the input sequence. Neuromorphic computing, especially spiking neural networks (SNNs), offers a brain-inspired path to energy-efficient intelligence. Despite recent work on attention-based spiking Transformers, the core attention layer remains non-neuromorphic. Current spiking attention (i) relies on dot-product or element-wise similarity suited to floating-point operations, not event-driven spikes; (ii) keeps attention matrices that suffer from the von Neumann bottleneck, limiting in-memory computing; and (iii) still diverges from brain-like computation. To address these issues, we propose the Spiking STDP Transformer (S$^{2}$TDPT), a neuromorphic Transformer that implements self-attention through spike-timing-dependent plasticity (STDP), embedding query--key correlations in synaptic weights. STDP, a core mechanism of memory and learning in the brain and widely studied in neuromorphic devices, naturally enables in-memory computing and supports non-von Neumann hardware. On CIFAR-10 and CIFAR-100, our model achieves 94.35\% and 78.08\% accuracy with only four timesteps and 0.49 mJ on CIFAR-100, an 88.47\% energy reduction compared to a standard ANN Transformer. Grad-CAM shows that the model attends to semantically relevant regions, enhancing interpretability. Overall, S$^{2}$TDPT illustrates how biologically inspired attention can yield energy-efficient, hardware-friendly, and explainable neuromorphic models.

Attention via Synaptic Plasticity is All You Need: A Biologically Inspired Spiking Neuromorphic Transformer

arXiv:2511.08955v2 Announce Type: replace-cross 
Abstract: Simulating microstructure evolution (MicroEvo) is vital for materials design but demands high numerical accuracy, efficiency, and physical fidelity. Although recent studies on deep learning (DL) offer a promising alternative to traditional solvers, the field lacks standardized benchmarks. Existing studies are flawed due to a lack of comparing specialized MicroEvo DL models with state-of-the-art spatio-temporal architectures, an overemphasis on numerical accuracy over physical fidelity, and a failure to analyze error propagation over time. To address these gaps, we introduce MicroEvoEval, the first comprehensive benchmark for image-based microstructure evolution prediction. We evaluate 14 models, encompassing both domain-specific and general-purpose architectures, across four representative MicroEvo tasks with datasets specifically structured for both short- and long-term assessment. Our multi-faceted evaluation framework goes beyond numerical accuracy and computational cost, incorporating a curated set of structure-preserving metrics to assess physical fidelity. Our extensive evaluations yield several key insights. Notably, we find that modern architectures (e.g., VMamba), not only achieve superior long-term stability and physical fidelity but also operate with an order-of-magnitude greater computational efficiency. The results highlight the necessity of holistic evaluation and identify these modern architectures as a highly promising direction for developing efficient and reliable surrogate models in data-driven materials science.

On bounds for norms of reparameterized ReLU artificial neural network parameters: sums of fractional powers of the Lipschitz norm control the network parameter vector

Was this article worth reading? Share it