While deep learning has achieved remarkable success across a wide range of applications, its theoretical understanding of representation learning remains limited. Deep neural kernels provide a principled framework to interpret over-parameterized neural networks by mapping hierarchical feature transformations into kernel spaces, thereby combining the expressive power of deep architectures with the analytical tractability of kernel methods. Recent advances, particularly neural tangent kernels (NTKs) derived by gradient inner products, have established connections between infinitely wide neural networks and nonparametric Bayesian inference. However, the existing NTK paradigm has been predominantly confined to the infinite-width regime, while overlooking the representational role of network depth. To address this gap, we propose a depth-induced NTK kernel based on a shortcut-related architecture, which converges to a Gaussian process as the network depth approaches infinity. We theoretically analyze the training invariance and spectrum properties of the proposed kernel, which stabilizes the kernel dynamics and mitigates degeneration. Experimental results further underscore the effectiveness of our proposed method. Our findings significantly extend the existing landscape of the neural kernel theory and provide an in-depth understanding of deep learning and the scaling law.

Vision-Language Models (VLMs) have shown strong performance in tasks like visual question answering and multimodal text generation, but their effectiveness in scientific domains such as materials science remains limited. While some machine learning methods have addressed specific challenges in this field, there is still a lack of foundation models designed for broad tasks like polymer property prediction using multimodal data. In this work, we present a multimodal polymer dataset to fine-tune VLMs through instruction-tuning pairs and assess the impact of multimodality on prediction performance. Our fine-tuned models, using LoRA, outperform unimodal and baseline approaches, demonstrating the benefits of multimodal learning. Additionally, this approach reduces the need to train separate models for different properties, lowering deployment and maintenance costs.

Reflection on one's thought process and making corrections to it if there exists dissatisfaction in its performance is, perhaps, one of the essential traits of intelligence. However, such high-level abstract concepts mandatory for Artificial General Intelligence can be modelled even at the low level of narrow Machine Learning algorithms. Here, we present the self-awareness mechanism emulation in the form of a supervising artificial neural network (ANN) observing patterns in activations of another underlying ANN in a search for indications of the high uncertainty of the underlying ANN and, therefore, the trustworthiness of its predictions. The underlying ANN is a convolutional neural network (CNN) ensemble employed for face recognition and facial expression tasks. The self-awareness ANN has a memory region where its past performance information is stored, and its learnable parameters are adjusted during the training to optimize the performance. The trustworthiness verdict triggers the active learning mode, giving elements of agency to the machine learning algorithm that asks for human help in high uncertainty and confusion conditions.

While T ext-T o-Video (T2V) models have advanced rapidly, they continue to struggle with generating legible and coherent text within videos. In particular, existing models often fail to render correctly even short phrases or words and previous attempts to address this problem are computationally expensive and not suitable for video generation. In this work, we investigate a lightweight approach to improve T2V diffusion models using synthetic supervision. W e first generate text-rich images using a text-to-image (T2I) diffusion model, then animate them into short videos using a text-agnostic image-to-video (I2v) model. These synthetic video-prompt pairs are used to fine-tune W an2.1, a pre-trained T2V model, without any architectural changes. Our results show improvement in short-text legibility and temporal consistency with emerging structural priors for longer text. These findings suggest that curated synthetic data and weak supervision offer a practical path toward improving textual fidelity in T2V generation.

The rapid advancement of spatial transcriptomics (ST), i.e., spatial gene expressions, has made it possible to measure gene expression within original tissue, enabling us to discover molecular mechanisms. However, current ST platforms frequently suffer from low resolution, limiting the in-depth understanding of spatial gene expression. Super-resolution approaches promise to enhance ST maps by integrating histology images with gene expressions of profiled tissue spots. However, it remains a challenge to model the interactions between histology images and gene expressions for effective ST enhancement. This study presents a cross-modal cross-content contrastive diffusion framework, called C3-Diff, for ST enhancement with histology images as guidance. In C3-Diff, we firstly analyze the deficiency of traditional contrastive learning paradigm, which is then refined to extract both modal-invariant and content-invariant features of ST maps and histology images. Further, to overcome the problem of low sequencing sensitivity in ST maps, we perform nosing-based information augmentation on the surface of feature unit hypersphere. Finally, we propose a dynamic cross-modal imputation-based training strategy to mitigate ST data scarcity. We tested C3-Diff by benchmarking its performance on four public datasets, where it achieves significant improvements over competing methods. Moreover, we evaluate C3-Diff on downstream tasks of cell type localization, gene expression correlation and single-cell-level gene expression prediction, promoting AI-enhanced biotechnology for biomedical research and clinical applications. Codes are available at https://github.com/XiaofeiWang2018/C3-Diff.

Distribution shifts and minority subpopulations frequently undermine the reliability of deep neural networks trained using Empirical Risk Minimization (ERM). Distributionally Robust Optimization (DRO) addresses this by optimizing for the worst-case risk within a neighborhood of the training distribution. However, conventional methods depend on a single, global robustness budget, which can lead to overly conservative models or a misallocation of robustness. We propose a variance-driven, adaptive, sample-level DRO (Var-DRO) framework that automatically identifies high-risk training samples and assigns a personalized robustness budget to each based on its online loss variance. Our formulation employs two-sided, KL-divergence-style bounds to constrain the ratio between adversarial and empirical weights for every sample. This results in a linear inner maximization problem over a convex polytope, which admits an efficient water-filling solution. To stabilize training, we introduce a warmup phase and a linear ramp schedule for the global cap on per-sample budgets, complemented by label smoothing for numerical robustness. Evaluated on CIFAR-10-C (corruptions), our method achieves the highest overall mean accuracy compared to ERM and KL-DRO. On Waterbirds, Var-DRO improves overall performance while matching or surpassing KL-DRO. On the original CIFAR-10 dataset, Var-DRO remains competitive, exhibiting the modest trade-off anticipated when prioritizing robustness. The proposed framework is unsupervised (requiring no group labels), straightforward to implement, theoretically sound, and computationally efficient.

Abstract--An adaptive structural learning method of Restricted Boltzmann Machine (RBM) and Deep Belief Network (DBN) has been developed as one of prominent deep learning models. The neuron generation-annihilation algorithm in R BM and layer generation algorithm in DBN make an optimal networ k structure for given input during the learning. In this paper, our model is applied to an automatic recognition method of road network system, called RoadTracer . A novel method of RoadTracer using the T eacher-Student base d ensemble learning model of Adaptive DBN is proposed, since t he road maps contain many complicated features so that a model with high representation power to detect should be required . The experimental results showed the detection accuracy of t he proposed model was improved from 40.0% to 89.0% on average in the seven major cities among the test dataset. In addition, we challenged to apply our method to the detection of availab le roads when landslide by natural disaster is occurred, in ord er to rapidly obtain a way of transportation. For fast inferenc e, a small size of the trained model was implemented on a small embedded edge device as lightweight deep learning. Recently there have been more cases of extreme climate events including unexpected and unusual weather. The atten - tion of these events has been received in the last few years, d ue to the significant loss of human lives and escalating economi c costs, as well as the impacts on landslides and changes in ecosystems. In Japan, the Japan Meteorological Agency (JMA) has issued "Climate Change Monitoring Report" every year informing the latest status of climate change. According to [1 ], during the Heavy Rain Event of July 2018, Japan experienced unprecedented heavy rainfall. Overall precipitation obse rved at AMeDAS stations throughout Japan in July 2018 was extremely high in comparison with past heavy rainfall event s since 1982. A prominent characteristic of this rain event is that the record-breaking local precipitation, particularly wi thin 48 to 72 hours, was observed extensively over western Japan and Tokyo region, including the Seto Inland Sea side of Chugoku and Shikoku regions. S. Kamada is with Hiroshima City University, Hiroshima, Jap an T. Ichimura is with Prefectural University of Hiroshima, Hi roshima, Japan In addition, lifelines such as wat er supply and communications damaged, and traffic obstacles occurred over a wide area. Due to the disruption of major roads and railroads, the supply was also suspended.

Raul Rojas Department of Mathemanullcs and Stanullsnullcs University of Nevada Reno October 2025 Abstract This paper shows how a mulnulllayer perceptron with two hidden layers, which has been designed to classify two classes of data points, can easily be transformed into a deep neural network with one - gate layers and skip connecnullons. As shown in [1], deep one - gate per layer networks can perfectly separate points belonging to two classes in an n - dimensional space. Here, I present an alternanullve proof that may be easier to understand. This proof shows that classical neural networks that separate two classes can be transformed into deep one - gate - per - layer networks with skip connecnullons. A perceptron receives a vector input and divides input space into two subspaces: the posinullve and neganullve half - spaces (Figure 1a).

Music language models (Music LMs), like vision language models, leverage mul-timodal representations to answer natural language queries about musical audio recordings. Although Music LMs are reportedly improving, we find that current evaluations fail to capture whether their answers are correct. Specifically, for all Music LMs that we examine, widely-used evaluation metrics such as BLEU, METEOR, and BERTScore fail to measure anything beyond linguistic fluency of the model's responses. To measure the true performance of Music LMs, we propose (1) a better general-purpose evaluation metric for Music LMs adapted to the music domain and (2) a factual evaluation framework to quantify the correctness of a Music LM's responses. Our framework is agnostic to the modality of the question-answering model and could be generalized to quantify performance in other open-ended question-answering domains. We use open datasets in our experiments and will release all code on publication. Music Language Models (Music LMs) are an emerging family of multimodal models that consume both language and audio as input. Music LMs are typically benchmarked with Natural Language Processing (NLP) metrics such as BERTScore (Zhang et al., 2020), which compare reference text with model outputs using a question-answering (QA) dataset, e.g., MusicQA. Prior work has identified that these metrics may be inadequate (Gardner et al., 2024; Lee & Lee, 2024; Zang et al., 2025), but they remain the predominant approach for evaluating Music LMs. In this work, we show that the standard NLP metrics used to assess Music LMs are not just inadequate; they fail to measure any ability of these models to extract information from audio. Specifically, we propose a baseline experiment that pairs each question in a Music QA dataset with a random, unrelated music recording from the dataset; this baseline tells us how a Music LM scores when it receives no useful information with which to answer the question; nevertheless, the standard NLP metrics judge outputs of this baseline to be equally good as when the correct music is provided. Furthermore, we show that adversarially crafted answers achieve very high scores under the standard metrics, despite being factually incorrect.

Graph-based retrieval-augmented generation (Graph-based RAG) has demonstrated significant potential in enhancing Large Language Models (LLMs) with structured knowledge. However, existing methods face three critical challenges: Inaccurate Graph Construction, caused by LLM hallucination; Poor Reasoning Ability, caused by failing to generate explicit reasons telling LLM why certain chunks were selected; and Inadequate Answering, which only partially answers the query due to the inadequate LLM reasoning, making their performance lag behind NaiveRAG on certain tasks. To address these issues, we propose AGRAG, an advanced graph-based retrieval-augmented generation framework. When constructing the graph, AGRAG substitutes the widely used LLM entity extraction method with a statistics-based method, avoiding hallucination and error propagation. When retrieval, AGRAG formulates the graph reasoning procedure as the Minimum Cost Maximum Influence (MCMI) subgraph generation problem, where we try to include more nodes with high influence score, but with less involving edge cost, to make the generated reasoning paths more comprehensive. We prove this problem to be NP-hard, and propose a greedy algorithm to solve it. The MCMI subgraph generated can serve as explicit reasoning paths to tell LLM why certain chunks were retrieved, thereby making the LLM better focus on the query-related part contents of the chunks, reducing the impact of noise, and improving AGRAG's reasoning ability. Furthermore, compared with the simple tree-structured reasoning paths, our MCMI subgraph can allow more complex graph structures, such as cycles, and improve the comprehensiveness of the generated reasoning paths.