Archives AI News

arXiv:2509.05656v1 Announce Type: new Abstract: Neural architecture search (NAS) is a hard computationally expensive optimization problem with a discrete, vast, and spiky search space. One of the key research efforts dedicated to this space focuses on accelerating NAS via certain proxy evaluations of neural architectures. Different from the prevalent predictor-based methods using surrogate models and differentiable architecture search via supernetworks, we propose an optimization proxy to streamline the NAS as an end-to-end optimization framework, named OptiProxy-NAS. In particular, using a proxy representation, the NAS space is reformulated to be continuous, differentiable, and smooth. Thereby, any differentiable optimization method can be applied to the gradient-based search of the relaxed architecture parameters. Our comprehensive experiments on $12$ NAS tasks of $4$ search spaces across three different domains including computer vision, natural language processing, and resource-constrained NAS fully demonstrate the superior search results and efficiency. Further experiments on low-fidelity scenarios verify the flexibility.

arXiv:2509.06917v1 Announce Type: cross Abstract: We introduce Paper2Agent, an automated framework that converts research papers into AI agents. Paper2Agent transforms research output from passive artifacts into active systems that can accelerate downstream use, adoption, and discovery. Conventional research papers require readers to invest substantial effort to understand and adapt a paper's code, data, and methods to their own work, creating barriers to dissemination and reuse. Paper2Agent addresses this challenge by automatically converting a paper into an AI agent that acts as a knowledgeable research assistant. It systematically analyzes the paper and the associated codebase using multiple agents to construct a Model Context Protocol (MCP) server, then iteratively generates and runs tests to refine and robustify the resulting MCP. These paper MCPs can then be flexibly connected to a chat agent (e.g. Claude Code) to carry out complex scientific queries through natural language while invoking tools and workflows from the original paper. We demonstrate Paper2Agent's effectiveness in creating reliable and capable paper agents through in-depth case studies. Paper2Agent created an agent that leverages AlphaGenome to interpret genomic variants and agents based on ScanPy and TISSUE to carry out single-cell and spatial transcriptomics analyses. We validate that these paper agents can reproduce the original paper's results and can correctly carry out novel user queries. By turning static papers into dynamic, interactive AI agents, Paper2Agent introduces a new paradigm for knowledge dissemination and a foundation for the collaborative ecosystem of AI co-scientists.

arXiv:2509.05663v1 Announce Type: new Abstract: Truly unsupervised approaches for time series anomaly detection are rare in the literature. Those that exist suffer from a poorly set threshold, which hampers detection performance, while others, despite claiming to be unsupervised, need to be calibrated using a labelled data subset, which is often not available in the real world. This work integrates active learning with an existing unsupervised anomaly detection method by selectively querying the labels of multivariate time series, which are then used to refine the threshold selection process. To achieve this, we introduce a novel query strategy called the dissimilarity-based query strategy (DQS). DQS aims to maximise the diversity of queried samples by evaluating the similarity between anomaly scores using dynamic time warping. We assess the detection performance of DQS in comparison to other query strategies and explore the impact of mislabelling, a topic that is underexplored in the literature. Our findings indicate that DQS performs best in small-budget scenarios, though the others appear to be more robust when faced with mislabelling. Therefore, in the real world, the choice of query strategy depends on the expertise of the oracle and the number of samples they are willing to label. Regardless, all query strategies outperform the unsupervised threshold even in the presence of mislabelling. Thus, whenever it is feasible to query an oracle, employing an active learning-based threshold is recommended.

arXiv:2409.00034v4 Announce Type: replace Abstract: Molecular circuits capable of autonomous learning could unlock novel applications in fields such as bioengineering and synthetic biology. To this end, existing chemical implementations of neural computing have mainly relied on emulating discrete-layered neural architectures using steady-state computations of mass action kinetics. In contrast, we propose an alternative dynamical systems-based approach in which neural computations are modeled as the time evolution of molecular concentrations. The analog nature of our framework naturally aligns with chemical kinetics-based computation, leading to more compact circuits. We present the advantages of our framework through three key demonstrations. First, we assemble an end-to-end supervised learning pipeline using only two sequential phases, the minimum required number for supervised learning. Then, we show (through appropriate simplifications) that both linear and nonlinear modeling circuits can be implemented solely using unimolecular and bimolecular reactions, avoiding the complexities of higher-order chemistries. Finally, we demonstrate that first-order gradient approximations can be natively incorporated into the framework, enabling nonlinear models to scale linearly rather than combinatorially with input dimensionality. All the circuit constructions are validated through training and inference simulations across various regression and classification tasks. Our work presents a viable pathway toward embedding learning behaviors in synthetic biochemical systems.

arXiv:2502.13729v5 Announce Type: replace Abstract: Structured state-space models (SSMs) have been developed to offer more persistent memory retention than traditional recurrent neural networks, while maintaining real-time inference capabilities and addressing the time-complexity limitations of Transformers. Despite this intended persistence, the memory mechanism of canonical SSMs is theoretically designed to decay monotonically over time, meaning that more recent inputs are expected to be retained more accurately than earlier ones. Contrary to this theoretical expectation, however, the present study reveals a counterintuitive finding: when trained and evaluated on a synthetic, statistically balanced memorization task, SSMs predominantly preserve the *initially* presented data in memory. This pattern of memory bias, known as the *primacy effect* in psychology, presents a non-trivial challenge to the current theoretical understanding of SSMs and opens new avenues for future research.

arXiv:2509.05679v1 Announce Type: new Abstract: Despite the notable success of deep neural networks (DNNs) in solving complex tasks, the training process still remains considerable challenges. A primary obstacle is the substantial time required for training, particularly as high performing DNNs tend to become increasingly deep (characterized by a larger number of hidden layers) and require extensive training datasets. To address these challenges, this paper introduces a distributed training method that integrates two prominent strategies for accelerating deep learning: data parallelism and fully decoupled parallel backpropagation algorithm. By utilizing multiple computational units operating in parallel, the proposed approach enhances the amount of training data processed in each iteration while mitigating locking issues commonly associated with the backpropagation algorithm. These features collectively contribute to significant improvements in training efficiency. The proposed distributed training method is rigorously proven to converge to critical points under certain conditions. Its effectiveness is further demonstrated through empirical evaluations, wherein an DNN is trained to perform classification tasks on the CIFAR-10 dataset.

arXiv:2506.03164v2 Announce Type: replace Abstract: The iterative and stochastic nature of diffusion models enables test-time scaling, whereby spending additional compute during denoising generates higher-fidelity samples. Increasing the number of denoising steps is the primary scaling axis, but this yields quickly diminishing returns. Instead optimizing the noise trajectory--the sequence of injected noise vectors--is promising, as the specific noise realizations critically affect sample quality; but this is challenging due to a high-dimensional search space, complex noise-outcome interactions, and costly trajectory evaluations. We address this by first casting diffusion as a Markov Decision Process (MDP) with a terminal reward, showing tree-search methods such as Monte Carlo tree search (MCTS) to be meaningful but impractical. To balance performance and efficiency, we then resort to a relaxation of MDP, where we view denoising as a sequence of independent contextual bandits. This allows us to introduce an $epsilon$-greedy search algorithm that globally explores at extreme timesteps and locally exploits during the intermediate steps where de-mixing occurs. Experiments on EDM and Stable Diffusion reveal state-of-the-art scores for class-conditioned/text-to-image generation, exceeding baselines by up to $164%$ and matching/exceeding MCTS performance. To our knowledge, this is the first practical method for test-time noise trajectory optimization of arbitrary (non-differentiable) rewards.

arXiv:2509.05697v1 Announce Type: new Abstract: A morphological perceptron is a multilayer feedforward neural network in which neurons perform elementary operations from mathematical morphology. For multiclass classification tasks, a morphological perceptron with a competitive layer (MPCL) is obtained by integrating a winner-take-all output layer into the standard morphological architecture. The non-differentiability of morphological operators renders gradient-based optimization methods unsuitable for training such networks. Consequently, alternative strategies that do not depend on gradient information are commonly adopted. This paper proposes the use of the convex-concave procedure (CCP) for training MPCL networks. The training problem is formulated as a difference of convex (DC) functions and solved iteratively using CCP, resulting in a sequence of linear programming subproblems. Computational experiments demonstrate the effectiveness of the proposed training method in addressing classification tasks with MPCL networks.

arXiv:2509.05771v1 Announce Type: new Abstract: We develop a new classification framework based on the theory of coherent risk measures and systemic risk. The proposed approach is suitable for multi-class problems when the data is noisy, scarce (relative to the dimension of the problem), and the labeling might be unreliable. In the first part of our paper, we provide the foundation of the use of systemic risk models and show how to apply it in the context of linear and kernel-based multi-class problems. More advanced formulation via a system-theoretic approach with non-linear aggregation is proposed, which leads to a two-stage stochastic programming problem. A risk-averse regularized decomposition method is designed to solve the problem. We use a popular multi-class method as a benchmark in the performance analysis of the proposed classification methods. We illustrate our ideas by proposing several generalization of that method by the use of coherent measures of risk. The viability of the proposed risk-averse methods are supported theoretically and numerically. Additionally, we demonstrate that the application of systemic risk measures facilitates enforcing fairness in classification. Analysis and experiments regarding the fairness of the proposed models are carefully conducted. For all methods, our numerical experiments demonstrate that they are robust in the presence of unreliable training data and perform better on unknown data than the methods minimizing expected classification errors. Furthermore, the performance improves when the number of classes increases.

arXiv:2507.03897v2 Announce Type: replace-cross Abstract: We introduce GenAI-Powered Inference (GPI), a statistical framework for both causal and predictive inference using unstructured data, including text and images. GPI leverages open-source Generative Artificial Intelligence (GenAI) models -- such as large language models and diffusion models -- not only to generate unstructured data at scale but also to extract low-dimensional representations that are guaranteed to capture their underlying structure. Applying machine learning to these representations, GPI enables estimation of causal and predictive effects while quantifying associated estimation uncertainty. Unlike existing approaches to representation learning, GPI does not require fine-tuning of generative models, making it computationally efficient and broadly accessible. We illustrate the versatility of the GPI framework through three applications: (1) analyzing Chinese social media censorship, (2) estimating predictive effects of candidates' facial appearance on electoral outcomes, and (3) assessing the persuasiveness of political rhetoric. An open-source software package is available for implementing GPI.