Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and demand significant resources for training from scratch. This paper introduces Gated Slot Attention (GSA), which enhances Attention with Bounded-memory-Control (ABC) by incorporating a gating mechanism inspired by Gated Linear Attention (GLA). Essentially, GSA comprises a two-layer GLA linked via softmax, utilizing context-aware memory reading and adaptive forgetting to improve memory capacity while maintaining compact recurrent state size. This design greatly enhances both training and inference efficiency through GLA's hardware-efficient training algorithm and reduced state size. Additionally, retaining the softmax operation is particularly beneficial in "finetuning pretrained Transformers to RNNs" (T2R) settings, reducing the need for extensive training from scratch. Extensive experiments confirm GSA's superior performance in scenarios requiring in-context recall and in T2R settings.

Standard deep learning-based classification approaches may not always be practical in real-world clinical applications, as they require a centralized collection of all samples. Federated learning (FL) provides a paradigm that can learn from distributed datasets across clients without requiring them to share data, which can help mitigate privacy and data ownership issues. In FL, sub-optimal convergence caused by data heterogeneity is common among data from different health centers due to the variety in data collection protocols and patient demographics across centers. Through experimentation in this study, we show that data heterogeneity leads to the phenomenon of catastrophic forgetting during local training. We propose FedImpres which alleviates catastrophic forgetting by restoring synthetic data that represents the global information as federated impression. To achieve this, we distill the global model resulting from each communication round. Subsequently, we use the synthetic data alongside the local data to enhance the generalization of local training. Extensive experiments show that the proposed method achieves state-of-the-art performance on both the BloodMNIST and Retina datasets, which contain label imbalance and domain shift, with an improvement in classification accuracy of up to 20%.

The damage detection problem becomes a more difficult task when the intrinsically nonlinear behavior of the structures and the natural data variation are considered in the analysis because both phenomena can be confused with damage if linear and deterministic approaches are implemented. Therefore, this work aims the experimental application of a stochastic version of the Volterra series combined with a novelty detection approach to detect damage in an initially nonlinear system taking into account the measured data variation, caused by the presence of uncertainties. The experimental setup is composed by a cantilever beam operating in a nonlinear regime of motion, even in the healthy condition, induced by the presence of a magnet near to the free extremity. The damage associated with mass changes in a bolted connection (nuts loosed) is detected based on the comparison between linear and nonlinear contributions of the stochastic Volterra kernels in the total response, estimated in the reference and damaged conditions. The experimental measurements were performed on different days to add natural variation to the data measured. The results obtained through the stochastic proposed approach are compared with those obtained by the deterministic version of the Volterra series, showing the advantage of the stochastic model use when we consider the experimental data variation with the capability to detect the presence of the damage with statistical confidence. Besides, the nonlinear metric used presented a higher sensitivity to the occurrence of the damage compared with the linear one, justifying the application of a nonlinear metric when the system exhibits intrinsically nonlinear behavior.

Correct reasoning steps are important for language models to achieve high performance on many tasks, such as commonsense reasoning, question answering, and mathematical problem-solving [Wei et al., 2022, Kojima et al., 2022, Suzgun et al., 2022]. One way to elicit reasoning is through the chain-of-thought (CoT) method Wei et al. [2022], Kojima et al. [2022], which asks the model to provide step-by-step reasoning. Another approach encourages the model to provide similar problems Yasunaga et al. [2024] as the query, indirectly compelling the model to first understand the original query. Similarly, repeating and rephrasing the query Deng et al. [2023], Mekala et al. [2023] requires the model to first understand the problem and then modify the query into its own words. This rephrasing might help simplify the problem for the model. Additionally, reasoning can be generated by indirectly providing reasoning examples in demonstrations, referred to as in-context learning (ICL) Brown et al. [2020], Min et al. [2022], Xie et al. [2021]. While these methods have demonstrated significant performance improvements, language models are still prone to errors due to incorrect context understanding or analytical steps. Furthermore, they are subject to instability when requests are paraphrased. This instability is particularly concerning in the context of adversarial prompts, where recent research [Zou et al., 2023, Zeng et al., 2024] has shown that adversaries can intentionally rewrite prompts to coax safety-aligned language models into generating objectionable content that they would not generate otherwise.

The quasi-potential is a key concept in stochastic systems as it accounts for the long-term behavior of the dynamics of such systems. It also allows us to estimate mean exit times from the attractors of the system, and transition rates between states. This is of significance in many applications across various areas such as physics, biology, ecology, and economy. Computation of the quasi-potential is often obtained via a functional minimization problem that can be challenging. This paper combines a sparse learning technique with action minimization methods in order to: (i) Identify the orthogonal decomposition of the deterministic vector field (drift) driving the stochastic dynamics; (ii) Determine the quasi-potential from this decomposition. This decomposition of the drift vector field into its gradient and orthogonal parts is accomplished with the help of a machine learning-based sparse identification technique. Specifically, the so-called sparse identification of non-linear dynamics (SINDy) [1] is applied to the most likely trajectory in a stochastic system (instanton) to learn the orthogonal decomposition of the drift. Consequently, the quasi-potential can be evaluated even at points outside the instanton path, allowing our method to provide the complete quasi-potential landscape from this single trajectory. Additionally, the orthogonal drift component obtained within our framework is important as a correction to the exponential decay of transition rates and exit times. We implemented the proposed approach in 2- and 3-D systems, covering various types of potential landscapes and attractors.

In this paper we present a step-by-step approach to long-form text translation, drawing on established processes in translation studies. Instead of viewing machine translation as a single, monolithic task, we propose a framework that engages language models in a multi-turn interaction, encompassing pre-translation research, drafting, refining, and proofreading, resulting in progressively improved translations. Extensive automatic evaluations using Gemini 1.5 Pro across ten language pairs show that translating step-by-step yields large translation quality improvements over conventional zeroshot prompting approaches and earlier humanlike baseline strategies, resulting in state-of-theart Figure 1: MetricX-23 quality improvements (where results on

Developing a consistent and reliable AI game master for text-based games is a challenging task due to the limitations of large language models (LLMs) and the complexity of the game master's role. This paper presents a novel approach to enhance AI game masters by leveraging function calling in the context of the table-top role-playing game "Jim Henson's Labyrinth: The Adventure Game." Our methodology involves integrating game-specific controls through functions, which we show improves the narrative quality and state update consistency of the AI game master. The experimental results, based on human evaluations and unit tests, demonstrate the effectiveness of our approach in enhancing gameplay experience and maintaining coherence with the game state. This work contributes to the advancement of game AI and interactive storytelling, offering insights into the design of more engaging and consistent AI-driven game masters.

The segmentation of the pubic symphysis and fetal head (PSFH) constitutes a pivotal step in monitoring labor progression and identifying potential delivery complications. Despite the advances in deep learning, the lack of annotated medical images hinders the training of segmentation. Traditional semi-supervised learning approaches primarily utilize a unified network model based on Convolutional Neural Networks (CNNs) and apply consistency regularization to mitigate the reliance on extensive annotated data. However, these methods often fall short in capturing the discriminative features of unlabeled data and in delineating the long-range dependencies inherent in the ambiguous boundaries of PSFH within ultrasound images. To address these limitations, we introduce a novel framework, the Dual-Student and Teacher Combining CNN and Transformer (DSTCT), which synergistically integrates the capabilities of CNNs and Transformers. Our framework comprises a Vision Transformer (ViT) as the teacher and two student mod ls one ViT and one CNN. This dual-student setup enables mutual supervision through the generation of both hard and soft pseudo-labels, with the consistency in their predictions being refined by minimizing the classifier determinacy discrepancy. The teacher model further reinforces learning within this architecture through the imposition of consistency regularization constraints. To augment the generalization abilities of our approach, we employ a blend of data and model perturbation techniques. Comprehensive evaluations on the benchmark dataset of the PSFH Segmentation Grand Challenge at MICCAI 2023 demonstrate our DSTCT framework outperformed ten contemporary semi-supervised segmentation methods. Code available at https://github.com/jjm1589/DSTCT.

Seasonal climate forecasts are commonly based on model runs from fully coupled forecasting systems that use Earth system models to represent interactions between the atmosphere, ocean, land and other Earth-system components. Recently, machine learning (ML) methods are increasingly being investigated for this task where large-scale climate variability is linked to local or regional temperature or precipitation in a linear or non-linear fashion. This paper investigates the use of interpretable ML methods to predict seasonal precipitation for East Africa in an operational setting. Dimension reduction is performed by decomposing the precipitation fields via empirical orthogonal functions (EOFs), such that only the respective factor loadings need to the predicted. Indices of large-scale climate variability--including the rate of change in individual indices as well as interactions between different indices--are then used as potential features to obtain tercile forecasts from an interpretable ML algorithm. Several research questions regarding the use of data and the effect of model complexity are studied. The results are compared against the ECMWF seasonal forecasting system (SEAS5) for three seasons--MAM, JJAS and OND--over the period 1993-2020. Compared to climatology for the same period, the ECMWF forecasts have negative skill in MAM and JJAS and significant positive skill in OND. The ML approach is on par with climatology in MAM and JJAS and a significantly positive skill in OND, if not quite at the level of the OND ECMWF forecast.

This paper introduces a generalized ps-BART model for the estimation of Average Treatment Effect (ATE) and Conditional Average Treatment Effect (CATE) in continuous treatments, addressing limitations of the Bayesian Causal Forest (BCF) model. The ps-BART model's nonparametric nature allows for flexibility in capturing nonlinear relationships between treatment and outcome variables. Across three distinct sets of Data Generating Processes (DGPs), the ps-BART model consistently outperforms the BCF model, particularly in highly nonlinear settings. The ps-BART model's robustness in uncertainty estimation and accuracy in both point-wise and probabilistic estimation demonstrate its utility for real-world applications. This research fills a crucial gap in causal inference literature, providing a tool better suited for nonlinear treatment-outcome relationships and opening avenues for further exploration in the domain of continuous treatment effect estimation.