Supervised fine-tuning (SFT) is a critical step in aligning large language models (LLMs) with human instructions and values, yet many aspects of SFT remain poorly understood. We trained a wide range of base models on a variety of datasets including code generation, mathematical reasoning, and general-domain tasks, resulting in 1,000+ SFT models under controlled conditions. We then identified the dataset properties that matter most and examined the layer-wise modifications introduced by SFT. Our findings reveal that some training-task synergies persist across all models while others vary substantially, emphasizing the importance of model-specific strategies. Moreover, we demonstrate that perplexity consistently predicts SFT effectiveness, often surpassing superficial similarity between the training data and the benchmark, and that mid-layer weight changes correlate most strongly with performance gains. We release these 1,000+ SFT models and benchmark results to accelerate further research. All resources are available at this https URL.

Sparse regularization is fundamental in signal processing for efficient signal recovery and feature extraction. However, it faces a fundamental dilemma: the most powerful sparsity-inducing penalties are often non-differentiable, conflicting with gradient-based optimizers that dominate the field. We introduce WEEP (Weakly-convex Envelope of Piecewise Penalty), a novel, fully differentiable sparse regularizer derived from the weakly-convex envelope framework. WEEP provides strong, unbiased sparsity while maintaining full differentiability and L-smoothness, making it natively compatible with any gradient-based optimizer. This resolves the conflict between statistical performance and computational tractability. We demonstrate superior performance compared to the L1-norm and other established non-convex sparse regularizers on challenging signal and image denoising tasks.

Action recognition models rely excessively on static cues rather than dynamic human motion, which is known as static bias. This bias leads to poor performance in real-world applications and zero-shot action recognition. In this paper, we propose a method to reduce static bias by separating temporal dynamic information from static scene information. Our approach uses a statistical independence loss between biased and unbiased streams, combined with a scene prediction loss. Our experiments demonstrate that this method effectively reduces static bias and confirm the importance of scene prediction loss.

Multi-object tracking, player identification, and pose estimation are fundamental components of sports analytics, essential for analyzing player movements, performance, and tactical strategies. However, existing datasets and methodologies primarily target mainstream team sports such as soccer and conventional 5-on-5 basketball, often overlooking scenarios involving fixed-camera setups commonly used at amateur levels, less mainstream sports, or datasets that explicitly incorporate pose annotations. In this paper, we propose the TrackID3x3 dataset, the first publicly available comprehensive dataset specifically designed for multi-player tracking, player identification, and pose estimation in 3x3 basketball scenarios. The dataset comprises three distinct subsets (Indoor fixed-camera, Outdoor fixed-camera, and Drone camera footage), capturing diverse full-court camera perspectives and environments. We also introduce the Track-ID task, a simplified variant of the game state reconstruction task that excludes field detection and focuses exclusively on fixed-camera scenarios. To evaluate performance, we propose a baseline algorithm called Track-ID algorithm, tailored to assess tracking and identification quality. Furthermore, our benchmark experiments, utilizing recent multi-object tracking algorithms (e.g., BoT-SORT-ReID) and top-down pose estimation methods (HRNet, RTMPose, and SwinPose), demonstrate robust results and highlight remaining challenges. Our dataset and evaluation benchmarks provide a solid foundation for advancing automated analytics in 3x3 basketball. Dataset and code will be available at this https URL.

Level set estimation (LSE), the problem of identifying the set of input points where a function takes value above (or below) a given threshold, is important in practical applications. When the function is expensive-to-evaluate and black-box, the \textit{straddle} algorithm, which is a representative heuristic for LSE based on Gaussian process models, and its extensions having theoretical guarantees have been developed. However, many of existing methods include a confidence parameter $\beta^{1/2}_t$ that must be specified by the user, and methods that choose $\beta^{1/2}_t$ heuristically do not provide theoretical guarantees. In contrast, theoretically guaranteed values of $\beta^{1/2}_t$ need to be increased depending on the number of iterations and candidate points, and are conservative and not good for practical performance. In this study, we propose a novel method, the \textit{randomized straddle} algorithm, in which $\beta_t$ in the straddle algorithm is replaced by a random sample from the chi-squared distribution with two degrees of freedom. The confidence parameter in the proposed method has the advantages of not needing adjustment, not depending on the number of iterations and candidate points, and not being conservative. Furthermore, we show that the proposed method has theoretical guarantees that depend on the sample complexity and the number of iterations. Finally, we confirm the usefulness of the proposed method through numerical experiments using synthetic and real data.

This paper describes ESPnet2-TTS, an end-to-end text-to-speech (E2E-TTS) toolkit. ESPnet2-TTS extends our earlier version, ESPnet-TTS, by adding many new features, including: on-the-fly flexible pre-processing, joint training with neural vocoders, and state-of-the-art TTS models with extensions like full-band E2E text-to-waveform modeling, which simplify the training pipeline and further enhance TTS performance. The unified design of our recipes enables users to quickly reproduce state-of-the-art E2E-TTS results. We also provide many pre-trained models in a unified Python interface for inference, offering a quick means for users to generate baseline samples and build demos. Experimental evaluations with English and Japanese corpora demonstrate that our provided models synthesize utterances comparable to ground-truth ones, achieving state-of-the-art TTS performance. The toolkit is available online at this https URL

In the graph-level prediction task (predict a label for a given graph), the information contained in subgraphs of the input graph plays a key role. In this paper, we propose Exact subgraph Isomorphism Network (EIN), which combines the exact subgraph enumeration, neural network, and a sparse regularization. In general, building a graph-level prediction model achieving high discriminative ability along with interpretability is still a challenging problem. Our combination of the subgraph enumeration and neural network contributes to high discriminative ability about the subgraph structure of the input graph. Further, the sparse regularization in EIN enables us 1) to derive an effective pruning strategy that mitigates computational difficulty of the enumeration while maintaining the prediction performance, and 2) to identify important subgraphs that contributes to high interpretability. We empirically show that EIN has sufficiently high prediction performance compared with standard graph neural network models, and also, we show examples of post-hoc analysis based on the selected subgraphs.

Testing under what conditions the product satisfies the desired properties is a fundamental problem in manufacturing industry. If the condition and the property are respectively regarded as the input and the output of a black-box function, this task can be interpreted as the problem called Level Set Estimation (LSE) -- the problem of identifying input regions such that the function value is above (or below) a threshold. Although various methods for LSE problems have been developed so far, there are still many issues to be solved for their practical usage. As one of such issues, we consider the case where the input conditions cannot be controlled precisely, i.e., LSE problems under input uncertainty. We introduce a basic framework for handling input uncertainty in LSE problem, and then propose efficient methods with proper theoretical guarantees. The proposed methods and theories can be generally applied to a variety of challenges related to LSE under input uncertainty such as cost-dependent input uncertainties and unknown input uncertainties. We apply the proposed methods to artificial and real data to demonstrate the applicability and effectiveness.

This roadmap provides a comprehensive and forward-looking perspective on the individualized application and safety of non-ionizing radiation (NIR) dosimetry in diagnostic and therapeutic medicine. Covering a wide range of frequencies, i.e., from low-frequency to terahertz, this document provides an overview of the current state of the art and anticipates future research needs in selected key topics of NIR-based medical applications. It also emphasizes the importance of personalized dosimetry, rigorous safety evaluation, and interdisciplinary collaboration to ensure safe and effective integration of NIR technologies in modern therapy and diagnosis.

We consider active learning (AL) in an uncertain environment in which trade-off between multiple risk measures need to be considered. As an AL problem in such an uncertain environment, we study Mean-Variance Analysis in Bayesian Optimization (MVA-BO) setting. Mean-variance analysis was developed in the field of financial engineering and has been used to make decisions that take into account the trade-off between the average and variance of investment uncertainty. In this paper, we specifically focus on BO setting with an uncertain component and consider multi-task, multi-objective, and constrained optimization scenarios for the mean-variance trade-off of the uncertain component. When the target blackbox function is modeled by Gaussian Process (GP), we derive the bounds of the two risk measures and propose AL algorithm for each of the above three problems based on the risk measure bounds. We show the effectiveness of the proposed AL algorithms through theoretical analysis and numerical experiments.

Dynamical behaviors of complex interacting systems, including brain activities, financial price movements, and physical collective phenomena, are associated with underlying interactions between the system's components. The issue of uncovering interaction relations in such systems using observable dynamics is called relational inference. In this study, we propose a Diffusion model for Relational Inference (DiffRI), inspired by a self-supervised method for probabilistic time series imputation. DiffRI learns to infer the probability of the presence of connections between components through conditional diffusion modeling.

Max-value entropy search (MES) is one of the state-of-the-art approaches in Bayesian optimization (BO). In this paper, we propose a novel variant of MES for constrained problems, called Constrained MES via Information lower BOund (CMES-IBO), that is based on a Monte Carlo (MC) estimator of a lower bound of a mutual information (MI). Unlike existing studies, our MI is defined so that uncertainty with respect to feasibility can be incorporated. We derive a lower bound of the MI that guarantees non-negativity, while a constrained counterpart of conventional MES can be negative. We further provide theoretical analysis that assures the low-variability of our estimator which has never been investigated for any existing information-theoretic BO. Moreover, using the conditional MI, we extend CMES-IBO to the parallel setting while maintaining the desirable properties. We demonstrate the effectiveness of CMES-IBO by several benchmark functions and real-world problems.

Malignant lymphoma subtype classification directly impacts treatment strategies and patient outcomes, necessitating classification models that achieve both high accuracy and sufficient explainability. This study proposes a novel explainable Multi-Instance Learning (MIL) framework that identifies subtype-specific Regions of Interest (ROIs) from Whole Slide Images (WSIs) while integrating cell distribution characteristics and image information. Our framework simultaneously addresses three objectives: (1) indicating appropriate ROIs for each subtype, (2) explaining the frequency and spatial distribution of characteristic cell types, and (3) achieving high-accuracy subtyping by leveraging both image and cell-distribution modalities. The proposed method fuses cell graph and image features extracted from each patch in the WSI using a Mixture-of-Experts (MoE) approach and classifies subtypes within an MIL framework. Experiments on a dataset of 1,233 WSIs demonstrate that our approach achieves state-of-the-art accuracy among ten comparative methods and provides region-level and cell-level explanations that align with a pathologist's perspectives.

The nominal performance of mechanical systems is often degraded by unknown disturbances. A two-degree-of-freedom control structure can decouple nominal performance from disturbance rejection. However, perfect disturbance rejection is unattainable when the disturbance dynamic is unknown. In this work, we reveal an inherent trade-off in disturbance estimation subject to tracking speed and tracking uncertainty. Then, we propose two novel methods to enhance disturbance estimation: an interacting multiple model extended Kalman filter-based disturbance observer and a multi-kernel correntropy extended Kalman filter-based disturbance observer. Experiments on an exoskeleton verify that the proposed two methods improve the tracking accuracy $36.3\%$ and $16.2\%$ in hip joint error, and $46.3\%$ and $24.4\%$ in knee joint error, respectively, compared to the extended Kalman filter-based disturbance observer, in a time-varying interaction force scenario, demonstrating the superiority of the proposed method.

A bilevel optimization problem consists of two optimization problems nested as an upper- and a lower-level problem, in which the optimality of the lower-level problem defines a constraint for the upper-level problem. This paper considers Bayesian optimization (BO) for the case that both the upper- and lower-levels involve expensive black-box functions. Because of its nested structure, bilevel optimization has a complex problem definition and, compared with other standard extensions of BO such as multi-objective or constraint settings, it has not been widely studied. We propose an information-theoretic approach that considers the information gain of both the upper- and lower-optimal solutions and values. This enables us to define a unified criterion that measures the benefit for both level problems, simultaneously. Further, we also show a practical lower bound based approach to evaluating the information gain. We empirically demonstrate the effectiveness of our proposed method through several benchmark datasets.

Gaussian process regression (GPR) or kernel ridge regression is a widely used and powerful tool for nonlinear prediction. Therefore, active learning (AL) for GPR, which actively collects data labels to achieve an accurate prediction with fewer data labels, is an important problem. However, existing AL methods do not theoretically guarantee prediction accuracy for target distribution. Furthermore, as discussed in the distributionally robust learning literature, specifying the target distribution is often difficult. Thus, this paper proposes two AL methods that effectively reduce the worst-case expected error for GPR, which is the worst-case expectation in target distribution candidates. We show an upper bound of the worst-case expected squared error, which suggests that the error will be arbitrarily small by a finite number of data labels under mild conditions. Finally, we demonstrate the effectiveness of the proposed methods through synthetic and real-world datasets.

We study preferential Bayesian optimization (BO) where reliable feedback is limited to pairwise comparison called duels. An important challenge in preferential BO, which uses the preferential Gaussian process (GP) model to represent flexible preference structure, is that the posterior distribution is a computationally intractable skew GP. The most widely used approach for preferential BO is Gaussian approximation, which ignores the skewness of the true posterior. Alternatively, Markov chain Monte Carlo (MCMC) based preferential BO is also proposed. In this work, we first verify the accuracy of Gaussian approximation, from which we reveal the critical problem that the predictive probability of duels can be inaccurate. This observation motivates us to improve the MCMC-based estimation for skew GP, for which we show the practical efficiency of Gibbs sampling and derive the low variance MC estimator. However, the computational time of MCMC can still be a bottleneck in practice. Towards building a more practical preferential BO, we develop a new method that achieves both high computational efficiency and low sample complexity, and then demonstrate its effectiveness through extensive numerical experiments.

Feature shifts have been shown to be useful for action recognition with CNN-based models since Temporal Shift Module (TSM) was proposed. It is based on frame-wise feature extraction with late fusion, and layer features are shifted along the time direction for the temporal interaction. TokenShift, a recent model based on Vision Transformer (ViT), also uses the temporal feature shift mechanism, which, however, does not fully exploit the structure of Multi-head Self-Attention (MSA) in ViT. In this paper, we propose Multi-head Self/Cross-Attention (MSCA), which fully utilizes the attention structure. TokenShift is based on a frame-wise ViT with features temporally shifted with successive frames (at time t+1 and t-1). In contrast, the proposed MSCA replaces MSA in the frame-wise ViT, and some MSA heads attend to successive frames instead of the current frame. The computation cost is the same as the frame-wise ViT and TokenShift as it simply changes the target to which the attention is taken. There is a choice about which of key, query, and value are taken from the successive frames, then we experimentally compared these variants with Kinetics400. We also investigate other variants in which the proposed MSCA is used along the patch dimension of ViT, instead of the head dimension. Experimental results show that a variant, MSCA-KV, shows the best performance and is better than TokenShift by 0.1% and then ViT by 1.2%.