The IDs of the 10 datasets used in this work, as well as the number of examples and features, are provided in Table 1 in the main manuscript. All of the datasets correspond to binary classification problems, with varying degrees of class imbalance. While the prediction is always performed in the logarithmic domain, when evaluating the models we transform both the labels and the model predictions back into their original domain. The loss function used for training and evaluation is the standard root mean-squared error (sklearn.metrics.mean_squared_error). We download the raw data programmatically using the Kaggle API, which produces the filetrain.tsv.

While neural network binary classifiers are often evaluated on metrics such as Accuracy and $F_1$-Score, they are commonly trained with a cross-entropy objective. How can this training-evaluation gap be addressed? While specific techniques have been adopted to optimize certain confusion matrix based metrics, it is challenging or impossible in some cases to generalize the techniques to other metrics. Adversarial learning approaches have also been proposed to optimize networks via confusion matrix based metrics, but they tend to be much slower than common training methods. In this work, we propose a unifying approach to training neural network binary classifiers that combines a differentiable approximation of the Heaviside function with a probabilistic view of the typical confusion matrix values using soft sets. Our theoretical analysis shows the benefit of using our method to optimize for a given evaluation metric, such as $F_1$-Score, with soft sets, and our extensive experiments show the effectiveness of our approach in several domains.

The category gap between training and evaluation has been characterised as one of the main obstacles to the success of Few-Shot Learning (FSL). In this paper, we for the first time empirically identify image background, common in realistic images, as a shortcut knowledge helpful for in-class classification but ungeneralizable beyond training categories in FSL. A novel framework, COSOC, is designed to tackle this problem by extracting foreground objects in images at both training and evaluation without any extra supervision. Extensive experiments carried on inductive FSL tasks demonstrate the effectiveness of our approaches.

Household tidying is an important application area, yet current benchmarks neither model user preferences nor support mobility, and they generalize poorly, making it hard to comprehensively assess integrated language-to-action capabilities. To address this, we propose RoboTidy, a unified benchmark for language-guided household tidying that supports Vision-Language-Action (VLA) and Vision-Language-Navigation (VLN) training and evaluation. RoboTidy provides 500 photorealistic 3D Gaussian Splatting (3DGS) household scenes (covering 500 objects and containers) with collisions, formulates tidying as an "Action (Object, Container)" list, and supplies 6.4k high-quality manipulation demonstration trajectories and 1.5k naviagtion trajectories to support both few-shot and large-scale training. We also deploy RoboTidy in the real world for object tidying, establishing an end-to-end benchmark for household tidying. RoboTidy offers a scalable platform and bridges a key gap in embodied AI by enabling holistic and realistic evaluation of language-guided robots.

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for training large language models (LLMs) with stronger reasoning abilities. It has also been applied to a variety of logic puzzles. In this work, we study the Korean word-chain game using RLVR. We show that rule-derived rewards can naturally conflict, and demonstrate through experiments that a curriculum-learning scheme mitigates these conflicts. Our findings motivate further studies of puzzle tasks in diverse languages.

In our attached video and Figure 1, we show additional results comparing novel view synthesis results from various methods.

The first voice timbre attribute detection challenge is featured in a special session at NCMMSC 2025. It focuses on the explainability of voice timbre and compares the intensity of two speech utterances in a specified timbre descriptor dimension. The evaluation was conducted on the VCTK-RVA dataset. Participants developed their systems and submitted their outputs to the organizer, who evaluated the performance and sent feedback to them. Six teams submitted their outputs, with five providing descriptions of their methodologies.

A majority of recent work in AI assesses models' generalization capabilities through the lens of performance on out-of-distribution (OOD) datasets. Despite their practicality, such evaluations build upon a strong assumption: that OOD evaluations can capture and reflect upon possible failures in a real-world deployment. In this work, we challenge this assumption and confront the results obtained from OOD evaluations with a set of specific failure modes documented in existing question-answering (QA) models, referred to as a reliance on spurious features or prediction shortcuts. We find that different datasets used for OOD evaluations in QA provide an estimate of models' robustness to shortcuts that have a vastly different quality, some largely under-performing even a simple, in-distribution evaluation. We partially attribute this to the observation that spurious shortcuts are shared across ID+OOD datasets, but also find cases where a dataset's quality for training and evaluation is largely disconnected. Our work underlines limitations of commonly-used OOD-based evaluations of generalization, and provides methodology and recommendations for evaluating generalization within and beyond QA more robustly.