Concept Bottleneck Models (CBMs) decompose image classification into a process governed by interpretable, human-readable concepts. Recent advances in CBMs have used Large Language Models (LLMs) to generate candidate concepts. However, a critical question remains: What is the optimal number of concepts to use? Current concept banks suffer from redundancy or insufficient coverage. To address this issue, we introduce a dynamic, agent-based approach that adjusts the concept bank in response to environmental feedback, optimizing the number of concepts for sufficiency yet concise coverage. Moreover, we propose Conditional Concept Bottleneck Models (CoCoBMs) to overcome the limitations in traditional CBMs’ concept scoring mechanisms. It enhances the accuracy of assessing each concept’s contribution to classification tasks and feature an editable matrix that allows LLMs to correct concept scores that conflict with their internal knowledge. Our evaluations across 6 datasets show that our method not only improves classification accuracy by 6% but also enhances interpretability assessments by 30%.

Multimodal Large Language Models (MLLMs) have shown promise in visual-textual reasoning, with Multimodal Chain-of-Thought (MCoT) prompting significantly enhancing interpretability.However, existing MCoT methods rely on rationale-rich datasets and largely focus on inter-object reasoning, overlooking the intraobject understanding crucial for image classification.To address this gap, we propose WISE, a Weak-supervIsion-guided Step-bystep Explanation method that augments any image classification dataset with MCoTs by reformulating the concept-based representations from Concept Bottleneck Models (CBMs) into concise, interpretable reasoning chains under weak supervision.Experiments across ten datasets show that our generated MCoTs not only improve interpretability by 37% but also lead to gains in classification accuracy when used to fine-tune MLLMs 1 .Our work bridges concept-based interpretability and generative MCoT reasoning, providing a generalizable framework for enhancing MLLMs in fine-grained visual understanding.

Abstract Survival analysis holds a crucial role across diverse disciplines, such as economics, engineering and healthcare. It empowers researchers to analyze both time-invariant and time-varying data, encompassing phenomena like customer churn, material degradation and various medical outcomes. Given the complexity and heterogeneity of such data, recent endeavors have demonstrated successful integration of deep learning methodologies to address limitations in conventional statistical approaches. However, current methods typically involve cluttered probability distribution function (PDF), have lower sensitivity in censoring prediction, only model static datasets, or only rely on recurrent neural networks for dynamic modelling. In this paper, we propose a novel survival regression method capable of producing high-quality unimodal PDFs without any prior distribution assumption, by optimizing novel Margin-Mean-Variance loss and leveraging the flexibility of Transformer to handle both temporal and non-temporal data, coined UniSurv. Extensive experiments on several datasets demonstrate that UniSurv places a significantly higher emphasis on censoring compared to other methods.

Transcending the binary categorization of racist and xenophobic texts, this research takes cues from social science theories to develop a four-dimensional category for racism and xenophobia detection, namely stigmatization, offensiveness, blame, and exclusion. With the aid of deep learning techniques, this categorical detection enables insights into the nuances of emergent topics reflected in racist and xenophobic expression on Twitter. Moreover, a stage wise analysis is applied to capture the dynamic changes of the topics across the stages of early development of Covid-19 from a domestic epidemic to an international public health emergency, and later to a global pandemic. The main contributions of this research include, first the methodological advancement. By bridging the state-of-the-art computational methods with social science perspective, this research provides a meaningful approach for future research to gain insight into the underlying subtlety of racist and xenophobic discussion on digital platforms. Second, by enabling a more accurate comprehension and even prediction of public opinions and actions, this research paves the way for the enactment of effective intervention policies to combat racist crimes and social exclusion under Covid-19.

A star sensor has become one of the most widely used attitude sensors for the satellite missions in the past decade. When no prior attitude information is available, it operates in a Lost-in-space (LIS) mode. The star pattern recognition technique forms the most crucial part of star sensor in the LIS mode. In this paper, we propose a novel star pattern recognition technique for an LIS mode star sensor. Firstly, a discrete sample signal is formed from the features extracted from the star image. Later, a 1D FFT is applied on the discrete sample signal. Finally, a binary pattern is formed from the relative magnitude of consecutive FFT coefficients for finding a match between the image and the database. Experiments are performed on simulated star images with missing and false stars. The proposed approach robustly maintains the identification accuracy to 97% on the swayed and biased simulated images.

High accuracy is required for determining the orientation of a satellite in space. Amongst the existing sensors, a star tracker provides a very high accuracy of attitude determination. When no prior attitude is available, it operates in the “Lost-In-Space (LIS)” mode. Star pattern recognition is the most crucial part of a star tracker in the LIS mode. In this paper, a novel star pattern recognition approach is proposed, which constructs a signal from the features extracted in the star image and utilizes spearman correlation for identifying the correct stars. The proposed technique achieves a high identification accuracy of 99.67%. The results from the simulations show that this technique is also highly recognition reliable to the cases of missing stars, deviation in star positions, magnitude uncertainty, and false stars compared to the existing star identification algorithms.