Multimodal large language models (MLLMs) have advanced the integration of visual and linguistic modalities, establishing themselves as the dominant paradigm for visual-language tasks. Current approaches like chain of thought (CoT) reasoning have augmented the cognitive capabilities of large language models (LLMs), yet their adaptation to MLLMs is hindered by heightened risks of hallucination in cross-modality comprehension. In this paper, we find that the thinking while looking paradigm in current multimodal CoT approaches--where reasoning chains are generated alongside visual input--fails to mitigate hallucinations caused by misleading images. To address these limitations, we propose the Visual Inference Chain (VIC) framework, a novel approach that constructs reasoning chains using textual context alone before introducing visual input, effectively reducing cross-modal biases and enhancing multimodal reasoning accuracy. Comprehensive evaluations demonstrate that VIC significantly improves zero-shot performance across various vision-related tasks, mitigating hallucinations while refining the reasoning capabilities of MLLMs. Our code repository can be found at https://github.com/Terry-Xu-666/visual_inference_chain.

This paper introduces the first graph-based framework for generating group counterfactual explanations to audit model fairness, a crucial aspect of trustworthy machine learning. Counterfactual explanations are instrumental in understanding and mitigating unfairness by revealing how inputs should change to achieve a desired outcome. Our framework, named Feasible Group Counterfactual Explanations (FGCEs), captures real-world feasibility constraints and constructs subgroups with similar counterfactuals, setting it apart from existing methods. It also addresses key trade-offs in counterfactual generation, including the balance between the number of counterfactuals, their associated costs, and the breadth of coverage achieved. To evaluate these trade-offs and assess fairness, we propose measures tailored to group counterfactual generation. Our experimental results on benchmark datasets demonstrate the effectiveness of our approach in managing feasibility constraints and trade-offs, as well as the potential of our proposed metrics in identifying and quantifying fairness issues.

Identifying and understanding the co-occurrence of multiple long-term conditions (MLTC) in individuals with intellectual disabilities (ID) is vital for effective healthcare management. These individuals often face earlier onset and higher prevalence of MLTCs, yet specific co-occurrence patterns remain unexplored. This study applies an unsupervised approach to characterise MLTC clusters based on shared disease trajectories using electronic health records (EHRs) from 13069 individuals with ID in Wales (2000-2021). Disease associations and temporal directionality were assessed, followed by spectral clustering to group shared trajectories. The population consisted of 52.3% males and 47.7% females, with an average of 4.5 conditions per patient. Males under 45 formed a single cluster dominated by neurological conditions (32.4%), while males above 45 had three clusters, the largest characterised circulatory (51.8%). Females under 45 formed one cluster with digestive conditions (24.6%) as most prevalent, while those aged 45 and older showed two clusters: one dominated by circulatory (34.1%), and the other by digestive (25.9%) and musculoskeletal (21.9%) system conditions. Mental illness, epilepsy, and reflux were common across groups. These clusters offer insights into disease progression in individuals with ID, informing targeted interventions and personalised healthcare strategies.

Graph clustering is an essential aspect of network analysis that involves grouping nodes into separate clusters. Recent developments in deep learning have resulted in advanced deep graph clustering techniques, which have proven effective in many applications. Nonetheless, these methods often encounter difficulties when dealing with the complexities of real-world graphs, particularly in the presence of noisy edges. Additionally, many denoising graph clustering strategies tend to suffer from lower performance compared to their non-denoised counterparts, training instability, and challenges in scaling to large datasets. To tackle these issues, we introduce a new framework called the Dual Adaptive Assignment Approach for Robust Graph-Based Clustering (RDSA). RDSA consists of three key components: (i) a node embedding module that effectively integrates the graph's topological features and node attributes; (ii) a structure-based soft assignment module that improves graph modularity by utilizing an affinity matrix for node assignments; and (iii) a node-based soft assignment module that identifies community landmarks and refines node assignments to enhance the model's robustness. We assess RDSA on various real-world datasets, demonstrating its superior performance relative to existing state-of-the-art methods. Our findings indicate that RDSA provides robust clustering across different graph types, excelling in clustering effectiveness and robustness, including adaptability to noise, stability, and scalability.

The emergence of Deep Convolutional Neural Networks (DCNNs) has been a pervasive tool for accomplishing widespread applications in computer vision. Despite its potential capability to capture intricate patterns inside the data, the underlying embedding space remains Euclidean and primarily pursues contractive convolution. Several instances can serve as a precedent for the exacerbating performance of DCNNs. The recent advancement of neural networks in the hyperbolic spaces gained traction, incentivizing the development of convolutional deep neural networks in the hyperbolic space. In this work, we propose Hyperbolic DCNN based on the Poincar\'{e} Disc. The work predominantly revolves around analyzing the nature of expansive convolution in the context of the non-Euclidean domain. We further offer extensive theoretical insights pertaining to the universal consistency of the expansive convolution in the hyperbolic space. Several simulations were performed not only on the synthetic datasets but also on some real-world datasets. The experimental results reveal that the hyperbolic convolutional architecture outperforms the Euclidean ones by a commendable margin.

Google now offers a dedicated Gemini AI app on iPhone. First spotted by MacRumors, the free software is available to download in Australia, India, the US and the UK following a soft launch in the Philippines earlier this week. Before today, iPhone users could access Gemini through the Google app, though there were some notable limitations. For instance, the dedicated app includes Google's Gemini Live feature, which allows users to interact with the AI agent from their iPhone's Dynamic Island and Lock Screen. As a result, you don't need to have the app open on your phone's screen to use Gemini.

In this paper, we introduce Motion-Grounded Video Reasoning, a new motion understanding task that requires generating visual answers (video segmentation masks) according to the input question, and hence needs implicit spatiotemporal reasoning and grounding. This task extends existing spatiotemporal grounding work focusing on explicit action/motion grounding, to a more general format by enabling implicit reasoning via questions. To facilitate the development of the new task, we collect a large-scale dataset called GROUNDMORE, which comprises 1,715 video clips, 249K object masks that are deliberately designed with 4 question types (Causal, Sequential, Counterfactual, and Descriptive) for benchmarking deep and comprehensive motion reasoning abilities. GROUNDMORE uniquely requires models to generate visual answers, providing a more concrete and visually interpretable response than plain texts. It evaluates models on both spatiotemporal grounding and reasoning, fostering to address complex challenges in motion-related video reasoning, temporal perception, and pixel-level understanding. Furthermore, we introduce a novel baseline model named Motion-Grounded Video Reasoning Assistant (MORA). MORA incorporates the multimodal reasoning ability from the Multimodal LLM, the pixel-level perception capability from the grounding model (SAM), and the temporal perception ability from a lightweight localization head. MORA achieves respectable performance on GROUNDMORE outperforming the best existing visual grounding baseline model by an average of 21.5% relatively. We hope this novel and challenging task will pave the way for future advancements in robust and general motion understanding via video reasoning segmentation

Wildfires pose a significantly increasing hazard to global ecosystems due to the climate crisis. Due to its complex nature, there is an urgent need for innovative approaches to wildfire prediction, such as machine learning. This research took a unique approach, differentiating from classical supervised learning, and addressed the gap in unsupervised wildfire prediction using autoencoders and clustering techniques for anomaly detection. Historical weather and normalised difference vegetation index datasets of Australia for 2005 - 2021 were utilised. Two main unsupervised approaches were analysed. The first used a deep autoencoder to obtain latent features, which were then fed into clustering models, isolation forest, local outlier factor and one-class SVM for anomaly detection. The second approach used a deep autoencoder to reconstruct the input data and use reconstruction errors to identify anomalies. Long Short-Term Memory (LSTM) autoencoders and fully connected (FC) autoencoders were employed in this part, both in an unsupervised way learning only from nominal data. The FC autoencoder outperformed its counterparts, achieving an accuracy of 0.71, an F1-score of 0.74, and an MCC of 0.42. These findings highlight the practicality of this method, as it effectively predicts wildfires in the absence of ground truth, utilising an unsupervised learning technique.

In this short paper, we introduce work that is aiming to purposefully venture into this mesh of questions from a different starting point. Interjecting into the conversation, we want to ask: 'What is it to be skilled at work?' Building on work from scholars like Tim Ingold, and strands of longstanding research in workplace studies and CSCW, our interest is in turning the attention to the active work of 'being good', or 'being skilled', at what we as workers do. As we see it, skill provides a counterpoint to the version of intelligence that appears to be easily blackboxed in systems like Slack, and that ultimately reduces much of what people do to work well together. To put it slightly differently, skill - as we will argue below - gives us a way into thinking about work as a much more entangled endeavour, unfolding through multiple and interweaving sets of practices, places, tools and collaborations. In this vein, designing for the future of work seems to be about much more than where work is done or how we might bolt on discrete containers of intelligence. More fruitful would be attending to how we succeed in threading so many entities together to do our jobs well - in 'coming to be skilled'.

Code-switching (CS) is the process of speakers interchanging between two or more languages which in the modern world becomes increasingly common. In order to better describe CS speech the Matrix Language Frame (MLF) theory introduces the concept of a Matrix Language, which is the language that provides the grammatical structure for a CS utterance. In this work the MLF theory was used to develop systems for Matrix Language Identity (MLID) determination. The MLID of English/Mandarin and English/Spanish CS text and speech was compared to acoustic language identity (LID), which is a typical way to identify a language in monolingual utterances. MLID predictors from audio show higher correlation with the textual principles than LID in all cases while also outperforming LID in an MLID recognition task based on F1 macro (60%) and correlation score (0.38). This novel approach has identified that non-English languages (Mandarin and Spanish) are preferred over the English language as the ML contrary to the monolingual choice of LID.