Novel view synthesis is a fundamental challenge in image-to-3D generation, requiring the generation of target view images from a set of conditioning images and their relative poses. While recent approaches like Zero-1-to-3 have demonstrated promising results using conditional latent diffusion models, they face significant challenges in generating consistent and accurate novel views, particularly when handling multiple conditioning images. In this work, we conduct a thorough investigation of Zero-1-to-3's cross-attention mechanism within the Spatial Transformer of the diffusion 2D-conditional UNet. Our analysis reveals a critical discrepancy between Zero-1-to-3's theoretical framework and its implementation, specifically in the processing of image-conditional context. We propose two significant improvements: (1) a corrected implementation that enables effective utilization of the cross-attention mechanism, and (2) an enhanced architecture that can leverage multiple conditional views simultaneously. Our theoretical analysis and preliminary results suggest potential improvements in novel view synthesis consistency and accuracy.

Multimodal Learning Analytics (MMLA) leverages advanced sensing technologies and artificial intelligence to capture complex learning processes, but integrating diverse data sources into cohesive insights remains challenging. This study introduces a novel methodology for integrating latent class analysis (LCA) within MMLA to map monomodal behavioural indicators into parsimonious multimodal ones. Using a high-fidelity healthcare simulation context, we collected positional, audio, and physiological data, deriving 17 monomodal indicators. LCA identified four distinct latent classes: Collaborative Communication, Embodied Collaboration, Distant Interaction, and Solitary Engagement, each capturing unique monomodal patterns. Epistemic network analysis compared these multimodal indicators with the original monomodal indicators and found that the multimodal approach was more parsimonious while offering higher explanatory power regarding students' task and collaboration performances. The findings highlight the potential of LCA in simplifying the analysis of complex multimodal data while capturing nuanced, cross-modality behaviours, offering actionable insights for educators and enhancing the design of collaborative learning interventions. This study proposes a pathway for advancing MMLA, making it more parsimonious and manageable, and aligning with the principles of learner-centred education.

This paper compares machine learning approaches with different input data formats for the classification of acoustic emission (AE) signals. AE signals are a promising monitoring technique in many structural health monitoring applications. Machine learning has been demonstrated as an effective data analysis method, classifying different AE signals according to the damage mechanism they represent. These classifications can be performed based on the entire AE waveform or specific features that have been extracted from it. However, it is currently unknown which of these approaches is preferred. With the goal of model deployment on resource-constrained embedded Internet of Things (IoT) systems, this work evaluates and compares both approaches in terms of classification accuracy, memory requirement, processing time, and energy consumption. To accomplish this, features are extracted and carefully selected, neural network models are designed and optimized for each input data scenario, and the models are deployed on a low-power IoT node. The comparative analysis reveals that all models can achieve high classification accuracies of over 99\%, but that embedded feature extraction is computationally expensive. Consequently, models utilizing the raw AE signal as input have the fastest processing speed and thus the lowest energy consumption, which comes at the cost of a larger memory requirement.

Out-of-Distribution (OOD) detection is crucial when deploying machine learning models in open-world applications. The core challenge in OOD detection is mitigating the model's overconfidence on OOD data. While recent methods using auxiliary outlier datasets or synthesizing outlier features have shown promising OOD detection performance, they are limited due to costly data collection or simplified assumptions. In this paper, we propose a novel OOD detection framework FodFoM that innovatively combines multiple foundation models to generate two types of challenging fake outlier images for classifier training. The first type is based on BLIP-2's image captioning capability, CLIP's vision-language knowledge, and Stable Diffusion's image generation ability. Jointly utilizing these foundation models constructs fake outlier images which are semantically similar to but different from in-distribution (ID) images. For the second type, GroundingDINO's object detection ability is utilized to help construct pure background images by blurring foreground ID objects in ID images. The proposed framework can be flexibly combined with multiple existing OOD detection methods. Extensive empirical evaluations show that image classifiers with the help of constructed fake images can more accurately differentiate real OOD images from ID ones. New state-of-the-art OOD detection performance is achieved on multiple benchmarks. The code is available at \url{https://github.com/Cverchen/ACMMM2024-FodFoM}.

Conversational agents are increasingly used in healthcare, and the integration of Large Language Models (LLMs) has significantly enhanced their capabilities. When integrated into social robots, LLMs offer the potential for more natural interactions. However, while LLMs promise numerous benefits, they also raise critical ethical concerns, particularly around the issue of hallucinations and deceptive patterns. In this case study, we observed a critical pattern of deceptive behavior in commercially available LLM-based care software integrated into robots. The LLM-equipped robot falsely claimed to have medication reminder functionalities. Not only did these systems assure users of their ability to manage medication schedules, but they also proactively suggested this capability, despite lacking it. This deceptive behavior poses significant risks in healthcare environments, where reliability is paramount. Our findings highlights the ethical and safety concerns surrounding the deployment of LLM-integrated robots in healthcare, emphasizing the need for oversight to prevent potentially harmful consequences for vulnerable populations.

We consider the problem of learning an arbitrarily-biased ReLU activation (or neuron) over Gaussian marginals with the squared loss objective. Despite the ReLU neuron being the basic building block of modern neural networks, we still do not understand the basic algorithmic question of whether one arbitrary ReLU neuron is learnable in the non-realizable setting. In particular, all existing polynomial time algorithms only provide approximation guarantees for the better-behaved unbiased setting or restricted bias setting. Our main result is a polynomial time statistical query (SQ) algorithm that gives the first constant factor approximation for arbitrary bias. It outputs a ReLU activation that achieves a loss of $O(\mathrm{OPT}) + \varepsilon$ in time $\mathrm{poly}(d,1/\varepsilon)$, where $\mathrm{OPT}$ is the loss obtained by the optimal ReLU activation. Our algorithm presents an interesting departure from existing algorithms, which are all based on gradient descent and thus fall within the class of correlational statistical query (CSQ) algorithms. We complement our algorithmic result by showing that no polynomial time CSQ algorithm can achieve a constant factor approximation. Together, these results shed light on the intrinsic limitation of gradient descent, while identifying arguably the simplest setting (a single neuron) where there is a separation between SQ and CSQ algorithms.

A large body of work in the statistics and computer science communities dating back to Huber (Huber, 1960) has led to statistically and computationally efficient outlier-robust estimators. Two particular outlier models have received significant attention: the adversarial and heavy-tailed models. While the former models outliers as the result of a malicious adversary manipulating the data, the latter relaxes distributional assumptions on the data allowing outliers to naturally occur as part of the data generating process. In the first setting, the goal is to develop estimators robust to the largest fraction of outliers while in the second, one seeks estimators to combat the loss of statistical efficiency, where the dependence on the failure probability is paramount. Despite these distinct motivations, the algorithmic approaches to both these settings have converged, prompting questions on the relationship between the models. In this paper, we investigate and provide a principled explanation for this phenomenon. First, we prove that any adversarially robust estimator is also resilient to heavy-tailed outliers for any statistical estimation problem with i.i.d data. As a corollary, optimal adversarially robust estimators for mean estimation, linear regression, and covariance estimation are also optimal heavy-tailed estimators. Conversely, for arguably the simplest high-dimensional estimation task of mean estimation, we construct heavy-tailed estimators whose application to the adversarial setting requires any black-box reduction to remove almost all the outliers in the data. Taken together, our results imply that heavy-tailed estimation is likely easier than adversarially robust estimation opening the door to novel algorithmic approaches for the heavy-tailed setting. Additionally, confidence intervals obtained for adversarially robust estimation also hold with high-probability.

Knowledge Graph Embedding models, representing entities and edges in a low-dimensional space, have been extremely successful at solving tasks related to completing and exploring Knowledge Graphs (KGs). One of the key aspects of training most of these models is teaching to discriminate between true statements positives and false ones (negatives). However, the way in which negatives can be defined is not trivial, as facts missing from the KG are not necessarily false and a set of ground truth negatives is hardly ever given. This makes synthetic negative generation a necessity. Different generation strategies can heavily affect the quality of the embeddings, making it a primary aspect to consider. We revamp a strategy that generates corruptions during training respecting the domain and range of relations, we extend its capabilities and we show our methods bring substantial improvement (+10% MRR) for standard benchmark datasets and over +150% MRR for a larger ontology-backed dataset.

While large language models (LLMs) showcase unprecedented capabilities, they also exhibit certain inherent limitations when facing seemingly trivial tasks. A prime example is the recently debated "reversal curse", which surfaces when models, having been trained on the fact "A is B", struggle to generalize this knowledge to infer that "B is A". In this paper, we examine the manifestation of the reversal curse across various tasks and delve into both the generalization abilities and the problem-solving mechanisms of LLMs. This investigation leads to a series of significant insights: (1) LLMs are able to generalize to "B is A" when both A and B are presented in the context as in the case of a multiple-choice question. (2) This generalization ability is highly correlated to the structure of the fact "A is B" in the training documents. For example, this generalization only applies to biographies structured in "[Name] is [Description]" but not to "[Description] is [Name]". (3) We propose and verify the hypothesis that LLMs possess an inherent bias in fact recalling during knowledge application, which explains and underscores the importance of the document structure to successful learning. (4) The negative impact of this bias on the downstream performance of LLMs can hardly be mitigated through training alone. These findings offer a novel perspective on interpreting LLMs' generalization through their intrinsic mechanisms and provide insights for developing more effective learning methods. Our code and data are available at https://github.com/alibaba/thinking_bias.git.

The spatial and temporal distribution of precipitation has a significant impact on human lives by determining freshwater resources and agricultural yield, but also rainfall-driven hazards like flooding or landslides. While the ERA5 reanalysis dataset provides consistent long-term global precipitation information that allows investigations of these impacts, it lacks the resolution to capture the high spatio-temporal variability of precipitation. ERA5 misses intense local rainfall events that are crucial drivers of devastating flooding - a critical limitation since extreme weather events become increasingly frequent. Here, we introduce spateGAN-ERA5, the first deep learning based spatio-temporal downscaling of precipitation data on a global scale. SpateGAN-ERA5 uses a conditional generative adversarial neural network (cGAN) that enhances the resolution of ERA5 precipitation data from 24 km and 1 hour to 2 km and 10 minutes, delivering high-resolution rainfall fields with realistic spatio-temporal patterns and accurate rain rate distribution including extremes. Its computational efficiency enables the generation of a large ensemble of solutions, addressing uncertainties inherent to the challenges of downscaling. Trained solely on data from Germany and validated in the US and Australia considering diverse climate zones, spateGAN-ERA5 demonstrates strong generalization indicating a robust global applicability. SpateGAN-ERA5 fulfils a critical need for high-resolution precipitation data in hydrological and meteorological research, offering new capabilities for flood risk assessment, AI-enhanced weather forecasting, and impact modelling to address climate-driven challenges worldwide.