Characters are important in narratives. They move the plot forward, create emotional connections, and embody the story's themes. Visual storytelling methods focus more on the plot and events relating to it, without building the narrative around specific characters. As a result, the generated stories feel generic, with character mentions being absent, vague, or incorrect. To mitigate these issues, we introduce the new task of character-centric story generation and present the first model capable of predicting visual stories with consistently grounded and coreferent character mentions. Our model is finetuned on a new dataset which we build on top of the widely used VIST benchmark. Specifically, we develop an automated pipeline to enrich VIST with visual and textual character coreference chains. We also propose new evaluation metrics to measure the richness of characters and coreference in stories. Experimental results show that our model generates stories with recurring characters which are consistent and coreferent to larger extent compared to baselines and state-of-the-art systems.

In this report, we present our first-place solution to the Multiple-choice Video Question Answering (QA) track of The Second Perception Test Challenge. This competition posed a complex video understanding task, requiring models to accurately comprehend and answer questions about video content. To address this challenge, we leveraged the powerful QwenVL2 (7B) model and fine-tune it on the provided training set. Additionally, we employed model ensemble strategies and Test Time Augmentation to boost performance. Through continuous optimization, our approach achieved a Top-1 Accuracy of 0.7647 on the leaderboard.

Recent advancements in computer vision, particularly in detection, segmentation, and classification, have significantly impacted various domains. However, these advancements are tied to RGB-based systems, which are insufficient for applications in industries like waste sorting, pharmaceuticals, and defense, where advanced object characterization beyond shape or color is necessary. Hyperspectral (HS) imaging, capturing both spectral and spatial information, addresses these limitations and offers advantages over conventional technologies such as X-ray fluorescence and Raman spectroscopy, particularly in terms of speed, cost, and safety. This study evaluates the potential of combining HS imaging with deep learning for material characterization. The research involves: i) designing an experimental setup with HS camera, conveyor, and controlled lighting; ii) generating a multi-object dataset of various plastics (HDPE, PET, PP, PS) with semi-automated mask generation and Raman spectroscopy-based labeling; and iii) developing a deep learning model trained on HS images for pixel-level material classification. The model achieved 99.94\% classification accuracy, demonstrating robustness in color, size, and shape invariance, and effectively handling material overlap. Limitations, such as challenges with black objects, are also discussed. Extending computer vision beyond RGB to HS imaging proves feasible, overcoming major limitations of traditional methods and showing strong potential for future applications.

Large Language Models (LLMs) are increasingly being used to generate text across various languages, for tasks such as translation, customer support, and education. Despite these advancements, LLMs show notable gender biases in English, which become even more pronounced when generating content in relatively underrepresented languages like Hindi. This study explores implicit gender biases in Hindi text generation and compares them to those in English. We developed Hindi datasets inspired by WinoBias to examine stereotypical patterns in responses from models like GPT-4o and Claude-3 sonnet. Our results reveal a significant gender bias of 87.8% in Hindi, compared to 33.4% in English GPT-4o generation, with Hindi responses frequently relying on gender stereotypes related to occupations, power hierarchies, and social class. This research underscores the variation in gender biases across languages and provides considerations for navigating these biases in generative AI systems.

The misuse of deep learning-based facial manipulation poses a potential threat to civil rights. To prevent this fraud at its source, proactive defense technology was proposed to disrupt the manipulation process by adding invisible adversarial perturbations into images, making the forged output unconvincing to the observer. However, their non-directional disruption of the output may result in the retention of identity information of the person in the image, leading to stigmatization of the individual. In this paper, we propose a novel universal framework for combating facial manipulation, called ID-Guard. Specifically, this framework requires only a single forward pass of an encoder-decoder network to generate a cross-model universal adversarial perturbation corresponding to a specific facial image. To ensure anonymity in manipulated facial images, a novel Identity Destruction Module (IDM) is introduced to destroy the identifiable information in forged faces targetedly. Additionally, we optimize the perturbations produced by considering the disruption towards different facial manipulations as a multi-task learning problem and design a dynamic weights strategy to improve cross-model performance. The proposed framework reports impressive results in defending against multiple widely used facial manipulations, effectively distorting the identifiable regions in the manipulated facial images. In addition, our experiments reveal the ID-Guard's ability to enable disrupted images to avoid face inpaintings and open-source image recognition systems.

Contribution: This Full paper in the Research Category track describes a practical, scalable platform that seamlessly integrates Generative AI (GenAI) with online educational forums, offering a novel approach to augment the instructional capabilities of staff. The platform empowers instructional staff to efficiently manage, refine, and approve responses by facilitating interaction between student posts and a Large Language Model (LLM). This contribution enhances the efficiency and effectiveness of instructional support and significantly improves the quality and speed of responses provided to students, thereby enriching the overall learning experience. Background: Grounded in Vygotsky's socio-cultural theory and the concept of the More Knowledgeable Other (MKO), the study examines how GenAI can act as an auxiliary MKO to enrich educational dialogue between students and instructors. Research Question: How effective is GenAI in reducing the workload of instructional staff when used to pre-answer student questions posted on educational discussion forums? Methodology: Using a mixed-methods approach in large introductory programming courses, human Teaching Assistants (AI-TAs) employed an AI-assisted platform to pre-answer student queries. We analyzed efficiency indicators like the frequency of modifications to AI-generated responses and gathered qualitative feedback from AI-TAs. Findings: The findings indicate no significant difference in student reception to responses generated by AI-TAs compared to those provided by human instructors. This suggests that GenAI can effectively meet educational needs when adequately managed. Moreover, AI-TAs experienced a reduction in the cognitive load required for responding to queries, pointing to GenAI's potential to enhance instructional efficiency without compromising the quality of education.

Recent years have been marked with the fast-pace diversification and increasing ubiquity of machine learning applications. Yet, a firm theoretical understanding of the surprising efficiency of neural networks to learn from high-dimensional data still proves largely elusive. In this endeavour, analyses inspired by statistical physics have proven instrumental, enabling the tight asymptotic characterization of the learning of neural networks in high dimensions, for a broad class of solvable models. This manuscript reviews the tools and ideas underlying recent progress in this line of work. We introduce a generic model -- the sequence multi-index model -- which encompasses numerous previously studied models as special instances. This unified framework covers a broad class of machine learning architectures with a finite number of hidden units, including multi-layer perceptrons, autoencoders, attention mechanisms; and tasks, including (un)supervised learning, denoising, contrastive learning, in the limit of large data dimension, and comparably large number of samples. We explicate in full detail the analysis of the learning of sequence multi-index models, using statistical physics techniques such as the replica method and approximate message-passing algorithms. This manuscript thus provides a unified presentation of analyses reported in several previous works, and a detailed overview of central techniques in the field of statistical physics of machine learning. This review should be a useful primer for machine learning theoreticians curious of statistical physics approaches; it should also be of value to statistical physicists interested in the transfer of such ideas to the study of neural networks.

In the rapidly evolving field of financial sentiment analysis, the efficiency and accuracy of predictive models are critical due to their significant impact on financial markets. Transformer based models like BERT and large language models (LLMs) like GPT-4, have advanced NLP tasks considerably. Despite their advantages, BERT-based models face challenges with computational intensity in edge computing environments, and the substantial size and compute requirements of LLMs limit their practical deployment. This study proposes leveraging the generative capabilities of LLMs, such as GPT-4 Omni, to create synthetic, domain-specific training data. This approach addresses the challenge of data scarcity and enhances the performance of smaller models by making them competitive with their larger counterparts. The research specifically aims to enhance FinBERT, a BERT model fine-tuned for financial sentiment analysis, and develop TinyFinBERT, a compact transformer model, through a structured, two-tiered knowledge distillation strategy. Using data augmented by GPT-4 Omni, which involves generating new training examples and transforming existing data, we significantly improved the accuracy of FinBERT, preparing it to serve as a teacher model. This enhanced FinBERT then distilled knowledge to TinyFinBERT, employing both GPT-4 Omni and GPT-3.5 Turbo augmented data. The distillation strategy incorporated both logit and intermediate layer distillation. The training and evaluation of TinyFinBERT utilized the PhraseBank dataset and the FiQA 2018 Task1 dataset, achieving performance comparable to FinBERT while being substantially smaller and more efficient. This research demonstrates how LLMs can effectively contribute to the advancement of financial sentiment analysis by enhancing the capabilities of smaller, more efficient models through innovative data augmentation and distillation techniques.

As audio machine learning outcomes are deployed in societally impactful applications, it is important to have a sense of the quality and origins of the data used. Noticing that being explicit about this sense is not trivially rewarded in academic publishing in applied machine learning domains, and neither is included in typical applied machine learning curricula, we present a study into dataset usage connected to the top-5 cited papers at the International Conference on Acoustics, Speech, and Signal Processing (ICASSP). In this, we conduct thorough depth-first analyses towards origins of used datasets, often leading to searches that had to go beyond what was reported in official papers, and ending into unclear or entangled origins. Especially in the current pull towards larger, and possibly generative AI models, awareness of the need for accountability on data provenance is increasing. With this, we call on the community to not only focus on engineering larger models, but create more room and reward for explicitizing the foundations on which such models should be built.

Generative models aim to learn the distribution of datasets, such as images, so as to be able to generate samples that statistically resemble real data. However, learning the underlying probability distribution can be very challenging and intractable. To this end, we introduce an approach which employs the characteristic function (CF), a probabilistic descriptor that directly corresponds to the distribution. However, unlike the probability density function (pdf), the characteristic function not only always exists, but also provides an additional degree of freedom, hence enhances flexibility in learning distributions. This removes the critical dependence on pdf-based assumptions, which limit the applicability of traditional methods. While several works have attempted to use CF in generative modeling, they often impose strong constraints on the training process. In contrast, our approach calculates the distance between query points in the CF domain, which is an unconstrained and well defined problem. Next, to deal with the sampling strategy, which is crucial to model performance, we propose a graph neural network (GNN)-based optimizer for the sampling process, which identifies regions where the difference between CFs is most significant. In addition, our method allows the use of a pre-trained model, such as a well-trained autoencoder, and is capable of learning directly in its feature space, without modifying its parameters. This offers a flexible and robust approach to generative modeling, not only provides broader applicability and improved performance, but also equips any latent space world with the ability to become a generative model.