THEME : Enhancing Thematic Investing with Semantic Stock Representations and Temporal Dynamics

Thematic investing aims to construct portfolios aligned with structural trends, yet selecting relevant stocks remains challenging due to overlapping sector boundaries and evolving market dynamics. To address this challenge, we construct the Thematic Representation Set (TRS), an extended dataset that begins with real-world thematic ETFs and expands upon them by incorporating industry classifications and financial news to overcome their coverage limitations. The final dataset contains both the explicit mapping of themes to their constituent stocks and the rich textual profiles for each. Building on this dataset, we introduce \textsc{THEME}, a hierarchical contrastive learning framework. By representing the textual profiles of themes and stocks as embeddings, \textsc{THEME} first leverages their hierarchical relationship to achieve semantic alignment. Subsequently, it refines these semantic embeddings through a temporal refinement stage that incorporates individual stock returns. The final stock representations are designed for effective retrieval of thematically aligned assets with strong return potential. Empirical results show that \textsc{THEME} outperforms strong baselines across multiple retrieval metrics and significantly improves performance in portfolio construction. By jointly modeling thematic relationships from text and market dynamics from returns, \textsc{THEME} provides a scalable and adaptive solution for navigating complex investment themes.

ACM Multimedia Grand Challenge on ENT Endoscopy Analysis

Automated analysis of endoscopic imagery is a critical yet underdeveloped component of ENT (ear, nose, and throat) care, hindered by variability in devices and operators, subtle and localized findings, and fine-grained distinctions such as laterality and vocal-fold state. In addition to classification, clinicians require reliable retrieval of similar cases, both visually and through concise textual descriptions. These capabilities are rarely supported by existing public benchmarks. To this end, we introduce ENTRep, the ACM Multimedia 2025 Grand Challenge on ENT endoscopy analysis, which integrates fine-grained anatomical classification with image-to-image and text-to-image retrieval under bilingual (Vietnamese and English) clinical supervision. Specifically, the dataset comprises expert-annotated images, labeled for anatomical region and normal or abnormal status, and accompanied by dual-language narrative descriptions. In addition, we define three benchmark tasks, standardize the submission protocol, and evaluate performance on public and private test splits using server-side scoring. Moreover, we report results from the top-performing teams and provide an insight discussion.

Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval

Recently, prompt learning has demonstrated remarkable success in adapting pre-trained Vision-Language Models (VLMs) to various downstream tasks such as image classification. However, its application to the downstream Image-Text Retrieval (ITR) task is more challenging. We find that the challenge lies in discriminating both fine-grained attributes and similar subcategories of the downstream data. To address this challenge, we propose Dual prompt Learning with Joint Category-Attribute Reweighting (DCAR), a novel dual-prompt learning framework to achieve precise image-text matching. The framework dynamically adjusts prompt vectors from both semantic and visual dimensions to improve the performance of CLIP on the downstream ITR task. Based on the prompt paradigm, DCAR jointly optimizes attribute and class features to enhance fine-grained representation learning. Specifically, (1) at the attribute level, it dynamically updates the weights of attribute descriptions based on text-image mutual information correlation; (2) at the category level, it introduces negative samples from multiple perspectives with category-matching weighting to learn subcategory distinctions. To validate our method, we construct the Fine-class Described Retrieval Dataset (FDRD), which serves as a challenging benchmark for ITR in downstream data domains. It covers over 1,500 downstream fine categories and 230,000 image-caption pairs with detailed attribute annotations. Extensive experiments on FDRD demonstrate that DCAR achieves state-of-the-art performance over existing baselines.

Context Steering: A New Paradigm for Compression-based Embeddings by Synthesizing Relevant Information Features

Compression-based distances (CD) offer a flexible and domain-agnostic means of measuring similarity by identifying implicit information through redundancies between data objects. However, as similarity features are derived from the data, rather than defined as an input, it often proves difficult to align with the task at hand, particularly in complex clustering or classification settings. To address this issue, we introduce "context steering," a novel methodology that actively guides the feature-shaping process. Instead of passively accepting the emergent data structure (typically a hierarchy derived from clustering CDs), our approach "steers" the process by systematically analyzing how each object influences the relational context within a clustering framework. This process generates a custom-tailored embedding that isolates and amplifies class-distinctive information. We validate the capabilities of this strategy using Normalized Compression Distance (NCD) and Relative Compression Distance (NRC) with common hierarchical clustering, providing an effective alternative to common transductive methods. Experimental results across heterogeneous datasets-from text to real-world audio-validate the robustness and generality of context steering, marking a fundamental shift in their application: from merely discovering inherent data structures to actively shaping a feature space tailored to a specific objective.

Improving Audio Classification by Transitioning from Zero- to Few-Shot

State-of-the-art audio classification often employs a zero-shot approach, which involves comparing audio embeddings with embeddings from text describing the respective audio class. These embeddings are usually generated by neural networks trained through contrastive learning to align audio and text representations. Identifying the optimal text description for an audio class is challenging, particularly when the class comprises a wide variety of sounds. This paper examines few-shot methods designed to improve classification accuracy beyond the zero-shot approach. Specifically, audio embeddings are grouped by class and processed to replace the inherently noisy text embeddings. Our results demonstrate that few-shot classification typically outperforms the zero-shot baseline.

Interpreting Fedspeak with Confidence: A LLM-Based Uncertainty-Aware Framework Guided by Monetary Policy Transmission Paths

"Fedspeak", the stylized and often nuanced language used by the U.S. Federal Reserve, encodes implicit policy signals and strategic stances. The Federal Open Market Committee strategically employs Fedspeak as a communication tool to shape market expectations and influence both domestic and global economic conditions. As such, automatically parsing and interpreting Fedspeak presents a high-impact challenge, with significant implications for financial forecasting, algorithmic trading, and data-driven policy analysis. In this paper, we propose an LLM-based, uncertainty-aware framework for deciphering Fedspeak and classifying its underlying monetary policy stance. Technically, to enrich the semantic and contextual representation of Fedspeak texts, we incorporate domain-specific reasoning grounded in the monetary policy transmission mechanism. We further introduce a dynamic uncertainty decoding module to assess the confidence of model predictions, thereby enhancing both classification accuracy and model reliability. Experimental results demonstrate that our framework achieves state-of-the-art performance on the policy stance analysis task. Moreover, statistical analysis reveals a significant positive correlation between perceptual uncertainty and model error rates, validating the effectiveness of perceptual uncertainty as a diagnostic signal.

Freeze and Reveal: Exposing Modality Bias in Vision-Language Models

Vision Language Models achieve impressive multi-modal performance but often inherit gender biases from their training data. This bias might be coming from both the vision and text modalities. In this work, we dissect the contributions of vision and text backbones to these biases by applying targeted debiasing using Counterfactual Data Augmentation and Task Vector methods. Inspired by data-efficient approaches in hate-speech classification, we introduce a novel metric, Degree of Stereotypicality and a corresponding debiasing method, Data Augmentation Using Degree of Stereotypicality - DAUDoS, to reduce bias with minimal computational cost. We curate a gender annotated dataset and evaluate all methods on VisoGender benchmark to quantify improvements and identify dominant source of bias. Our results show that CDA reduces the gender gap by 6% and DAUDoS by 3% but using only one-third of the data. Both methods also improve the model's ability to correctly identify gender in images by 3%, with DAUDoS achieving this improvement using only almost one-third of training data. From our experiment's, we observed that CLIP's vision encoder is more biased whereas PaliGemma2's text encoder is more biased. By identifying whether bias stems more from vision or text encoders, our work enables more targeted and effective bias mitigation strategies in future multi-modal systems.

Multimodal Fact Checking with Unified Visual, Textual, and Contextual Representations

The growing rate of multimodal misinformation, where claims are supported by both text and images, poses significant challenges to fact-checking systems that rely primarily on textual evidence. In this work, we have proposed a unified framework for fine-grained multimodal fact verification called "MultiCheck", designed to reason over structured textual and visual signals. Our architecture combines dedicated encoders for text and images with a fusion module that captures cross-modal relationships using element-wise interactions. A classification head then predicts the veracity of a claim, supported by a contrastive learning objective that encourages semantic alignment between claim-evidence pairs in a shared latent space. We evaluate our approach on the Factify 2 dataset, achieving a weighted F1 score of 0.84, substantially outperforming the baseline. These results highlight the effectiveness of explicit multimodal reasoning and demonstrate the potential of our approach for scalable and interpretable fact-checking in complex, real-world scenarios.

Detecting Reading-Induced Confusion Using EEG and Eye Tracking

Humans regularly navigate an overwhelming amount of information via text media, whether reading articles, browsing social media, or interacting with chatbots. Confusion naturally arises when new information conflicts with or exceeds a reader's comprehension or prior knowledge, posing a challenge for learning. In this study, we present a multimodal investigation of reading-induced confusion using EEG and eye tracking. We collected neural and gaze data from 11 adult participants as they read short paragraphs sampled from diverse, real-world sources. By isolating the N400 event-related potential (ERP), a well-established neural marker of semantic incongruence, and integrating behavioral markers from eye tracking, we provide a detailed analysis of the neural and behavioral correlates of confusion during naturalistic reading. Using machine learning, we show that multimodal (EEG + eye tracking) models improve classification accuracy by 4-22% over unimodal baselines, reaching an average weighted participant accuracy of 77.3% and a best accuracy of 89.6%. Our results highlight the dominance of the brain's temporal regions in these neural signatures of confusion, suggesting avenues for wearable, low-electrode brain-computer interfaces (BCI) for real-time monitoring. These findings lay the foundation for developing adaptive systems that dynamically detect and respond to user confusion, with potential applications in personalized learning, human-computer interaction, and accessibility.

EPIC: Efficient Prompt Interaction for Text-Image Classification

In recent years, large-scale pre-trained multimodal models (LMMs) generally emerge to integrate the vision and language modalities, achieving considerable success in multimodal tasks, such as text-image classification. The growing size of LMMs, however, results in a significant computational cost for fine-tuning these models for downstream tasks. Hence, prompt-based interaction strategy is studied to align modalities more efficiently. In this context, we propose a novel efficient prompt-based multimodal interaction strategy, namely Efficient Prompt Interaction for text-image Classification (EPIC). Specifically, we utilize temporal prompts on intermediate layers, and integrate different modalities with similarity-based prompt interaction, to leverage sufficient information exchange between modalities. Utilizing this approach, our method achieves reduced computational resource consumption and fewer trainable parameters (about 1\% of the foundation model) compared to other fine-tuning strategies. Furthermore, it demonstrates superior performance on the UPMC-Food101 and SNLI-VE datasets, while achieving comparable performance on the MM-IMDB dataset.