EchoVLM: Measurement-Grounded Multimodal Learning for Echocardiography

Echocardiography is the most widely used imaging modality in cardiology, yet its interpretation remains labor-intensive and inherently multimodal, requiring view recognition, quantitative measurements, qualitative assessments, and guideline-based reasoning. While recent vision-language models (VLMs) have achieved broad success in natural images and certain medical domains, their potential in echocardiography has been limited by the lack of large-scale, clinically grounded image-text datasets and the absence of measurement-based reasoning central to echo interpretation. We introduce EchoGround-MIMIC, the first measurement-grounded multimodal echocardiography dataset, comprising 19,065 image-text pairs from 1,572 patients with standardized views, structured measurements, measurement-grounded captions, and guideline-derived disease labels. Building on this resource, we propose EchoVLM, a vision-language model that incorporates two novel pretraining objectives: (i) a view-informed contrastive loss that encodes the view-dependent structure of echocardiographic imaging, and (ii) a negation-aware contrastive loss that distinguishes clinically critical negative from positive findings. Across five types of clinical applications with 36 tasks spanning multimodal disease classification, image-text retrieval, view classification, chamber segmentation, and landmark detection, EchoVLM achieves state-of-the-art performance (86.5% AUC in zero-shot disease classification and 95.1% accuracy in view classification). We demonstrate that clinically grounded multimodal pretraining yields transferable visual representations and establish EchoVLM as a foundation model for end-to-end echocardiography interpretation. We will release EchoGround-MIMIC and the data curation code, enabling reproducibility and further research in multimodal echocardiography interpretation.

The Effect of Negation on CLIP in Medical Imaging: Limitations of Contrastive Language-Image Pretraining

Large vision-language models like CLIP are increasingly used in medical imaging tasks due to their ability to align images and text without the need for extensive labeled data. This makes them particularly useful for applications like image retrieval, report generation, and classification in clinical settings. A potential issue to this approach is that CLIP-based models often under perform when interpreting negated phrases, which is especially problematic in the context of medical diagnosing. In this study, we evaluate the Stanford AIMI CheXagent model on its ability to correctly retrieve chest X-ray images using prompts with and without negation. The goal of this project is to understand where this model fails and then use it as a base model to improve its retrieval accuracy by fine tuning methods outlined in previous work. Results from this study show improvement in handling of negation in the CLIP model with a slight decrease in accuracy of positive prompt evaluation. Alongside retrieval accuracy, we examined internal model behavior through token attribution, t-SNE projection, and attention-head ablation to better characterize how each fine tuning approach reshaped the text encoders representation of negated clinical language. Through this work, we hope to better understand the internal behavior of CLIP and improve its handling of negation using clinically relevant language for improving its reliability in medical AI devices.

High-Dimensional Data Processing: Benchmarking Machine Learning and Deep Learning Architectures in Local and Distributed Environments

This document reports the sequence of practices and methodologies implemented during the Big Data course. It details the workflow beginning with the processing of the Epsilon dataset through group and individual strategies, followed by text analysis and classification with RestMex and movie feature analysis with IMDb. Finally, it describes the technical implementation of a distributed computing cluster with Apache Spark on Linux using Scala.

Decoding Fake Narratives in Spreading Hateful Stories: A Dual-Head RoBERTa Model with Multi-Task Learning

Social media platforms, while enabling global connectivity, have become hubs for the rapid spread of harmful content, including hate speech and fake narratives \cite{davidson2017automated, shu2017fake}. The Faux-Hate shared task focuses on detecting a specific phenomenon: the generation of hate speech driven by fake narratives, termed Faux-Hate. Participants are challenged to identify such instances in code-mixed Hindi-English social media text. This paper describes our system developed for the shared task, addressing two primary sub-tasks: (a) Binary Faux-Hate detection, involving fake and hate speech classification, and (b) Target and Severity prediction, categorizing the intended target and severity of hateful content. Our approach combines advanced natural language processing techniques with domain-specific pretraining to enhance performance across both tasks. The system achieved competitive results, demonstrating the efficacy of leveraging multi-task learning for this complex problem.

Why Text Prevails: Vision May Undermine Multimodal Medical Decision Making

With the rapid progress of large language models (LLMs), advanced multimodal large language models (MLLMs) have demonstrated impressive zero-shot capabilities on vision-language tasks. In the biomedical domain, however, even state-of-the-art MLLMs struggle with basic Medical Decision Making (MDM) tasks. We investigate this limitation using two challenging datasets: (1) three-stage Alzheimer's disease (AD) classification (normal, mild cognitive impairment, dementia), where category differences are visually subtle, and (2) MIMIC-CXR chest radiograph classification with 14 non-mutually exclusive conditions. Our empirical study shows that text-only reasoning consistently outperforms vision-only or vision-text settings, with multimodal inputs often performing worse than text alone. To mitigate this, we explore three strategies: (1) in-context learning with reason-annotated exemplars, (2) vision captioning followed by text-only inference, and (3) few-shot fine-tuning of the vision tower with classification supervision. These findings reveal that current MLLMs lack grounded visual understanding and point to promising directions for improving multimodal decision making in healthcare.

BrepLLM: Native Boundary Representation Understanding with Large Language Models

Current token-sequence-based Large Language Models (LLMs) are not well-suited for directly processing 3D Boundary Representation (Brep) models that contain complex geometric and topological information. We propose BrepLLM, the first framework that enables LLMs to parse and reason over raw Brep data, bridging the modality gap between structured 3D geometry and natural language. BrepLLM employs a two-stage training pipeline: Cross-modal Alignment Pre-training and Multi-stage LLM Fine-tuning. In the first stage, an adaptive UV sampling strategy converts Breps into graphs representation with geometric and topological information. We then design a hierarchical BrepEncoder to extract features from geometry (i.e., faces and edges) and topology, producing both a single global token and a sequence of node tokens. Then we align the global token with text embeddings from a frozen CLIP text encoder (ViT-L/14) via contrastive learning. In the second stage, we integrate the pretrained BrepEncoder into an LLM. We then align its sequence of node tokens using a three-stage progressive training strategy: (1) training an MLP-based semantic mapping from Brep representation to 2D with 2D-LLM priors. (2) performing fine-tuning of the LLM. (3) designing a Mixture-of-Query Experts (MQE) to enhance geometric diversity modeling. We also construct Brep2Text, a dataset comprising 269,444 Brep-text question-answer pairs. Experiments show that BrepLLM achieves state-of-the-art (SOTA) results on 3D object classification and captioning tasks.

Leveraging Text Guidance for Enhancing Demographic Fairness in Gender Classification

In the quest for fairness in artificial intelligence, novel approaches to enhance it in facial image based gender classification algorithms using text guided methodologies are presented. The core methodology involves leveraging semantic information from image captions during model training to improve generalization capabilities. Two key strategies are presented: Image Text Matching (ITM) guidance and Image Text fusion. ITM guidance trains the model to discern fine grained alignments between images and texts to obtain enhanced multimodal representations. Image text fusion combines both modalities into comprehensive representations for improved fairness. Exensive experiments conducted on benchmark datasets demonstrate these approaches effectively mitigate bias and improve accuracy across gender racial groups compared to existing methods. Additionally, the unique integration of textual guidance underscores an interpretable and intuitive training paradigm for computer vision systems. By scrutinizing the extent to which semantic information reduces disparities, this research offers valuable insights into cultivating more equitable facial analysis algorithms. The proposed methodologies contribute to addressing the pivotal challenge of demographic bias in gender classification from facial images. Furthermore, this technique operates in the absence of demographic labels and is application agnostic.

PathFLIP: Fine-grained Language-Image Pretraining for Versatile Computational Pathology

While Vision-Language Models (VLMs) have achieved notable progress in computational pathology (CPath), the gigapixel scale and spatial heterogeneity of Whole Slide Images (WSIs) continue to pose challenges for multimodal understanding. Existing alignment methods struggle to capture fine-grained correspondences between textual descriptions and visual cues across thousands of patches from a slide, compromising their performance on downstream tasks. In this paper, we propose PathFLIP (Pathology Fine-grained Language-Image Pretraining), a novel framework for holistic WSI interpretation. PathFLIP decomposes slide-level captions into region-level subcaptions and generates text-conditioned region embeddings to facilitate precise visual-language grounding. By harnessing Large Language Models (LLMs), PathFLIP can seamlessly follow diverse clinical instructions and adapt to varied diagnostic contexts. Furthermore, it exhibits versatile capabilities across multiple paradigms, efficiently handling slide-level classification and retrieval, fine-grained lesion localization, and instruction following. Extensive experiments demonstrate that PathFLIP outperforms existing large-scale pathological VLMs on four representative benchmarks while requiring significantly less training data, paving the way for fine-grained, instruction-aware WSI interpretation in clinical practice.

Topic Discovery and Classification for Responsible Generative AI Adaptation in Higher Education

As generative artificial intelligence (GenAI) becomes increasingly capable of delivering personalized learning experiences and real-time feedback, a growing number of students are incorporating these tools into their academic workflows. They use GenAI to clarify concepts, solve complex problems, and, in some cases, complete assignments by copying and pasting model-generated contents. While GenAI has the potential to enhance learning experience, it also raises concerns around misinformation, hallucinated outputs, and its potential to undermine critical thinking and problem-solving skills. In response, many universities, colleges, departments, and instructors have begun to develop and adopt policies to guide responsible integration of GenAI into learning environments. However, these policies vary widely across institutions and contexts, and their evolving nature often leaves students uncertain about expectations and best practices. To address this challenge, the authors designed and implemented an automated system for discovering and categorizing AI-related policies found in course syllabi and institutional policy websites. The system combines unsupervised topic modeling techniques to identify key policy themes with large language models (LLMs) to classify the level of GenAI allowance and other requirements in policy texts. The developed application achieved a coherence score of 0.73 for topic discovery. In addition, GPT-4.0-based classification of policy categories achieved precision between 0.92 and 0.97, and recall between 0.85 and 0.97 across eight identified topics. By providing structured and interpretable policy information, this tool promotes the safe, equitable, and pedagogically aligned use of GenAI technologies in education. Furthermore, the system can be integrated into educational technology platforms to help students understand and comply with relevant guidelines.

Confidence-Credibility Aware Weighted Ensembles of Small LLMs Outperform Large LLMs in Emotion Detection

This paper introduces a confidence-weighted, credibility-aware ensemble framework for text-based emotion detection, inspired by Condorcet's Jury Theorem (CJT). Unlike conventional ensembles that often rely on homogeneous architectures, our approach combines architecturally diverse small transformer-based large language models (sLLMs) - BERT, RoBERTa, DistilBERT, DeBERTa, and ELECTRA, each fully fine-tuned for emotion classification. To preserve error diversity, we minimize parameter convergence while taking advantage of the unique biases of each model. A dual-weighted voting mechanism integrates both global credibility (validation F1 score) and local confidence (instance-level probability) to dynamically weight model contributions. Experiments on the DAIR-AI dataset demonstrate that our credibility-confidence ensemble achieves a macro F1 score of 93.5 percent, surpassing state-of-the-art benchmarks and significantly outperforming large-scale LLMs, including Falcon, Mistral, Qwen, and Phi, even after task-specific Low-Rank Adaptation (LoRA). With only 595M parameters in total, our small LLMs ensemble proves more parameter-efficient and robust than models up to 7B parameters, establishing that carefully designed ensembles of small, fine-tuned models can outperform much larger LLMs in specialized natural language processing (NLP) tasks such as emotion detection.