Multimodal Contrastive Learning

In this study, we propose an enhancement to the similarity computation mechanism in multimodal contrastive pretraining frameworks such as CLIP. Prior theoretical research has demonstrated that the optimal similarity metrics between paired modalities should correspond to the pointwise mutual information (PMI) between the two modalities. However, the current implementations of CLIP and its variants fail to fully utilize the underlying linear structure of PMI. We therefore propose KME-CLIP, which leverages this structure through the inner product in a reproducing kernel Hilbert space (RKHS). We theoretically prove that, under our assumptions, the KME-CLIP similarity can bring the contrastive loss arbitrarily close to its optimal value, which is attained by PMI, as the size of the point set grows, and we empirically evaluate KME-CLIP against CLIP and its kernel-based variants across several retrieval and classification tasks.

Different machine learning models can represent the same underlying concept in different ways. This variability is particularly valuable for in-the-wild multimodal retrieval, where the objective is to identify the corresponding representation in one modality given another modality as input. This challenge can be effectively framed as a representation alignment problem. For example, given a sentence encoded by a language model, retrieve the most semantically aligned image based on representations produced by an image encoder, or vice versa. To gain insights into the performance impact of different metrics, embedding spaces, and representation alignment for retrieval tasks, we first empirically investigate the geometric relationships between visual and textual embeddings derived from both vision-language models and combined unimodal models. We then align these representations using four standard similarity metrics as well as two learned ones, implemented via neural networks of different architectures with varying losses across multiple benchmarks. Our experimental findings indicate that cosine similarity consistently outperforms all the investigated metrics in representation alignment tasks, and that Wasserstein distance provides a complementary perspective on cross-modal distributional differences. We also observe that our proposed custom contrastive loss is advantageous over the MSE loss for aligning image and text representations, for both multilayer perceptrons and transformer-based models. Taken together, our findings offer novel insights and practical considerations for researchers working in multimodal information retrieval, particularly in real-world, cross-modal applications. Our code is publicly available.

Generating semantically controllable 3D CT volumes from radiology reports requires more than a rich text encoder, it requires vision-language alignment grounded in volumetric space. Existing Text-to-CT approaches condition generation on encoders pretrained with language only or 2D vision-language objectives, providing conditioning signals that are linguistically expressive but volumetrically blind. We argue this is a structural limitation: the quality of 3D vision-language alignment, not the richness of the text encoder, is the primary bottleneck for semantic controllability in volumetric diffusion models. To address this, we propose a generation-oriented 3D-CLIP encoder trained with structured hard negatives that operate exclusively at the text level. This design increases contrastive difficulty without any additional 3D memory cost, overcoming the small-batch constraints inherent to volumetric encoders. The resulting encoder conditions a fully end-to-end latent diffusion model that operates directly in 3D latent space, eliminating the spatial artifacts and cross-slice inconsistencies introduced by super-resolution pipelines. Through systematic ablations, we establish a clear empirical link between grounding quality and downstream generative controllability. Evaluated on CT-RATE across 18 pathological conditions, our method achieves state-of-the-art performance on both image fidelity and factual correctness, while requiring less inference time and GPU memory than all competing methods. Code is at https://github.com/danielemolino/Text2CT.

Electrocardiograms (ECGs) are essential non-invasive tools for diagnosing cardiovascular diseases. While recent multimodal ECG-Report contrastive learning methods have shown promise for zero-shot ECG interpretation, they predominantly rely on global representations, failing to capture the fine-grained relationship between localized waveform patches and specific pathological tags. This limitation is further exacerbated by the fact that nearly 55% of standard clinical reports (e.g., in MIMIC-ECG) lack explicit waveform descriptions. In this paper, we propose FOCAL, a novel framework that achieves precise, fine-grained alignment between localized ECG segments and individual report tags via Optimal Transport. Furthermore, because fine-grained alignment at the tag level exacerbates the false negative problem among reports sharing common diagnoses, we introduce a semantic similarity matrix to guide the contrastive objective and correct misalignments. To address the scarcity of detailed waveform text, we introduce a coarse-to-fine enrichment pipeline that leverages Large Language Models (LLMs) to recover missing semantics, utilizing a coarse model verification step to rigorously filter out hallucinations. Extensive experiments across six datasets demonstrate that FOCAL establishes new state-of-the-art performance in zero-shot prediction and linear probing.

Multimodal representation learning, exemplified by multimodal contrastive learning (MMCL) using image-text pairs, aims to learn powerful representations by aligning cues across modalities. This approach relies on the core assumption that the exemplar image-text pairs constitute two representations of an identical concept. However, recent research has revealed that real-world datasets often exhibit cross-modal misalignment. There are two distinct viewpoints on how to address this issue: one suggests mitigating the misalignment, and the other leveraging it. We seek here to reconcile these seemingly opposing perspectives and to provide a practical guide for practitioners. Using latent variable models, we thus formalize cross-modal misalignment by introducing two specific mechanisms: selection bias, where some semantic variables are absent in the text, and perturbation bias, where semantic variables are altered---both leading to misalignment in data pairs. Our theoretical analysis shows that, under suitable assumptions, population global minimizers of an alignment--entropy surrogate yield representations that depend only on the semantic variables unaffected by selection and perturbation biases and locally identify this subset almost surely. Extensive empirical studies on synthetic data and real image-text datasets further examine how cross-modal misalignment shapes semantic predictability and downstream performance, shedding light on its nuanced impact on multimodal representation learning.

Medical image segmentation is a fundamental task in numerous medical engineering applications. Recently, language-guided segmentation has shown promise in medical scenarios where textual clinical reports are readily available as semantic guidance. Clinical reports contain diagnostic information provided by clinicians, which can provide auxiliary textual semantics to guide segmentation. However, existing language-guided segmentation methods neglect the inherent pattern gaps between image and text modalities, resulting in sub-optimal visual-language integration. Contrastive learning is a well-recognized approach to align image-text patterns, but it has not been optimized for bridging the pattern gaps in medical language-guided segmentation that relies primarily on medical image details to characterize the underlying disease/targets. Current contrastive alignment techniques typically align high-level global semantics without involving low-level localized target information, and thus cannot deliver fine-grained textual guidance on crucial image details. In this study, we propose a Target-informed Multi-level Contrastive Alignment framework (TMCA) to bridge image-text pattern gaps for medical language-guided segmentation. TMCA enables target-informed image-text alignments and fine-grained textual guidance by introducing: (i) a target-sensitive semantic distance module that utilizes target information for more granular image-text alignment modeling, (ii) a multi-level contrastive alignment strategy that directs fine-grained textual guidance to multi-scale image details, and (iii) a language-guided target enhancement module that reinforces attention to critical image regions based on the aligned image-text patterns. Extensive experiments on four public benchmark datasets demonstrate that TMCA enabled superior performance over state-of-the-art language-guided medical image segmentation methods.