Multi-Modal Representation Learning

Multimodal representation learning seeks shared representations for cross-modal retrieval and knowledge transfer. Hub-based binding reduces pairwise supervision costs, but separate hub connections cannot guarantee reliable alignment between modalities without direct joint training. We introduce Hub-Spectral Activation (HSA), a closed-form method for recovering and activating the hub-readable component of latent multimodal knowledge in frozen representations. We formalize this knowledge as source-induced cross-modal dependence and characterize the component determined by the second-order statistics of two trained hub edges. Under a second-order source model, we establish conditions for exact recovery of the complete source-induced relation and bound the dimension of its hub-readable component by the hub covariance rank. HSA composes and standardizes hub-edge statistics, extracts paired spectral directions, and combines reliability-weighted matching evidence with source-gated candidate resolution for bidirectional retrieval and prototype classification. HSA requires no target-pair supervision, gradient optimization, or backbone updates. Across 19 retrieval and 11 prototype-classification relations on ImageBind and LanguageBind, HSA raises mean bidirectional Recall@10 from 18.27% to 31.15% and mean macro Top-1 accuracy from 29.01% to 52.43%, respectively. Controlled analyses further identify valid hub-edge correspondence and leading spectral directions as key sources of retrieval gains, demonstrating the utility of latent multimodal knowledge beyond native similarity scores. Code and models are publicly available at https://github.com/Luo1Yan/HSA.

Region-level retrieval aims to align user-specified image regions with relevant regions or textual descriptions, playing a crucial role in realworld applications such as e-commerce product search and RAG. Although recent Large Multimodal Models (LMMs) have made significant strides in multimodal retrieval, they primarily focus on global-level tasks and struggle to capture effective region-level representations. To bridge this gap, we present RegRet, an LMM-based Region-level Retrieval framework that enhances the regional representations without compromising overall global retrieval performance. At its core, RegRet integrates a Region-Aware Encoder to capture detailed regional features while balancing them with the global background context. To further enhance the fine-grained understanding and discriminability of representations, we design a multi-stage training pipeline that includes detailed localized captioning and regional contrastive learning tasks. In addition, considering the absence of region-level contrastive training data and the limited diversity of evaluation tasks in current benchmarks, we introduce the REGMB benchmark. It comprises 225k contrastive pairs, covering four multimodal retrieval tasks. Extensive experiments validate the effectiveness of our approach. RegRet outperforms strong baselines in the zero-shot setting. Further training with contrastive learning leads to an average improvement of more than 20% on both REGMB and public benchmarks, while achieving comparable or better results on global-level retrieval tasks.

Traditional multimodal representation learning and generation are two stages: a contrastive or self-supervised visual encoder is trained first, followed by a separate downstream generative model. This setup bottlenecks generative performance behind frozen embeddings. To bridge this gap, we revisit joint multimodal representation learning and generation to produce linearly interpolatable embeddings that are directly consumable by generative decoders. We present FLAT (Flexible-Length Aligned Transmodal representations), a representation pre-training framework that jointly optimizes a shared multimodal encoder alongside downstream text-to-image (T2I) and image-to-text (I2T) decoders. By combining contrastive alignment with bidirectional cross-modal generative objectives, FLAT ensures its representations function as both discriminative semantic descriptors and generative conditions. Architecturally, FLAT maps visual and textual inputs into a unified continuous 1D sequence space, applying nested dropout over prefix-K tokens to enable dynamic output lengths. A single pre-training stage allows FLAT to perform cross-modal retrieval and generation across variable prefix K, achieving a T2I GenEval score of 71.1. Task-specific fine-tuning aligns model performance with state-of-the-art baselines: 83.1 GenEval on T2I generation; 40.5 BLEU-4 and 138.6 CIDEr on MS-COCO image captioning; and Recall@5 scores of 86.8 (I2T) / 75.8 (T2I) on MS-COCO alongside 98.3 (I2T) / 93.6 (T2I) on Flickr30K. Finally, qualitative evaluations demonstrate that FLAT representations natively support linear interpolation, latent space arithmetic, and zero-shot composed retrieval.

Molecular property prediction requires representations that generalize from limited labeled data to structurally novel compounds. Existing molecular pretraining methods often rely on a single view: graph-based approaches model atom-bond topology but provide limited fragment-level supervision, whereas fingerprint descriptors encode chemical patterns but are typically used as fixed auxiliary features. We propose HiFi-Mol, a multi-view framework that separately pretrains a hierarchical graph encoder and a contextualized fingerprint encoder before downstream integration. The graph branch uses fragment-aware masking with multi-resolution supervision to capture substructure-aware representations, while the fingerprint branch tokenizes active entries from seven fingerprint families and applies masked language modeling to learn contextualized embeddings. During fine-tuning, HiFi-Mol combines projected multi-resolution graph features with fingerprint embeddings for downstream prediction. Evaluated on MoleculeNet benchmarks under the scaffold split, HiFi-Mol achieves a 2.77% improvement in average ROC-AUC over the best baseline across eight classification tasks while maintaining competitive performance on three regression tasks. Further analyses reveal that fragment-aware masking improves graph representation quality, and classification results demonstrate dataset-dependent strengths of the individual graph and fingerprint variants, confirming that the two views provide complementary predictive signals.

Urban region representation learning commonly combines heterogeneous data sources, such as mobility flows, points of interest, and land-use information, to support tasks including mobility analysis, public safety forecasting, and service demand estimation. Existing multi-view methods typically improve region embeddings by strengthening interactions across views. However, such methods often overlook view-specific regional structures and may propagate correlations induced by shared latent factors, which can reduce the stability of downstream predictions. To overcome this major limitation, we propose CURE, a confounder-aware framework for multi-view urban region representation learning. CURE first encodes each view with its regional graph structure, estimates a shared latent component, and then reduces its projected influence before cross-view interaction. A hierarchical graph-aware fusion module subsequently aggregates the residual view representations using local and global regional contexts Experiments on three real-world cities show that CURE improves predictive performance, remains robust under missing and noisy input views, and provides reliable cross-view integration through shared component separation and context-dependent view weighting.

Recent advances in Earth Observation representation learning accommodate heterogeneous sensors and missing observations, often through larger architectures. We present MEOX (Multimodal Earth Observation with eXperts), a multimodal masked autoencoder with a 2.939 million-parameter encoder and 3.115 million parameters in total. Sensor-specific adapters, explicit validity signals, and a shared sparse-expert block preserve modality-dependent processing before a learned patch-wise fusion. Four metadata tokens then accompany a single spatial sequence through fourteen further encoder blocks. Shared expert projections with private low-rank residuals constrain parameter growth, while rotary attention supports downstream spatial grids different from pretraining. The model is pretrained on 1.228 million MMEarth64 samples using modality-balanced masked reconstruction and structured sensor dropout. Frozen transfer is evaluated on six GEO-Bench tasks at both 64 and 224 pixels. The model reaches 64.42% mean intersection-over-union on cashew segmentation at 64 pixels and 90.56% average accuracy on EuroSAT at 224 pixels, exceeding the corresponding reported CSMoE results. BigEarthNet finetuning reaches 72.95% micro-average precision. Routing diagnostics distinguish expert participation, spatial dependence, modality association, and functional contribution. A held-out WorldCover probe measures a 0.64-percentage-point benefit from metadata, while retrieval separates same-sensor semantics from cross-sensor alignment. These results demonstrate sensor-flexible representation learning and strong task transfer using a compact parameter budget.

Accurate daily predictions of cold hardiness in woody plants are critical in regions where freezing temperatures can damage dormant buds and reduce seasonal yield. Existing biophysical, hybrid, and deep learning models have shown high predictive accuracy when trained on local data but remain largely site-specific. The limited availability of cold hardiness data, coupled with the lack of principled methods for transferring cold hardiness predictions to new regions and cultivars, has limited the broader adoption and practical utility of these approaches, particularly in data-scarce regions. To address these limitations, we propose a cold hardiness prediction framework that learns a transferable latent representation by capturing region-specific variation through learned embeddings. To enable prediction in previously unseen regions, we infer embeddings from (1) text descriptions of the cultivar and growing region, and (2) limited historical observations, supporting both zero-shot and few-shot transfer. Experiments on datasets from six regions across North America demonstrate that our approach consistently outperforms state-of-the-art cold hardiness prediction methods, yielding more accurate predictions and substantially improving transfer to data-scarce regions.

Surgical phase recognition is key to context-aware computer-assisted feedback in vitreoretinal procedures, yet the scarcity of synchronized multimodal intraoperative data, particularly microscope views and intraoperative OCT, limits approaches that aim to replicate the multimodal integration surgeons perform naturally. Surgical narration, by contrast, is abundantly available online and offers rich semantic supervision. Prior work has mainly explored pairwise contrastive learning (e.g., intraoperative OCT-microscope or microscope-narration), leaving the joint modeling of all three modalities largely unexplored. We introduce a framework that uses microscope views as a shared anchor to bridge surgical narrations and intraoperative OCT (iOCT) without requiring a fully synchronized tri-modal dataset, leveraging real microscope-narration videos and a synthetic dataset of synchronized microscope video and tool-aligned iOCT pairs. Contrastive alignment transfers structural priors from the synthetic domain to real videos lacking iOCT, and a dual-head MS-TCN++ integrates the resulting embeddings for joint macro- and micro-phase prediction. Evaluated on real vitreoretinal surgeries, our framework improves macro-phase recognition over a zero-shot baseline (mean F1 0.38 to 0.53) and provides an exploratory route to estimating fine-grained instrument-tissue measurements that are not directly observable in real microscope video alone; these micro-phase estimates are validated quantitatively on synthetic data and shown only qualitatively on real surgery. To our knowledge, this is the first work to unify microscope view, iOCT B-scans, and surgical narrations in a shared latent space for surgical phase recognition.

Reinforcement-learning (RL) post-training equips multimodal large reasoning models (MLRMs) with exploratory chains of thought (CoT), substantially improving visual reasoning. However, we find that this capability introduces a distinct privacy vulnerability: even when a sensitive fact is successfully unlearned from the final answer, the model may still reproduce it in its reasoning trace. This leakage is substantially more pronounced in natively RL-trained MLRMs than in their non -reasoning base models, revealing a privacy risk that existing unlearning methods are not designed to address. We show that RL-induced exploration leaves sensitive content with a distinctive token-level entropy signature that is largely absent from base models. Based on this observation, we propose LEMUR, a fully training-free, inference-time unlearning framework for natively RL-trained multimodal models. LEMUR uses entropy dynamics as a control signal to identify when sensitive reasoning begins and when sanitization should stop. During this interval, it redirects the reasoning trajectory through entropy-modulated visual-anchor latent injection, replacing committed tokens with sanitized, probability-weighted embeddings re-grounded in the input image. Across diverse MLRMs, LEMUR consistently outperforms existing unlearning met hods in suppressing both reasoning-trace and answer leakage, while better preserving non-sensitive utility and output fluency. These results demonstrate that RL-induced entropy dynamics provide a distinctive signal for privacy leakage and that exploiting this signal enables effective training-free unlearning for reasoning-capable multimodal models.

Determining the complexity, or Intrinsic Dimension (ID), of data is fundamental to efficient and interpretable representation learning. This is particularly challenging in multi-modal settings when trying to learn disentangled representations for shared and private information. Existing techniques leave a critical gap: they are often static, uni-modal, or in the case of contrastive methods, adapt only to the shared ID implicitly. We introduce Fidelity-Guided Rank Optimization (FiGuRO), a framework for approximating the ID of uni- and multi-modal data under constraints of model capacity and hyperparameters. FiGuRO learns the dimensions of low-rank projections using truncated singular value decomposition and an algorithm that determines when to reduce or increase dimension and in which latent space. Disentanglement of shared and private information arises as an emergent property of this optimization, eliminating the need for complex auxiliary loss functions. We demonstrate that FiGuRO outperforms existing ID estimation techniques and is more robust to hyperparameter changes. Across simulations and real-world data, FiGuRO captures distinct ID scales and varying subspace ratios, and decomposes shared and private information successfully. Furthermore, we show that FiGuRO can be applied to modern uni-modal pretrained models, enabling efficient, post-hoc disentanglement of multi-modal representations.

Modern recommender systems in food delivery increasingly leverage multimodal signals, including images, text, and user interaction histories, to enhance user experience, yet effective fusion of these heterogeneous modalities remains challenging, hindering both the joint modeling of multimodal signals and adaptation to evolving user intent. In mainstream two-stage approaches, the separation between content-semantic pretraining of image-text encoders and behavior-driven ranking models limits alignment between semantic understanding and user behavior patterns. To address these issues, we present GALA, a three-stage pipeline whose core innovation lies in an intermediate "generative RL alignment" stage that constructs multimodal pretraining data from user behavior and refines it via conversion-based rewards, effectively bridging the pretraining-fine-tuning gap to align with downstream objectives. GALA comprises three stages: first, behavior-aware triplet pretraining on query-image-text pairs from search logs to early capture user intent and content preferences; second, a novel intermediate stage that refines multimodal embeddings through reward-driven optimization (GRPO) to dynamically align them with user behavior and bridge the pretraining-fine-tuning gap; and finally, integration of multimodal and ID embeddings via adaptive gating with a hybrid loss, preserving multimodal contributions under long-term ID-dominant training. GALA has been deployed in the production environment at Taobao Shangou, serving over 200 million daily active users. Compared with state-of-the-art (SOTA) methods, it delivers consistent offline gains of +0.12/+0.20 AUC along with better PCOC metrics. Large-scale online A/B tests further report a 0.55 percent increase in order volume, confirming GALA's effectiveness at industrial scale and its robustness across diverse demand patterns.

Submodular Information Measures (SIMs) have recently emerged as a powerful framework for representation learning and multimodal learning. In particular, the SCORE framework~\cite{majee2024score} demonstrated that SIMs can serve as effective objectives for supervised contrastive learning. Despite their empirical success, however, the geometric and statistical properties induced by different submodular information measures remain poorly understood. In this work, we develop a unified theoretical framework connecting SIMs to classical concepts in representation learning and statistical pattern recognition. We show that Total Information (TI) objectives characterize intra-class structure: Graph Cut TI recovers within-class variance, LogDet TI recovers generalized variance and covariance volume, and Facility Location TI induces imbalance-aware separation that emphasizes rare and confusable classes. We further show that Mutual Information (MI) objectives capture complementary notions of inter-class structure: Graph Cut MI is closely related to centroid separation and Fisher-style discrimination, LogDet MI captures covariance-aware separation through Mahalanobis distance, and Facility Location MI measures nearest-mode representational overlap. We validate these theoretical characterizations using controlled synthetic experiments that independently vary variance, covariance, class imbalance, class separation, and multimodal overlap. Across all settings, the empirical behavior closely matches the proposed theory. Our results provide the first unified geometric and statistical understanding of submodular information measures and offer principled guidance for selecting and designing SIM-based objectives for representation learning.

Vision-language pre-training (VLP) serves as a cornerstone for medical multimodal representation learning. However, existing medical VLP frameworks are often constrained by the limited context windows and shallow representational capacities of lightweight text encoders when processing lengthy, terminology-dense clinical reports. While integrating medical large language models (LLMs) offers unprecedented clinical reasoning capabilities, it introduces three major bottlenecks: (i) the anisotropic representational collapse of generative LLMs under standard contrastive objectives, (ii) the prohibitive memory overhead of joint end-to-end training with large batch sizes, and (iii) the medical hallucinations induced by vanilla contrastive losses that ignore fine-grained anatomical laterality and negation modifiers. To address these challenges, we propose \textbf{SCALPEL}, a \textbf{S}emantic \textbf{C}ross-modal \textbf{A}lignment framework via \textbf{L}LM-\textbf{P}owered \textbf{E}ncoder \textbf{L}earning. First, Clinical Report Contrastive fine-tuning converts a generative LLM into an isotropic encoder via domain-specific clinical text adaptation. Second, an asymmetric alignment strategy leverages offline feature caching to enable efficient training. Critically, we formulate an Anatomy-Negation Aware Objective that explicitly penalizes mismatched image-text pairs involving laterality confusion or false negations. Extensive experiments across MIMIC-CXR, CheXpert, and IU X-Ray benchmarks demonstrate that SCALPEL achieves state-of-the-art performance in cross-modal retrieval, zero-shot disease classification and medical visual question answering.

Multimodal drug discovery enables drug representation learning beyond chemical structure by incorporating cellular responses such as gene expression and cell morphology. However, direct fusion and instance-level contrastive alignment may mix mechanism-related signals with modality-specific noise and incorrectly separate structurally dissimilar but biologically related compounds. This limitation can obscure transferable mechanism patterns required for predicting the properties of unseen compounds. We introduce PMRD, a pharmacological response domain-guided framework for multimodal zero-shot drug property prediction. PMRD separates mechanism-consistent factors from modality-specific information and constructs a consensus response domain across three modalities. Mechanism candidate augmentation identifies locally stable factors, while retrieval-geometry attribution dynamically reweights the alignment and augmentation objectives according to whether their updates preserve inter-drug discriminability.This feedback suppresses training signals that conflict with mechanism-discriminative retrieval. PMRD further combines complementary representations through reliability-aware multiview retrieval. Experiments on public datasets show improved zero-shot property prediction and more biologically coherent drug neighborhoods. Hard-negative analysis further indicates fewer conflicts between structurally dissimilar but response-related compounds. These results support PMRD as an effective framework for mechanism-aware multimodal drug representation learning.\footnote{The code will be released upon publication.}

The renewed global focus on lunar exploration, driven by the prospect of in-situ resource utilization and a sustained human presence on the Moon, has created growing demand for accurate, large-scale characterization of the lunar surface. Although vast quantities of orbital remote-sensing data have been collected, scientific analysis and resource mapping remain fragmented by heterogeneous multiinstrument observations, sparse labels, and bespoke task-specific modelling workflows. Here we introduce LunarFM, a multimodal foundation model that learns a general representation of the lunar surface from diverse orbital measurements. LunarFM assimilates observations from six instruments across three lunar missions, mapping 18 input channels to a shared embedding space. We demonstrate that this embedding space supports a diverse range of downstream applications, including similarity search, few-shot resource mapping, mineral abundance regression, and geological unit classification, enabling efficient scientific investigation and resource-oriented analysis. We provide a machine-learning-ready dataset of co-registered multimodal observations spanning latitudes from 70°S to 70°N, a pretrained multimodal masked autoencoder, and a companion embedding dataset providing a joint 768-dimensional representation of lunar surface properties. All code and data are available at https://lunarfm.trillium.tech/

Multimodal models such as CLIP learn a shared embedding space for cross-modal retrieval, but continual adaptation to sequentially arriving data can disrupt the cross-modal alignment acquired from earlier phases. Conventional continual-learning methods return a single checkpoint, which commits every retrieval direction to the same stability-plasticity trade-off. We propose AlphaWiSE, a post-hoc weight-space interpolation method that composes two frozen source checkpoints. For each aligned parameter tensor identified by its checkpoint key, AlphaWiSE fits one scalar interpolation coefficient shared by all tensor entries. The coefficients are fitted on a smaller exemplar memory and used to materialize one interpolated checkpoint. The deployed model has the same architecture and parameter count as either source checkpoint, which does not require additional inference time. Extensive experiments on audio-image-text retrieval show consistent improvements over strong continual-learning baselines across multiple retrieval directions and evaluation metrics.

Spatially resolved omics studies increasingly combine transcriptomic and epigenomic assays, yet downstream analysis is often still performed using single-modality pipelines. We present LATTICE (Latent Alignment of Tissue-level and Transcriptomic Information for Cross-modal Embedding), a graph-based self-supervised framework that learns spot-level representations from harmonized multimodal features. LATTICE integrates five aligned modality blocks per Visium spot: Visium RNA, scMultiome RNA, scMultiome ATAC, spatial ATAC, and spatial CUT&Tag. These modalities capture spatial transcriptomic measurements, single-cell inferred regulatory activity, and in situ chromatin and histone states within a unified lattice representation. LATTICE constructs a spatial neighborhood graph and trains a TransformerConv encoder using masked reconstruction, cross-modal alignment, and spatial smoothness objectives. On a private 11-sample melanoma cohort from an anonymized clinical collaborator comprising 54{,}912 total spots, LATTICE demonstrated stable optimization behavior, reproducible embeddings across analysis seeds, and complete multimodal integration across all samples. Adding scMultiome RNA to Visium RNA alone substantially improved concordance with Space Ranger clusters across 11 runs (adjusted Rand index [ARI] +0.157, normalized mutual information [NMI] +0.143, and spatial contiguity +0.174). Additional modalities further improved spatial contiguity and multimodal utility score (MUS), although they sometimes reduced agreement with RNA-derived reference labels, likely because the learned embeddings captured chromatin and regulatory structure beyond transcriptomic similarity alone. These results position LATTICE as a practical and empirically grounded framework for multimodal spatial omics integration, while also highlighting the need for stronger supervision and broader external benchmarking.

Urban region profiling constitutes a core problem in urban computing, supporting applications such as population estimation, economic assessment, and environmental monitoring. Existing methods typically formulate this task as multimodal representation learning, fusing heterogeneous urban data, e.g., satellite imagery, points of interest, textual descriptions, and 3D building information, into latent embeddings for prediction. However, these approaches are largely correlation-driven, assume cross-modal consistency, and rely on static pipelines, which limit their robustness in heterogeneous or unseen urban regions. We propose UrbanAgent, an agentic framework that reframes urban region profiling as a reasoning-driven inference problem. UrbanAgent instantiates an independent agent for each data modality and performs structured multi-agent collaborative reasoning to explicitly address cross-modal inconsistencies rather than absorbing them into a single representation. In addition, UrbanAgent extends indicator prediction as a closed-loop process of active evidence acquisition and iterative reasoning, enabling agents to verify uncertain inferences through tool-augmented retrieval of external knowledge optimized via reinforcement learning. Extensive experiments on global urban datasets for Carbon emissions, GDP, and Population estimation show that UrbanAgent consistently outperforms existing baselines, achieving an average improvement of 8.1% in R2, and exhibiting strong generalization performance in unseen-city settings.

Multimodal information is pivotal for e-commerce search ranking. Existing works leverage multimodal data typically by fine-tuning general Multimodal Large Language Models (MLLMs) via collaborative signals, subsequently integrating the derived representations into ranking models as item features. Despite their efficacy, these methods face two primary limitations: (1) they rely on a single collaborative signal for MLLM fine-tuning, failing to exploit the heterogeneous signals essential for multitask ranking; and (2) they treat multimodal representations as regular item features in ranking models, underutilizing their latent potential for user behavior modeling. To address these challenges, we propose the Multiplex Multimodal Representation Model (MMRM), a unified framework that aligns MLLMs with diverse collaborative signals. By employing a shared backbone with task-specific tokens and projection layers, MMRM simultaneously learns from multiple signals and generates comprehensive multiplex item representations in a single inference pass. Furthermore, we introduce a multiplex user representation strategy in ranking models, which derives task-specific user representations via search-based behavior sequence modeling leveraging multiplex item representations. Extensive experiments demonstrate MMRM's superior efficiency and effectiveness. Notably, MMRM has been successfully deployed in the JD e-commerce search engine, yielding significant performance gains for millions of daily users.

We study the modality gap in CLIP-style dual-encoder contrastive learning, where image and text embeddings remain misaligned despite being trained in a shared space. We argue that the gap is induced by a failure of the InfoNCE formulation with independent encoders. We conduct a uni-modal experiment with two independent encoders and identical initialization conditions and find that InfoNCE actively generates a gap at low temperatures. We provide a theoretical analysis of this phenomenon and show that the modality gap is indeed a mode-failure of InfoNCE, but only at low temperatures. We propose a simple modification called xNCE, which uses intermodal as well as intra-modality negative contrastive pairs. xNCE matches retrieval performance on MS-COCO while consistently reducing the gap even at low temperatures. Notably, xNCE improves zero-shot classification over the InfoNCE baseline across all benchmarks, whereas high-temperature InfoNCE and regularized InfoNCE both fail to do so, demonstrating that xNCE reduces the modality gap without sacrificing the discriminative geometry needed for transfer.

This paper studies the problem of learning a joint distribution from marginal observations, which is inherently ill-posed due to the ambiguity of feasible couplings. We propose LUD-MSR, a latent-variable probabilistic framework that models the joint distribution via auxiliary representations and optimizes evidence lower bounds using only marginal data. Under mild assumptions, we establish an upper bound on the distribution approximation error. This analysis reveals a trade-off in representation learning between domain consistency and information preservation. To address this trade-off, we introduce a Multi-Scale image Representation (MSR) mapping that exploits structural similarity at coarse scales while suppressing domain-specific variations. We show that MSR achieves a more favorable balance of this trade-off compared to existing approaches. Experiments on real-world denoising benchmarks, including cryo-electron microscopy (cryo-EM), demonstrate the effectiveness of the proposed framework.

Multi-Modal Knowledge Graphs (MMKGs) enrich entities with multiple modalities such as text and images, yet entities with highly similar multi-modal features remain difficult to distinguish. Temporal information of an entity can serve as an additional modality to disambiguate such entities, but existing approaches rarely treat time as a separate modality alongside text and images due to two major challenges: (1) sparse temporal semantics, which hinder alignment with richer modalities, and (2) multiple timestamps, which introduce noise or reduce robustness in representation learning. To address these challenges, we propose Time Imprint, a framework that treats time as an entity-level modality and jointly aligns temporal, textual, and visual representations via a three-view contrastive objective. Additionally, to mitigate multi-timestamp ambiguity, Time Imprint studies a compact timestamp subset selection design space and aggregates the selected timestamps into a discriminative temporal embedding with attention pooling, balancing temporal specificity and robustness. Experiments on three MMKG benchmarks demonstrate that Time Imprint achieves state-of-the-art link prediction performance, improving Hits@1 by up to 6.07% overall and yielding up to 58% gains on the subset of the top-1% ambiguity samples. We further examine different fusion strategies and the sensitivity to timestamp availability and quality, clarifying when and why time-as-modality is most beneficial, while adding only modest training overhead. We release our code at https://anonymous.4open.science/r/Time-Imprint.

Images tell us what a scene looks like, but rarely what it would feel like to be there. While recent datasets pair visual scenes with electronic-nose measurements, aligning smell signals with images remains challenging because many olfactory cues arise from contextual environmental factors that are not directly visible in pixels. We introduce SCENT, a multimodal framework that uses language guidance as a semantic bridge between vision and olfaction. Our approach leverages Vision-Language Models (VLMs) to generate scene descriptors capturing objects, environmental context, and plausible ambient smell cues suggested by the visual scene. These descriptors provide semantic guidance for learning olfactory representations. We train a smell encoder that maps electronic-nose signals into a shared embedding space aligned with both visual and textual representations, and introduce a languageguided latent decomposition that separates object-specific odors from contextual environmental contributions. Experiments on the New York Smells dataset demonstrate that SCENT significantly improves crossmodal retrieval compared to vision-only baselines, achieving state-of-theart performance on smell-to-image and smell-to-text retrieval tasks. In addition, our framework produces interpretable olfactory representations that enable the disentanglement of complex smell mixtures. Our results reveal the importance of contextual semantic information for grounding olfactory perception in multimodal learning and pave the way for future research in this area.

The structure of human visual representations underpins our capacity for adaptive behaviour. While pretrained neural networks model human visual representations with unprecedented success, a large discrepancy remains. We propose one reason: these networks optimise a single fixed objective, whereas human representations must support open-ended tasks. We hypothesise this flexibility arises from meta-learning (learning to learn), a pressure shaping representations to acquire new tasks from few observations. To test this, we train a sequence model, without any supervision from human data, across thousands of semantically rich tasks mapping images to high-level concepts. Compared to their pretrained base encoders, meta-learned representations better predict human similarity judgements, semantic rule learning, and high-level visual cortex. Behavioural gains depend on disentangled, high-level task distributions, while brain alignment is driven primarily by the learning-to-learn pressure. Our results suggest the flexibility of human visual representations reflects the functional demand to learn new semantic relationships on the fly.

Morphological traits provide important evidence for phylogenetic reconstruction and evolutionary relationship analysis. Recent image-based approaches have introduced deep learning, particularly convolutional models, to derive morphological features from specimen images, but these methods generally rely on single-modality visual representations and do not explicitly incorporate morphological semantics. This study proposes a morphology-aware multimodal alignment framework for insect phylogenetic reconstruction. The framework combines specimen images with curated morphological descriptions by adapting a vision transformer through parameter-efficient fine-tuning and supervised contrastive learning, followed by image-text alignment in a shared latent space. The learned image embeddings are then used as continuous traits for Bayesian phylogenetic reconstruction. On the public Rove-Tree-11 dataset, comparative and ablation experiments across multiple visual backbones and feature adaptation strategies demonstrate that multimodal alignment improves topological agreement with the reference phylogeny. The results indicate that the proposed framework can derive morphology-aware visual traits for computational phylogenetic reconstruction.

Navigation in partially observable environments presents a significant challenge for autonomous agents, requiring effective decision-making with limited sensory information in unknown environments. Belief-based methods, particularly those using neural networks to approximate the belief space, often fail to capture the inherent multimodality of belief spaces, especially in high-dimensional cases with perceptual aliasing. While generative models present a compelling alternative, they typically require substantial data or expert demonstrations and lack explicit mechanisms for long-term planning. In this paper, we introduce BeliefDiffusion, a novel framework that combines the benefits of both generation and planning. BeliefDiffusion leverages diffusion models to explicitly characterize multimodal belief distributions and utilizes Model Predictive Control (MPC) to simultaneously plan ahead. It consists of two steps: (1) Imagining plausible environment configurations based on observation history and (2) Planning efficient navigation strategies across an aggregated configurations. Through extensive experiments in synthetic map environments, we demonstrate that BeliefDiffusion significantly outperforms both model-free reinforcement learning baselines and other generative approaches in navigation success rate and path efficiency. Our results validate that explicitly incorporating multimodal belief representations into planning enables more robust navigation in partially observable settings.

Cross-modal alignment (CA) and cross-modal prediction (CP) are the dominant paradigms for multimodal representation learning, yet there is no systematic understanding of when each succeeds and when each fails --- a gap that leaves practitioners, especially in scientific domains with heterogeneous instruments and multiple levels of measurement, unable to diagnose why standard methods underperform the best single modality. We study both objectives under a spiked signal-plus-noise model with structured cross-modal nuisance correlation, the ingredient that breaks the classical recovery guarantees, and derive separation ratios that expose complementary failure modes: alignment whitens each modality and fails when nuisance is strongly correlated across views; prediction encodes whatever is cross-predictable through a one-sided whitening, with recovery governed by source-modality quality. The resulting phase diagram partitions multimodal problems into four regimes --- Both, CA only, CP only, and Neither --- refined by a recovery count that separates partial recovery from complete failure. We present a data-driven procedure to locate real-world datasets in this diagram using a small labeled subsample, identifying the preferred objective and prediction direction before any cross-modal training, and identifying when no objective in the CA/CP family can improve on the stronger modality alone. Experiments on synthetic data, stereo-vision benchmarks, image--caption pairs, and two real scientific domains --- astronomy and single-cell multi-omics --- validate the predictions in the nonlinear regime, including both faces of the Neither regime. Code to reproduce the results is available at https://github.com/IlayMalinyak/mm_align_vs_pred.

Variations in illumination remain a major challenge for visual representation learning, as they induce substantial appearance changes both across and within environments. While existing approaches typically address this issue through data augmentations that encourage models to become invariant to lighting changes, such strategies do not explicitly model lighting information during learning. Inspired by theories of human vision, we propose a lighting-aware representation learning framework that incorporates illumination variation as an explicit training signal rather than a nuisance factor to be suppressed. Our method extends contrastive learning by introducing an auxiliary objective that captures illumination-dependent variation in rendered scenes, enabling the model to jointly learn representations that preserve semantic consistency while remaining sensitive to lighting-dependent visual structure. We evaluate the proposed model on image classification and object detection tasks across the ImageNet, ExDark, and PASCAL VOC benchmarks. Results demonstrate that the proposed lighting-aware training consistently improves downstream performance over standard contrastive learning baselines, while maintaining the same architecture and training budget. Furthermore, our approach shows promising performance in supervised learning frameworks and under settings involving simpler lighting variation, suggesting broad applicability beyond complex illumination scenarios. These results indicate its potential to enhance model robustness and adaptability in complex visual environments as well as in more conventional image processing tasks.

To leverage the full potential of multimodal data, we need representations that go beyond the state-of-the-art alignment and fusion approaches and exploit all cross-modal interactions without sacrificing modality-specific information. Learning disentangled representations is a principled way to identify these underlying shared and unique factors that are hidden in observational data. However, while multimodal disentanglement is a compelling paradigm, existing methods are largely confined to the two-modality regime due to its inherent scalability bottleneck. To address this, we propose RePercENT, a self-supervised framework designed to surpass these limitations and unlocks scalable pairwise disentanglement beyond two modalities. Through a multimodal `plug-and-play' architecture, our approach operates directly on pre-extracted embeddings, eliminating the need for extensive joint pre-training while making no assumptions regarding the underlying modalities or foundation model backbones. Moreover, we introduce a joint optimization objective for simultaneously deriving the shared and unique components, and provide formal theoretical guarantees that characterize the optimality of our solution. Across diverse modalities and tasks, RePercENT successfully recovers disentangled components while maintaining competitive performance and significantly reducing computational complexity.

Robust self-supervised learning of multi-modal video representations is critical for real-world applications such as driver distraction detection, where multiple sensors provide complementary but noisy signals. Conventional contrastive objectives, such as InfoNCE, assume all negatives are equally informative and all positives are reliable. However, this assumption is frequently violated in multi-modal data due to viewpoint changes, occlusions, or semantic overlap across modalities. In this work, we propose a novel framework for multi-modal global alignment that addresses these challenges by jointly modeling faulty negatives and unreliable or faulty positives. We introduce soft targets derived from cycle-consistency scores to relax the hard-negative assumption, and a weighting mechanism based on similarity distributions to mitigate the impact of noisy or faulty positives. Our approach extends traditional pairwise alignment to a principled global multi-modal setting, aggregating alignment information across all modality pairs. We evaluate our method on the Drive&Act dataset, demonstrating that it consistently outperforms both pairwise and existing global alignment baselines across RGB, IR, Depth, and Skeleton modalities. Cross-view ablation studies further show strong generalization to unseen camera perspectives, highlighting the robustness of our representations. Overall, our framework provides a scalable and effective solution for self-supervised global multi-modal representation learning, enabling reliable driver distraction detection and pioneering in real-world multi-modal video understanding. Our code will be published on GitHub.

Multimodal neuroimaging fusion of functional MRI (fMRI) and diffusion tensor imaging (DTI) provides complementary information for cognitive impairment analysis, but remains challenged by heterogeneous feature spaces and misaligned representations. We propose \textit{NeuroAlign}, a hierarchical framework for structured multimodal fusion. It introduces (1) \textit{Dual-Modal Hierarchical Alignment} (DMHA), which models multi-scale dynamic connectivity and aligns dynamic-static and functional-structural embeddings; and (2) \textit{Dual-Domain Hierarchical Interaction} (DDHI), which enables fine-grained modulation and global interaction between connectivity- and region-level features. To support feature-level inspection, we design \textit{Synergistic Activation Mapping} (SAM), a gradient-free, marker-oriented attribution method for DFC, SFC, ALFF, and FA. Evaluated on GUTCM, ADNI, and OASIS under five-fold validation, NeuroAlign achieves competitive MCI/SCD detection and preliminary cross-dataset transferability. Attribution analyses reveal modality-specific and partially consistent brain patterns, providing model-derived evidence for multimodal representation analysis.

We introduce HQ-JEPA, a hybrid quantum-classical joint-embedding predictive architecture for cross-modal remote sensing representation learning. The proposed framework extends JEPA-style masked latent prediction to paired Sentinel-1 and Sentinel-2 imagery by predicting masked target representations from visible context regions while aligning heterogeneous modality features in a shared embedding space. To improve representation quality, HQ-JEPA combines four complementary objectives: latent token prediction, cross-modal token alignment, SIGReg-based Gaussian regularization in the fused latent space, and a differentiable SWAP-test-based Fidelity Quantum Similarity (FQS) loss. Unlike pixel reconstruction methods, HQ-JEPA learns semantic representations directly in latent space and uses quantum state-overlap-based similarity as an additional regularization signal. We evaluate the pretrained encoder on GeoBench classification and segmentation tasks under linear probing and fine-tuning settings. Results show that HQ-JEPA achieves competitive and often superior performance over strong self-supervised and remote sensing foundation-model baselines, demonstrating the benefit of integrating predictive self-supervision, cross-modal geometric regularization, and quantum fidelity-based representation learning for remote sensing applications.

Although multi-scales representation learning enables elastic-dimension embeddings, nested subspaces often suffer from dimensional redundancy and spectral collapse. To address this, we introduce MIC, a framework that optimizes the geometric landscape of multi-granular embeddings through isotropic subspace alignment. MIC employs Soft Collapse Regularization (SCR) to mitigate redundancy between prefix and residual subspaces via cross-correlation penalties, alongside Spectral Isotropy Regularization (SIR) to ensure hyper-spherical uniformity in low-dimensional prefixes. By unifying these strategies through a self-distillation objective, MIC generates semantically dense representations that maintain high discriminative power. Our experiments demonstrate that MIC significantly outperforms standard baselines, particularly in high-compression scenarios where maintaining informational capacity is most critical.

Electrocardiograms (ECGs) are widely used non-invasive measurements of cardiac activity and play a central role in clinical diagnosis. Recent multimodal approaches align ECG signals with clinical reports to incorporate diagnostic semantics, but clinical reports often fail to preserve the rich physiological structure of ECG waveforms, particularly across multiple levels of abstraction ranging from coarse diagnostic categories to fine-grained morphology. To address this limitation, we formulate ECG representation learning from an information-theoretic perspective and derive a tractable objective that jointly preserves signal structure and integrates clinical semantics. Based on this principle, we propose \textbf{MERIT} (Multimodal ECG Representation via Information Theory), a dual-branch pretraining framework combining masked ECG modeling with ECG--text contrastive alignment. Extensive experiments on PTB-XL and additional benchmarks demonstrate consistent improvements over prior methods, including gains exceeding $3$ F1 on PTB-XL All and $5$ F1 on SubClass classification. In zero-shot evaluation, MERIT further improves performance by up to $+2.66\%$ AUC and $+2.11\%$ F1 on PTB-XL SubClass, while also demonstrating robustness under multiple distribution-shift settings. Moreover, leveraging the learned ECG representations for ECG-conditioned clinical text generation with large language models improves text quality across several metrics, including ROUGE and METEOR. Together, these results demonstrate that MERIT learns more informative and clinically meaningful ECG representations, particularly for fine-grained clinical applications.

Urban representation learning encodes complex urban environments into general-purpose embeddings for diverse downstream tasks and emerging urban foundation models. However, current evaluations are limited, typically focusing on one or two cities and tasks and relying on random splits that introduce spatial leakage, leading to inflated performance and weak support for cross-location generalization and fair comparison. To address this, we propose CityRep, a unified benchmark that evaluates urban representations across data modalities, cities, and tasks using spatially structured splits. CityRep consists of three key components: (1) a spatial unit-agnostic evaluation framework that supports heterogeneous urban representations through a standardized alignment module; (2) a unified evaluation protocol using block-based spatial splits to mitigate spatial leakage and enable rigorous model comparison; and (3) an extensible multi-city, multi-task benchmark suite spanning 8 cities and 8 tasks across regression, classification, and distribution prediction. We evaluate 11 representative urban representation models. Results show that performance is highly sensitive to the split protocol, with random splits inflating scores and altering model rankings. We also observe substantial variability across cities and tasks, underscoring the need for generalization-aware evaluation. CityRep is released as a reproducible benchmark with datasets, evaluation pipelines, and diagnostic tools to facilitate fair comparison and support future research in urban representation learning towards urban foundation models.

Understanding why independently trained neural networks from different modalities converge toward shared representations, and where this convergence leads, remains an open question in representation learning. All existing evidence relies on symmetric similarity measures, which can detect convergence but are structurally blind to its direction. We introduce directional convergence analysis using cycle-kNN, an asymmetric alignment measure, applied across dozens of independently trained unimodal models spanning point clouds, vision, and language. We uncover a consistent directional asymmetry: non-language modalities move toward the neighborhood structure of language significantly more than the reverse, and this pattern holds across all model families and scales--yet is entirely invisible to symmetric measures. Mechanistic analysis traces the directionality to feature density asymmetry, whereby language representations occupy the most compact regions of representational space. The Information Bottleneck framework provides a principled interpretation: optimization under compression drives representations toward discrete, compositional structures characteristic of language. We formalize this as the Wittgensteinian Representation Hypothesis: the semantic structure of language is the asymptotic attractor of multimodal representation convergence.

Weakly supervised Audio-Visual Video Parsing (AVVP) aims to recognize and temporally localize audio, visual, and audio-visual events in videos using only coarse-grained labels. Faced with the challenging task settings, existing research advances along two main paths: pre-training pseudo-label generators for fine-grained cross-modal semantic guidance, or refining AVVP model architectures to enhance audio-visual fusion. However, since audio and visual signals are typically unaligned, achieving accurate video parsing fundamentally relies on precise perception of uni-modal events. Yet these multi-modal focused strategies excessively emphasize multi-modal fusion while inadequately guiding and preserving uni-modal semantics, resulting in noisy pseudo-labels and sub-optimal video parsing performance. This paper proposes a novel framework that enhances uni-modal representations for both the pseudo-label generator and the AVVP model. Specifically, we introduce a similarity-based label migration approach to annotate pre-training data, thereby enabling the pseudo-label generator to better understand uni-modal events. We also employ a soft-constrained manner to refine modeling of uni-modal features in parallel with multi-modal fusion. These designs enable coordinated attention to both uni-modal and cross-modal representations, thus boosting the localization performance for events. Extensive experiments show that our method outperforms state-of-the-art methods in both pseudo-label and AVVP performance.

Semantic segmentation of large-scale 3D point clouds is crucial for applications such as autonomous driving and urban digital twins. However, the sparse sampling pattern of LiDAR and the view-dependent geometric distortion in image observations complicate cross-modal alignment and hinder stable fusion. Inspired by the fact that 2D images captured by cameras are representations of the 3D world, we recognize that the features learned from 2D and 3D segmentation share some common semantics, while other aspects remain modality-specific. This insight motivates a unified multimodal framework for joint 2D-3D semantic segmentation. We combine a SAM-based vision encoder with a SPTNet-based geometric encoder to extract complementary semantic and geometric representations. The resulting features from both modalities are explicitly decomposed into shared and private subspaces, where the shared components summarize semantic factors common to both domains, and the private components preserve properties that are unique to each modality. A lightweight attention-based fusion module aggregates the shared features into a consistent cross-modal representation, and a regularized training objective ensures both semantic alignment and subspace independence. Experiments on the SemanticKITTI and nuScenes benchmarks demonstrate consistent improvements in segmentation accuracy over representative multimodal baselines, accompanied by competitive computational efficiency. Cross-domain evaluation on nuScenes USA-Singapore shows stable performance under distribution shifts, demonstrating strong generalization. The implementation code is publicly available at: https://github.com/shuaizhang69/UniD-Shift.

Recent advances in generative AI have democratized video creation at scale. AI-generated videos, including partially manipulated clips across visual and audio channels, pose escalating risks of semantic distortion and misuse, which motivates the need for reliable detection tools. Most existing AI-generated video detectors remain limited by single- or partial-modality of data modeling and the lack of fine-grained temporal forgery localization. To address these challenges, our primary novelty introduces a core architecture that jointly integrates an LMM semantic branch with a spatio-temporal (ST) visual branch and a multi-scale partial-spoof (PS) audio branch. This multi-modal approach enables simultaneous detection and fine-grained temporal localization of partially manipulated AI-generated video forgeries. Extensive experiments show that this approach outperforms existing state-of-the-art methods.

We propose S3 (Specialization, Selection, Sparsification), a framework that rethinks multimodal learning through a structural perspective. Instead of encoding all signals into a fixed embedding, S3 decomposes multimodal inputs into semantic experts and selectively routes them for each task. Specialization forms concept-level experts in a shared latent space, Selection adapts routing for task-specific needs, and Sparsification prunes low-utility paths to yield compact, information-minimal representations. Across four MultiBench benchmarks, S3 improves accuracy and shows a consistent reverse U-shaped sparsity-performance trend, with peak performance at intermediate sparsity. These results suggest that structuring multimodal representations as selectable semantic components provides a practical and principled alternative to contrastive learning or InfoMax-driven approaches.

Source code and its accompanying comments are complementary yet naturally aligned modalities-code encodes structural logic while comments capture developer intent. However, existing vulnerability detection methods mostly rely on single-modality code representations, overlooking the complementary semantic information embedded in comments and thus limiting their generalization across complex code structures and logical relationships. To address this, we propose MultiVul, a multimodal contrastive framework that aligns code and comment representations through dual similarity learning and consistency regularization, augmented with diverse code-text pairs to improve robustness. Experiments on widely adopted DiverseVul and Devign datasets across four large language models (LLMs) (i.e., DeepSeek-Coder-6.7B, Qwen2.5-Coder-7B, StarCoder2-7B, and CodeLlama-7B) show that MultiVul achieves up to 27.07% F1 improvement over prompting-based methods and 13.37% over code-only Fine-Tuning, while maintaining comparable inference efficiency.

Representation learning is fundamental to NLP, but building embeddings that work well at different computational budgets is challenging. Matryoshka Representation Learning (MRL) offers a flexible inference paradigm through nested embeddings; however, learning such structures requires explicit coordination of how information is arranged across embedding dimensionality and model depth. In this work, we propose MIPIC (Matryoshka Representation Learning via Self-Distilled Intra-Relational Alignment and Progressive Information Chaining), a unified training framework designed to produce structurally coherent and semantically compact Matryoshka representations. MIPIC promotes cross-dimensional structural consistency through Self-Distilled Intra-Relational Alignment (SIA), which aligns token-level geometric and attention-driven relations between full and truncated representations using top-k CKA self-distillation. Complementarily, it enables depth-wise semantic consolidation via Progressive Information Chaining (PIC), a scaffolded alignment strategy that incrementally transfers mature task semantics from deeper layers into earlier layers. Extensive experiments on STS, NLI, and classification benchmarks (spanning models from TinyBERT to BGEM3, Qwen3) demonstrate that MIPIC yields Matryoshka representations that are highly competitive across all capacities, with significant performance advantages observed under extreme low-dimensional.

Multimodal representation is crucial for E-commerce tasks such as identical product retrieval. Large representation models (e.g., VLM2Vec) demonstrate strong multimodal understanding capabilities, yet they struggle with fine-grained semantic comprehension, which is essential for distinguishing highly similar items. To address this, we propose Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning (AFMRL), which defines product fine-grained understanding as an attribute generation task. It leverages the generative power of Multimodal Large Language Models (MLLMs) to extract key attributes from product images and text, and enhances representation learning through a two-stage training framework: 1) Attribute-Guided Contrastive Learning (AGCL), where the key attributes generated by the MLLM are used in the image-text contrastive learning training process to identify hard samples and filter out noisy false negatives. 2) Retrieval-aware Attribute Reinforcement (RAR), where the improved retrieval performance of the representation model post-attribute integration serves as a reward signal to enhance MLLM's attribute generation during multimodal fine-tuning. Extensive experiments on large-scale E-commerce datasets demonstrate that our method achieves state-of-the-art performance on multiple downstream retrieval tasks, validating the effectiveness of harnessing generative models to advance fine-grained representation learning.

Recently, large language models (LLMs) have advanced recommendation systems (RSs), and recent works have begun to explore how to integrate LLMs into industrial RSs. While most approaches deploy LLMs offline to generate and pre-cache augmented representations for RSs, high-dimensional representations from LLMs introduce substantial storage and computational costs. Thus, it is crucial to compress LLM representations effectively. However, we identify a counterintuitive phenomenon during representation compression: Mid-layer Representation Advantage (MRA), where representations from middle layers of LLMs outperform those from final layers in recommendation tasks. This degraded final layer renders existing compression methods, which typically compress on the final layer, suboptimal. We interpret this based on modularity theory that LLMs develop spontaneous internal functional modularity and force the final layer to specialize in the proxy training task. Thus, we propose \underline{M}odul\underline{a}r \underline{R}epresentation \underline{C}ompression (MARC) to explicitly control the modularity of LLMs. First, Modular Adjustment explicitly introduces compression and task adaptation modules, enabling the LLM to operate strictly as a representation-learning module. Next, to ground each module to its specific task, Modular Task Decoupling uses information constraints and different network structures to decouple tasks. Extensive experiments validate that MARC addresses MRA and produces efficient representations. Notably, MARC achieved a 2.82% eCPM lift in an online A/B test within a large-scale commercial search advertising scenario.

Incomplete Multi-View Clustering (IMVC) faces the challenge of learning discriminative representations from fragmentary observations while maintaining robustness against missing views. However, prevalent Euclidean-based methods suffer from a geometric mismatch when modeling real-world data with intrinsic hierarchies, leading to semantic blurring where representations drift towards spatially proximal but semantically distinct neighbors. To bridge this gap, we propose HERL, a Hyperbolic Enhanced Representation Learning framework for IMVC. Operating within the Poincaré ball, HERL constructs a structure-aware latent space to enhance representation learning. Specifically, we design a dual-constraint hyperbolic contrastive mechanism optimizing: an angular-based loss to preserve semantic identity via directional alignment, and a distance-based loss to enforce hierarchical compactness. Furthermore, a hyperbolic prototype head is introduced to rectify global structural drift by aligning cross-view hierarchy-aware prototype distributions. Consequently, HERL disentangles fine-grained semantic correlations to sharpen cluster boundaries and imposes geometric constraints to rectify the data recovery process. Extensive experimental results demonstrate that HERL consistently outperforms state-of-the-art approaches.

Medical diagnosis requires the effective synthesis of visual manifestations and clinical metadata. However, existing methods often treat metadata as isolated tags, failing to exploit the rich semantic knowledge embedded in clinical descriptions. We propose PRIMA (Pre-training with Risk-integrated Image-Metadata Alignment), a framework that integrates domain-specific knowledge into multi-modal representation learning. We first curate an expert corpus of risk--disease correlations via Retrieval-Augmented Generation (RAG) to refine Clinical ModernBERT, embedding diagnostic priors into the text encoder. To bridge the modality gap, we introduce a dual-encoder pre-training strategy utilizing DINOv3 and our refined Clinical ModernBERT, optimized by a suite of four complementary loss functions. These losses are designed to capture multi-granular semantic alignment and handle the ambiguity of clinical correlations through soft labels. Finally, we leverage Qwen3 to fuse these aligned features for precise disease classification. Extensive experiments demonstrate that PRIMA effectively harmonizes pixel-level features with abstract clinical expertise, consistently outperforming other state-of-the-art methods. Notably, our framework achieves strong performance without requiring massive data collection or exhaustive computational resources. Our code will is available at https://github.com/yqwang01/PRIMA.

Survival analysis plays a vital role in making clinical decisions. However, the models currently in use are often difficult to interpret, which reduces their usefulness in clinical settings. Prototype learning presents a potential solution, yet traditional methods focus on local similarities and static matching, neglecting the broader tumor context and lacking strong semantic alignment with genomic data. To overcome these issues, we introduce an innovative prototype-based multimodal framework, FeatProto, aimed at enhancing cancer survival prediction by addressing significant limitations in current prototype learning methodologies within pathology. Our framework establishes a unified feature prototype space that integrates both global and local features of whole slide images (WSI) with genomic profiles. This integration facilitates traceable and interpretable decision-making processes. Our approach includes three main innovations: (1) A robust phenotype representation that merges critical patches with global context, harmonized with genomic data to minimize local bias. (2) An Exponential Prototype Update Strategy (EMA ProtoUp) that sustains stable cross-modal associations and employs a wandering mechanism to adapt prototypes flexibly to tumor heterogeneity. (3) A hierarchical prototype matching scheme designed to capture global centrality, local typicality, and cohort-level trends, thereby refining prototype inference. Comprehensive evaluations on four publicly available cancer datasets indicate that our method surpasses current leading unimodal and multimodal survival prediction techniques in both accuracy and interpretability, providing a new perspective on prototype learning for critical medical applications. Our source code is available at https://github.com/JSLiam94/FeatProto.