Multimodal Pretraining

Follow this topic Ask about this topic

Momentum

15 papers in the last four weeks, up 67% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 121

May 13, 2026cs.LG

KAST-BAR: Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Modeling for Universal Neural Interpretation

While EEG foundation models have shown significant potential in universal neural decoding across tasks, their advancement remains constrained by the inadequacy modeling of complex spatiotemporal topology, as well as the inherent modality gap between low-level physiological signals and high-level textual semantics. To address these challenges, we propose a Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Model (KAST-BAR), which dynamically aligns physiological representations derived from multi-level brain topology with an expert-level semantic space. Specifically, we design a Dual-Stream Hierarchical Attention (DSHA) encoder that accurately captures the brain's intrinsic non-Euclidean topology by modeling local temporal dynamics with global spatial contexts. On this basis, a Knowledge-Anchored Semantic Profiler (KASP) is proposed to synthesize physically-grounded and instance-level textual profiles, which subsequently drive a Semantic Text-Aware Refiner (STAR) to dynamically reconstruct EEG representations using Latent Expert Queries. By conducting large-scale pre-training on 21 diverse datasets to build a foundation model, KAST-BAR effectively integrates expert-level medical knowledge into EEG signal representations, consistently achieving superior performance across six downstream tasks. Our code is available at https://github.com/KAST-BAR/KAST-BAR

Haoning Wang, Wenchao Yang, Shuai Shen +1

School of Automation Science and Electrical Engineering, Beihang University, Beijing, China. · School of Biological Science and Medical Engineering, Beihang University, Beijing, China. · State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China. +1

EEG Decoding Multimodal Pretraining Representation Alignment EEG Foundation Models

May 13, 2026cs.CV

BrainAnytime: Anatomy-Aware Cross-Modal Pretraining for Brain Image Analysis with Arbitrary Modality Availability

Clinical diagnostic workups typically follow a modality escalation pathway: after initial clinical evaluation, clinicians begin with routine structural imaging (e.g., MRI), selectively add sequences such as FLAIR or T2 to refine the differential, and reserve molecular imaging (e.g., amyloid-PET) for cases that remain uncertain after standard evaluation. Consequently, patients are observed with heterogeneous and often incomplete modality subsets. However, most current AI models assume fixed data modalities as the model inputs. In this paper, we present BrainAnytime, a unified pretraining framework pretrained on 34,899 3D brain scans from five datasets that support brain image analysis under arbitrary modality availability spanning multi-sequence MRI and amyloid-PET. A single model accepts whatever imaging is available, from a lone T1 scan to a full multimodal workup. Pretraining learns structural-molecular correspondences between MRI and PET via cross-modal distillation (RCMD) and prioritizes disease-vulnerable anatomy via atlas-guided curriculum masking (PACM), all within a shared 3D masked autoencoder (Multi-MAE3D). Across four downstream tasks and five clinically motivated modality settings, BrainAnytime largely outperforms modality-specific models, missing-modality baselines, and large-scale brain MRI pretrained foundation models on most modality settings. Notably, it surpasses the strongest missing-modality baselines with relative improvements of 6.2% and 7.0% in average accuracy on CN vs. AD and CN vs. MCI classification, respectively. Code is available at https://github.com/SDH-Lab/BrainAnytime.

Guangqian Yang, Tong Ding, Wenlong Hou +4

Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China · Department of Technology Management for Innovation, The University of Tokyo, Japan · Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China

Missing-Modality Learning Masked Autoencoders Multimodal Pretraining Medical Image Classification Alzheimer's Disease Classification

May 11, 2026cs.CL

Phoenix-VL 1.5 Medium Technical Report

We introduce Phoenix-VL 1.5 Medium, a 123B-parameter natively multimodal and multilingual foundation model, adapted to regional languages and the Singapore context. Developed as a sovereign AI asset, it demonstrates that deep domain adaptation can be achieved with minimal degradation to broad-spectrum intelligence and alignment. Continued pretraining was performed on Mistral Medium 3.1 using a localized 1-trillion tokens multimodal corpus, followed by a 250-billion tokens long-context extension phase. Subsequent post-training incorporated a novel human-annotated Singapore multimodal dataset and curated textual corpus on Singapore culture, knowledge, and legislation, totaling 22-billion tokens. An additional 5 billion tokens of model alignment was performed through Online Direct Preference Optimization. Phoenix-VL 1.5 Medium achieves state-of-the-art performance for its size on Singapore multimodal, legal, and government policy benchmarks while remaining globally competitive on general multimodal intelligence, multilingual, and STEM benchmarks. We also introduce a novel evaluation suite encompassing localized knowledge benchmarks and an institutionally aligned model behavior and safety framework. We report the data curation principles, training methodology, and highlight benchmark and inference performance.

Team Phoenix, :, Arka Ray +30

HTX × Mistral AI ∗

Multilingual Language Models Domain Adaptation Multimodal Pretraining Multimodal Large Language Models Domain Adaptation for LLMs Multimodal Foundation Models+1

May 9, 2026cs.CV

MultiMedVision: Multi-Modal Medical Vision Framework

Multi-modal medical imaging enables comprehensive diagnostics, yet current foundation models process 2D (e.g. X-ray) and 3D (e.g. CT) data with separate, dimensionality-specific architectures. We present MultiMedVision, a unified framework for joint 2D/3D representation learning built on a Sparse Vision Transformer. Our model uses 3D Rotary Positional Embeddings and variable-length sequence packing to process mixed-modality batches natively within a shared latent space, without modality-specific adapters or treating 3D volumes as 2D slice sequences. Trained with a self-supervised objective on chest X-rays (MIMIC-CXR) and CT scans (CT-RATE), and using a single shared encoder with 5x less data, MultiMedVision achieves competitive performance on both 2D benchmarks (Macro AUROC 0.82 on MIMIC, 0.84 on CheXpert) and 3D tasks (0.85 on CT-RATE). Analysis of the learned representations reveals coexisting modality-specific and shared feature subspaces, demonstrating that unified cross-dimensional representation learning is feasible without sacrificing modality-specific performance.

Frank Li, Bardia Khosravi, Mohammadreza Chavoshi +5

Emory University · Yale University

Medical Imaging Foundation Models Vision Transformer Multimodal Pretraining Multimodal Foundation Models Medical Image Representation Learning

May 8, 2026cs.MM

Anisotropic Modality Align

Training multimodal large language models has long been limited by the scarcity of high-quality paired multimodal data. Recent studies show that the shared representation space of pretrained multimodal contrastive models can serve as a bridge, enabling models to perform multimodal training with unimodal data. However, the key premise of this paradigm remains insufficiently understood: can representations from different modalities be reliably interchanged? The core obstacle lies in the persistent Modality Gap in the shared space. In this work, we revisit the geometric nature of the modality gap. We find that modality representations already share compatible dominant semantic geometry. What truly hinders modality interchangeability is not a simple global shift, but an anisotropic residual structure concentrated along a small number of dominant directions. Based on this finding, we further propose the principle of anisotropic modality gap alignment: effective modality alignment should align with the target-modality distribution while preserving the semantic structure of the source modality. Guided by this principle, we propose an anisotropic geometric correction framework, AnisoAlign, for unpaired modality alignment. This framework leverages the internal geometric prior of the target modality and performs bounded correction on source-modality representations, thereby constructing substitute representations in the target modality. Experiments confirm its benefits in both geometric diagnostics and text-only MLLM training. Overall, this work recasts the modality gap from an empirical observation into a correctable, structured geometric phenomenon and provides a new representation alignment perspective for training multimodal models with unimodal data.

Xiaomin Yu, Yijiang Li, Yuhui Zhang +8

HKUST(GZ) · NUS · Stanford +2

Cross-Modal Learning Cross-Modal Alignment Multimodal Pretraining Multimodal Large Language Models

May 8, 2026cs.CV

Pan-FM: A Pan-Organ Foundation Model with Saliency-Guided Masking for Missing Robustness

Foundation models (FMs) have shown great promise in medical imaging, but most FMs are trained on unimodal data within isolated domains, such as brain MRI alone. Human aging and disease arise through coordinated biological processes across organs, therefore motivating multimodal FMs that learn whole-body representations. A key challenge, however, is that real-world multimodal biomedical data are often missing not at random, which can reduce power, limit generalizability, and introduce bias. We propose Pan-FM, a pan-organ foundation model pre-trained on imaging from seven organs (Brain, Heart, Adipose, Liver, Kidney, Spleen, and Pancreas) under realistic missing-organ scenarios. Pan-FM uses a unified backbone that handles organ missingness during both training and inference, and is pre-trained with masking-based self-distillation. We find that naive multimodal pre-training leads to dominant-organ shortcut learning bias, with the model over-relying on dominant organs such as adipose and heart. To address this, we introduce Saliency-Guided Masking (SGM), which uses the model attention distribution to adaptively mask dominant organs during pre-training, thus encouraging more balanced cross-organ, whole-body learning. Notably, SGM introduces negligible computational overhead and can be seamlessly integrated into existing self-supervised learning frameworks to improve multi-organ representation learning. On the UK Biobank, Pan-FM achieves stronger prediction across 13 disease categories and 14 single disease entities than single-organ and multi-organ baselines, with improved robustness under missing-organ settings. Pan-FM serves as a scalable solution to realistic modality-missingness in multimodal learning in system neuroscience and as a step toward more generalizable whole-body FMs.

Qiangqiang Wu, Grace McIlvain, Zhou Yu +1

Laboratory of AI and Biomedical Science (LABS) · 2Columbia University

Missing-Modality Learning Medical Imaging Medical Imaging Foundation Models Multimodal Pretraining Multimodal Foundation Models Medical Image Representation Learning+1

May 7, 2026cs.CV

TRAJGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations

Multimodal self-supervised learning (MSSL) has emerged as a key paradigm for pretraining geospatial foundation models. However, existing geospatial MSSL methods are mainly designed for static pairs of modalities, such as satellite imagery, street-view imagery, and text, where learning is driven by aligning observations from the same or nearby locations. This assumption breaks down for human mobility trajectories, which represent continuous movement along paths rather than discrete observations at individual locations. Although trajectories are important for urban understanding through their ability to capture human activity across roads, neighborhoods, and places over time, they remain largely underexplored in current geospatial MSSL frameworks. We present TrajGANR, a novel trajectory-centric geospatial MSSL framework that aligns continuous movement patterns with static, location-based observations. TrajGANR learns a continuous neural representation of trajectories at arbitrary points along each path, which enables fine-grained alignment with nearby street-view images, even when they are not co-located with any trajectory waypoints. We leverage this capability to introduce an MSSL objective that jointly aligns three modalities: trajectories, street-view images, and their geographic locations. We evaluate TrajGANR on four urban mobility and road understanding tasks. Across these tasks, TrajGANR consistently outperforms existing geospatial MSSL frameworks and a trajectory-specific foundation model. Ablation studies further demonstrate that our proposed MSSL objective and the multimodal learning framework are the primary drivers of these improvements, highlighting the importance of fine-grained geospatial alignment over coarser aggregation, as well as geospatial multimodal learning.

Maria Despoina Siampou, Gengchen Mai, Ni Lao +4

Google Research, Mountain View, CA · Dept. of Computer Science, University of Southern California, Los Angeles, CA · SEAI Lab, Dept. of Geography and the Environment, The University of Texas at Austin, Austin, TX +1

Geospatial Foundation Models Cross-Modal Alignment Multimodal Pretraining Trajectory Representation Learning

May 7, 2026cs.CV

Knowledge Transfer Scaling Laws for 3D Medical Imaging

Vision foundation models are increasingly moving beyond 2D to volumetric domains such as 3D medical imaging, where unified pretraining across different imaging modalities (i.e. CT, MRI, and PET) could provide foundational models for diverse clinical tasks. However, training such models requires mixing heterogeneous imaging domains, and current mixture strategies remain largely heuristic. In this work, we observe that different medical imaging domains scale at variable rates during pretraining, and knowledge transfer between domains is strongly asymmetric: training on one domain can substantially improve another, but the reverse may be much weaker. Interestingly, both MAE reconstruction loss and cross-domain transfer follow predictable power-law trends with domain-specific behaviors. Motivated by these findings, we formulate data allocation as a scaling-law optimization problem. The derived allocations reveal an interpretable hub-and-island structure: highly transferable domains emerge as hubs that benefit many others and deserve strategic allocation, while isolated domains act as islands requiring direct investment. Empirically, transfer-aware allocation outperforms data-proportional sampling by up to 58% and generalizes well to unseen budgets with r=0.989. Downstream validation on disease classification and organ/lesion segmentation further confirms that the derived transfer-aware mixtures provide stronger pretrained representations for clinical 3D medical imaging tasks.

Ho Hin Lee, Dongna Du, Chu Wang +4

Vanderbilt University · Zhejiang University · McGill University +1

Medical Imaging Foundation Models 3D Medical Imaging Multimodal Pretraining Cross-Domain Transfer Learning Scaling Laws

May 5, 2026cs.CV

Audio-Visual Intelligence in Large Foundation Models

Audio-Visual Intelligence (AVI) has emerged as a central frontier in artificial intelligence, bridging auditory and visual modalities to enable machines that can perceive, generate, and interact in the multimodal real world. In the era of large foundation models, joint modeling of audio and vision has become increasingly crucial, i.e., not only for understanding but also for controllable generation and reasoning across dynamic, temporally grounded signals. Recent advances, such as Meta MovieGen and Google Veo-3, highlight the growing industrial and academic focus on unified audio-vision architectures that learn from massive multimodal data. However, despite rapid progress, the literature remains fragmented, spanning diverse tasks, inconsistent taxonomies, and heterogeneous evaluation practices that impede systematic comparison and knowledge integration. This survey provides the first comprehensive review of AVI through the lens of large foundation models. We establish a unified taxonomy covering the broad landscape of AVI tasks, ranging from understanding (e.g., speech recognition, sound localization) to generation (e.g., audio-driven video synthesis, video-to-audio) and interaction (e.g., dialogue, embodied, or agentic interfaces). We synthesize methodological foundations, including modality tokenization, cross-modal fusion, autoregressive and diffusion-based generation, large-scale pretraining, instruction alignment, and preference optimization. Furthermore, we curate representative datasets, benchmarks, and evaluation metrics, offering a structured comparison across task families and identifying open challenges in synchronization, spatial reasoning, controllability, and safety. By consolidating this rapidly expanding field into a coherent framework, this survey aims to serve as a foundational reference for future research on large-scale AVI.

You Qin, Kai Liu, Shengqiong Wu +12

National University of Singapore · University of Oxford · University of Toronto +5

Audio-Visual Understanding Audio-Video Generation Multimodal Pretraining Audio-Visual Alignment Multimodal Foundation Models

May 2, 2026cs.AI

Valley3: Scaling Omni Foundation Models for E-commerce

In this work, we present Valley3, an omni multimodal large language model (MLLM) developed for diverse global e-commerce tasks, with unified understanding and reasoning capabilities across text, images, video, and audio. A key feature of Valley3 is its native multilingual audio capability for e-commerce, developed by extending vision-language models to better support crucial audio-visual tasks, particularly in short-video scenarios. To achieve this, we carefully design a four-stage omni e-commerce continued pre-training pipeline, through which Valley3 progressively acquires audio understanding, cross-modal instruction-following, e-commerce domain knowledge, and long-context reasoning capabilities, ultimately evolving into an omni model for diverse e-commerce scenarios. Then, we further improve Valley3 through post-training to encourage long-chain reasoning with controllable reasoning modes, enabling one non-thinking mode and three distinct levels of thinking, thereby balancing inference efficiency in simple scenarios with deep reasoning for complex applications. Moreover, we equip Valley3 with agentic search capabilities to proactively invoke search tools and acquire task-relevant information for e-commerce deep research tasks. To comprehensively assess the capabilities of Valley3, we construct an omni e-commerce benchmark spanning 6 tasks. Experimental results show that Valley3 consistently outperforms strong baselines on our in-house and open-source e-commerce benchmarks, while remaining competitive on general-domain benchmarks. Our code and model weights are available at https://github.com/bytedance/Valley.

Zeyu Chen, Guanghao Zhou, Min Yang +6

Valley Team, ByteDance Group

Unified Multimodal Models Multimodal Pretraining Multimodal Large Language Models Multimodal Reasoning E-Commerce Multimodal Foundation Models+1

May 1, 2026cs.SD

GaMMA: Towards Joint Global-Temporal Music Understanding in Large Multimodal Models

In this paper, we propose GaMMA, a state-of-the-art (SoTA) large multimodal model (LMM) designed to achieve comprehensive musical content understanding. GaMMA inherits the streamlined encoder-decoder design of LLaVA, enabling effective cross-modal learning between music and language. By incorporating audio encoders in a mixture-of-experts manner, GaMMA effectively unifies both time-series and non-time-series music understanding tasks within one set of parameters. Our approach combines carefully curated datasets at scale with a progressive training pipeline, effectively pushing the boundaries of music understanding via pretraining, supervised fine-tuning (SFT), and reinforcement learning (RL). To comprehensively assess both temporal and non-temporal capability of music LMMs, we introduce MusicBench, the largest music-oriented benchmark, comprising 3,739 human-curated multiple-choice questions covering diverse aspects of musical understanding. Extensive experiments demonstrate that GaMMA establishes new SoTA in the music domain, achieving 79.1% accuracy on MuchoMusic, 79.3% on MusicBench-Temporal, and 81.3% on MusicBench-Global, consistently outperforming previous methods.

Zuyao You, Zhesong Yu, Mingyu Liu +3

1Fudan University · 2ByteDance

Multimodal Pretraining Multimodal Large Language Models Audio Understanding Audio-Language Models Music Information Retrieval Multimodal Model Evaluation+1

Apr 29, 2026cs.CV

A Multimodal Pre-trained Network for Integrated EEG-Video Seizure Detection

Reliable seizure detection in mouse models is essential for preclinical epilepsy research, yet manual review of synchronized video-EEG recordings is labor-intensive and single-modality systems fail for complementary reasons: video-based methods are easily confounded by benign behaviors, whereas EEG-based methods are vulnerable to ictal motion artifacts. We present EEGVFusion, a multimodal framework that combines self-supervised EEG representation learning, spatio-temporal video encoding, optimal-transport alignment, and bidirectional cross-attention to integrate neural and behavioral evidence. We also curate an expert-annotated dataset of synchronized EEG and video recordings comprising 93 sessions from 15 mice for training and evaluation. In the random-session split, EEGVFusion achieved a Balanced Accuracy of 0.9957 with perfect event sensitivity and an Event FAR of 0.6250 FP/h, indicating strong seizure detection performance with a low false-alarm burden. In a single held-out-subject evaluation with Subject 110 reserved for testing, EEGVFusion achieved a Balanced Accuracy of 0.9718 and reduced Event FAR from 2.7250 FP/h for the EEG-only counterpart to 0.4833 FP/h while preserving perfect event sensitivity. Targeted ablations further showed that EEG pre-training and OT alignment help reduce false alarms while preserving event sensitivity.

Tong Lu, Ke Xu, Zimo Zhang +12

Beijing Institute for Brain Research, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, 102206, China · Chinese Institute for Brain Research, Beijing, Beijing, 102206, China · Department of Neurosurgery, SanBo Brain Hospital, Capital Medical University, Beijing, 100018, China +4

Electroencephalography EEG Seizure Detection Multimodal Pretraining Multimodal Classification Multimodal Fusion

Apr 27, 2026cs.CV

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creating misalignment between the two tasks and preventing fully end-to-end optimization from raw pixels. We introduce Tuna-2, a native unified multimodal model that performs visual understanding and generation directly based on pixel embeddings. Tuna-2 drastically simplifies the model architecture by employing simple patch embedding layers to encode visual input, completely discarding the modular vision encoder designs such as the VAE or the representation encoder. Experiments show that Tuna-2 achieves state-of-the-art performance in multimodal benchmarks, demonstrating that unified pixel-space modelling can fully compete with latent-space approaches for high-quality image generation. Moreover, while the encoder-based variant converges faster in early pretraining, Tuna-2's encoder-free design achieves stronger multimodal understanding at scale, particularly on tasks requiring fine-grained visual perception. These results show that pretrained vision encoders are not necessary for multimodal modelling, and end-to-end pixel-space learning offers a scalable path toward stronger visual representations for both generation and perception.

Zhiheng Liu, Weiming Ren, Xiaoke Huang +12

Meta AI · University of Waterloo · The University of Hong Kong

Unified Multimodal Models Multimodal Pretraining Multimodal Generation Multimodal Foundation Models Multimodal Learning Multimodal Understanding

Apr 25, 2026cs.MM

OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models

The vast and underexplored ocean plays a critical role in regulating global climate and supporting marine biodiversity, yet artificial intelligence has so far delivered limited impact in this domain due to a fundamental data bottleneck. Specifically, ocean data are highly fragmented across disparate sources and inherently exhibit multi-modal, high-noise, and weakly labeled characteristics, lacking unified schemas and semantic alignment. Although Multimodal Large Language Models (MLLMs) have achieved remarkable success in general domains, their application to ocean science remains severely constrained by the absence of large-scale, well-aligned multimodal datasets tailored to marine environments. To bridge this gap, we introduce OceanPile, a large-scale multimodal corpus designed for ocean foundation models. It comprises three key components: OceanCorpus, a unified collection integrating sonar data, underwater imagery, marine science visuals, and scientific text from diverse authoritative sources; OceanInstruction, a high-quality instruction dataset synthesized via a novel pipeline guided by a hierarchical Ocean Concept Knowledge Graph; and OceanBenchmark, a manually curated evaluation benchmark for rigorous assessment. We establish a multi-stage quality control process to ensure scientific validity and alignment across modalities. Experimental validation demonstrates significant performance improvements for models trained on our data. All datasets are publicly released to advance the field of marine artificial intelligence and empower domain-specific MLLMs.

Yida Xue, Ningyu Zhang, Tingwei Wu +5

College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China. · School of Software Technology, Zhejiang University, Ningbo 315048, China. · State Key Laboratory of Ocean Sensing, Hangzhou 311200, China. +2

AI for Science Multimodal Pretraining Multimodal Instruction Tuning

Apr 24, 2026cs.CV

CheXmix: Unified Generative Pretraining for Vision Language Models in Medical Imaging

Recent medical multimodal foundation models are built as multimodal LLMs (MLLMs) by connecting a CLIP-pretrained vision encoder to an LLM using LLaVA-style finetuning. This two-stage, decoupled approach introduces a projection layer that can distort visual features. This is especially concerning in medical imaging where subtle cues are essential for accurate diagnoses. In contrast, early-fusion generative approaches such as Chameleon eliminate the projection bottleneck by processing image and text tokens within a single unified sequence, enabling joint representation learning that leverages the inductive priors of language models. We present CheXmix, a unified early-fusion generative model trained on a large corpus of chest X-rays paired with radiology reports. We expand on Chameleon's autoregressive framework by introducing a two-stage multimodal generative pretraining strategy that combines the representational strengths of masked autoencoders with MLLMs. The resulting models are highly flexible, supporting both discriminative and generative tasks at both coarse and fine-grained scales. Our approach outperforms well-established generative models across all masking ratios by 6.0% and surpasses CheXagent by 8.6% on AUROC at high image masking ratios on the CheXpert classification task. We further inpaint images over 51.0% better than text-only generative models and outperform CheXagent by 45% on the GREEN metric for radiology report generation. These results demonstrate that CheXmix captures fine-grained information across a broad spectrum of chest X-ray tasks. Our code is at: https://github.com/StanfordMIMI/CheXmix.

Ashwin Kumar, Robbie Holland, Corey Barrett +8

Stanford AIMI, Stanford University · Oracle Health AI · Department of Radiology, Stanford University

Radiology Report Generation Chest X-Ray Classification Radiology VLMs Unified Multimodal Models Multimodal Pretraining

Apr 23, 2026cs.CV

Context Unrolling in Omni Models

We present Omni, a unified multimodal model natively trained on diverse modalities, including text, images, videos, 3D geometry, and hidden representations. We find that such training enables Context Unrolling, where the model explicitly reasons across multiple modal representations before producing predictions. This process enables the model to aggregate complementary information across heterogeneous modalities, facilitating a more faithful approximation of the shared multimodal knowledge manifold and improving downstream reasoning fidelity. As a result, Omni achieves strong performance on both multimodal generation and understanding benchmarks, while demonstrating advanced multimodal reasoning capabilities, including in-context generation of text, image, video, and 3D geometry.

Ceyuan Yang, Zhijie Lin, Yang Zhao +16

Cross-Modal Learning Unified Multimodal Models Multimodal Pretraining Multimodal Reasoning Multimodal Generation Multimodal Foundation Models+1

Apr 21, 2026cond-mat.mtrl-sci

Multimodal Transformer for Sample-Aware Prediction of Metal-Organic Framework Properties

Metal-organic frameworks (MOFs) are a major target of machine-learning-based property prediction, yet most models assume that a single framework representation maps to a single property value. This assumption becomes problematic for experimental MOFs, where samples reported as the same framework can exhibit different properties because of differences in crystallinity, phase purity, defects, and other sample-dependent factors. Here we introduce Experimental X-ray Diffraction Integrated Transformer (EXIT), a multimodal transformer for sample-aware prediction of MOF properties that combines MOFid with X-ray diffraction (XRD). In EXIT, MOFid encodes MOF identity, whereas XRD provides complementary information about the experimentally realized sample state. EXIT is pre-trained on one million hypothetical MOFs with simulated XRD to learn transferable representations, leading to improved downstream performance relative to existing approaches. EXIT is fine-tuned on literature-derived experimental datasets for surface area and pore volume prediction. Incorporating experimental XRD improves predictive performance relative to models without experimental XRD, and attention analysis and sample-level case studies further show that EXIT assigns different predictions to samples sharing the same MOF identity when their XRD patterns differ. These results establish a practical step from framework-aware to sample-aware MOF property prediction and highlight the value of incorporating experimental characterization into porous materials informatics.

Seunghee Han, Jaewoong Lee, Jihan Kim

Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of Korea. · Department of Materials Science and Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of Korea.

Multimodal Pretraining Materials Property Prediction

Apr 18, 2026cs.CV

Better with Less: Tackling Heterogeneous Multi-Modal Image Joint Pretraining via Conditioned and Degraded Masked Autoencoder

Learning robust representations across extremely heterogeneous modalities remains a fundamental challenge in multi-modal vision. As a critical and profound instantiation of this challenge, high-resolution (HR) joint optical and synthetic aperture radar (SAR) pretraining seeks modality synergy to mutually enhance single-source representations; its potential is severely hindered by the Heterogeneity-Resolution Paradox: finer spatial scales drastically amplify the physical divergence between complex radar geometries and non-homologous optical textures. Consequently, migrating medium-resolution-oriented rigid alignment paradigms to HR scenarios triggers either severe feature suppression to force equivalence, or feature contamination driven by extreme epistemic uncertainty. Both extremes inevitably culminate in profound representation degradation and negative transfer. To overcome this bottleneck, we propose CoDe-MAE, pioneering a \textit{better synergy with less alignment} philosophy. First, Optical-anchored Knowledge Distillation (OKD) implicitly regularizes SAR's speckle noise by mapping it into a pure semantic manifold. Building on this, Conditioned Contrastive Learning (CCL) utilizes a gradient buffering mechanism to align shared consensus while safely preserving divergent physical signatures. Concurrently, Cross-Modal Degraded Reconstruction (CDR) deliberately strips non-homologous spectral pseudo-features, truncating the inherently ill-posed mapping to capture true structural invariants. Extensive analyses validate our theoretical claims. Pretrained on 1M samples, CoDe-MAE demonstrates remarkable data efficiency, successfully preventing representation degradation and establishing new state-of-the-art performance across diverse single- and bi-modal downstream tasks, substantially outperforming foundation models scaled on vastly larger datasets.

Bowen Peng, Yongxiang Liu, Jie Zhou +4

College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha 410073, China · Beijing Institute of Remote Sensing Information, Beijing 100192, China

Cross-Modal Learning Masked Autoencoders Cross-Modal Alignment Multimodal Pretraining Synthetic Aperture Radar Multimodal Contrastive Learning

Apr 18, 2026cs.CV

PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging

Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities. Model merging provides a cost-effective mechanism for integrating multiple expert MLLMs with complementary strengths into a unified model. However, existing model merging research mainly focuses on post-finetuning scenarios, leaving the pre-training stage largely unexplored. We argue that the core of MLLM pre-training lies in establishing effective cross-modal alignment, which bridges visual and textual representations into a unified semantic space. Motivated by this insight, we introduce the post-alignment merging task, which aims to integrate cross-modal alignment capabilities learned from heterogeneous multimodal pre-training. This setting introduces two key challenges: cross-domain parameter interference, where parameter updates learned from different data distributions conflict during merging, and layer-wise alignment contribution disparity, where different layers and projectors contribute unevenly to cross-modal alignment. To address them, we propose \textbf{PivotMerge}, a post-alignment merging framework for cross-modal projectors. PivotMerge incorporates two key components: Shared-space Decomposition and Filtering, which disentangles shared alignment patterns from domain-specific variations and suppresses conflicting directions, and Alignment-guided Layer-wise Merging, which assigns layer-specific merging weights based on differing alignment contributions. We construct systematic CC12M-based post-alignment merging scenarios for evaluation. Extensive experiments on multiple multimodal benchmarks show that PivotMerge consistently outperforms existing baselines, demonstrating its effectiveness and generalization ability.

Zibo Shao, Baochen Xiong, Xiaoshan Yang +4

State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · Pengcheng Laboratory, Shenzhen 518066, China · School of Artificial Intelligence, University of Chinese Academy Sciences, Beijing 100049, China +1

Cross-Modal Learning Cross-Modal Alignment Multimodal Pretraining Multimodal Large Language Models

Apr 13, 2026cs.CV

MedP-CLIP: Medical CLIP with Region-Aware Prompt Integration

Contrastive Language-Image Pre-training (CLIP) has demonstrated outstanding performance in global image understanding and zero-shot transfer through large-scale text-image alignment. However, the core of medical image analysis often lies in the fine-grained understanding of specific anatomical structures or lesion regions. Therefore, precisely comprehending region-of-interest (RoI) information provided by medical professionals or perception models becomes crucial. To address this need, we propose MedP-CLIP, a region-aware medical vision-language model (VLM). MedP-CLIP innovatively integrates medical prior knowledge and designs a feature-level region prompt integration mechanism, enabling it to flexibly respond to various prompt forms (e.g., points, bounding boxes, masks) while maintaining global contextual awareness when focusing on local regions. We pre-train the model on a meticulously constructed large-scale dataset (containing over 6.4 million medical images and 97.3 million region-level annotations), equipping it with cross-disease and cross-modality fine-grained spatial semantic understanding capabilities. Experiments demonstrate that MedP-CLIP significantly outperforms baseline methods in various medical tasks, including zero-shot recognition, interactive segmentation, and empowering multimodal large language models. This model provides a scalable, plug-and-play visual backbone for medical AI, combining holistic image understanding with precise regional analysis.

Jiahui Peng, He Yao, Jingwen Li +9

aSichuan University, Chengdu, 610065, China · bXinjiang University, Urumqi, 830046, China · cAlibaba Group, Hangzhou, 310023, China +3

Promptable Image Segmentation Multimodal Pretraining Medical VLMs Medical Image Grounding Vision-Language Alignment

Apr 9, 2026cs.CV

Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding

Empowering Large Multimodal Models (LMMs) with image generation often leads to catastrophic forgetting in understanding tasks due to severe gradient conflicts. While existing paradigms like Mixture-of-Transformers (MoT) mitigate this conflict through structural isolation, they fundamentally sever cross-modal synergy and suffer from capacity fragmentation. In this work, we present Symbiotic-MoE, a unified pre-training framework that resolves task interference within a native multimodal Mixture-of-Experts (MoE) Transformers architecture with zero-parameter overhead. We first identify that standard MoE tuning leads to routing collapse, where generative gradients dominate expert utilization. To address this, we introduce Modality-Aware Expert Disentanglement, which partitions experts into task-specific groups while utilizing shared experts as a multimodal semantic bridge. Crucially, this design allows shared experts to absorb fine-grained visual semantics from generative tasks to enrich textual representations. To optimize this, we propose a Progressive Training Strategy featuring differential learning rates and early-stage gradient shielding. This mechanism not only shields pre-trained knowledge from early volatility but eventually transforms generative signals into constructive feedback for understanding. Extensive experiments demonstrate that Symbiotic-MoE achieves rapid generative convergence while unlocking cross-modal synergy, boosting inherent understanding with remarkable gains on MMLU and OCRBench.

Xiangyue Liu, Zijian Zhang, Miles Yang +3

HKUST · Tencent Hunyuan

Cross-Modal Representation Learning Unified Multimodal Models Multimodal Pretraining Multimodal Generation Mixture-of-Experts Models

Mar 12, 2026cs.LG

Overcoming the Modality Gap in Context-Aided Forecasting

Context-aided forecasting (CAF) holds promise for integrating domain knowledge and forward-looking information, enabling AI systems to surpass traditional statistical methods. However, recent empirical studies reveal a puzzling gap: multimodal models often fail to outperform their unimodal counterparts. We hypothesize that this underperformance stems from poor context quality in existing datasets, as verification is challenging. To address these limitations, we introduce a semi-synthetic data augmentation method that generates contexts both descriptive of temporal dynamics and verifiably complementary to numerical histories. This approach enables massive-scale dataset creation, resulting in CAF-7M, a corpus of 7 million context-augmented time series windows, including a rigorously verified test set. We demonstrate that semi-synthetic pre-training transfers effectively to real-world evaluation, and show clear evidence of context utilization. Our results suggest that dataset quality, rather than architectural limitations, has been the primary bottleneck in context-aided forecasting.

Vincent Zhihao Zheng, Étienne Marcotte, Arjun Ashok +4

ServiceNow AI Research, Montréal, Canada · Department of Civil Engineering, McGill University, Montréal, Canada · DIRO, Université de Montréal, Montréal, Canada +1

Synthetic Data Augmentation Multimodal Pretraining Time Series Forecasting

Mar 6, 2026cs.CV

GreenRFM: Learning a resource-efficient radiology vision-language foundation model via supervision-centric pre-training

Radiology foundation models (RFMs) have largely inherited the scale-first recipe of natural-image vision--language pre-training. This recipe is difficult to deploy in 3D radiology, where training corpora are smaller, reports vary across institutions, and receiving hospitals often need local adaptation under privacy and compute constraints. We ask whether routine radiology reports can instead be converted into auditable diagnostic supervision that shapes the image encoder, text encoder, aligned space, and local-adaptation procedure. We develop GreenRFM, a supervision-centric pre-training framework organized around four empirical principles: More distilled, Ubiquitous, Semantic-enforcing, and Task-aligning (MUST) supervision. These principles convert noisy reports into structured diagnostic signals and use them to learn discriminative unimodal encoders plus an aligned image--text space for diagnosis-centered multimodal use. GreenRFM requires 24 GPU-hours on a single 24GB GPU (lightweight variant: 6GB VRAM, 4~hours) and reaches a zero-shot CT-RATE AUC of 84.8. Evaluations using more than 200,000 volumes from six institutions and two modalities show transfer to private clinical cohorts and to musculoskeletal MRI. On a local institutional cohort, computationally feasible retraining raises macro-AUC from 70.5 to 82.1. The aligned space also improves hepatocellular-carcinoma microvascular-invasion prediction and trans-arterial chemoembolization response analysis over established clinical scores. These results support supervision-centric pre-training as a practical route to resource-efficient, locally adaptable, diagnosis-centered radiology vision--language representations.

Yingtai Li, Shuai Ming, Qiuli Wang +13

School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China (USTC), Hefei, Anhui, 230026, China · Center for Medical Imaging, Robotics, Analytic Computing & Learning (MIRACLE), Suzhou Institute for Advanced Research, USTC, Suzhou, Jiangsu, 215123, China · Department of Radiology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, USTC, Hefei, Anhui, 230001, China +7

Medical Imaging Foundation Models Radiology VLMs Vision-Language Models VLM Adaptation Multimodal Pretraining

Mar 4, 2026cs.CV

MPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction

Zero-shot MRI reconstruction relies on generative priors, but single-modality unconditional priors produce hallucinations under severe ill-posedness. In many clinical workflows, complementary MRI acquisitions (e.g. high-quality structural scans) are routinely available, yet existing reconstruction methods lack mechanisms to leverage this additional information. We propose MPFlow, a zero-shot multi-modal reconstruction framework built on rectified flow that incorporates auxiliary MRI modalities at inference time without retraining the generative prior to improve anatomical fidelity. Cross-modal guidance is enabled by our proposed self-supervised pretraining strategy, Patch-level Multi-modal MR Image Pretraining (PAMRI), which learns shared representations across modalities. Sampling is jointly guided by data consistency and cross-modal feature alignment using pre-trained PAMRI, systematically suppressing intrinsic and extrinsic hallucinations. Extensive experiments on HCP and BraTS show that MPFlow matches diffusion baselines on image quality using only 20% of sampling steps while reducing tumor hallucinations by more than 15% (segmentation dice score). This demonstrates that cross-modal guidance enables more reliable and efficient zero-shot MRI reconstruction.

Seunghoi Kim, Chen Jin, Henry F. J. Tregidgo +2

University College London, UK · Centre for AI, DS&AI, AstraZeneca, UK

Cross-Modal Alignment Multimodal Pretraining Image Reconstruction Accelerated MRI Reconstruction

Mar 1, 2026cs.CL

MedGPT-oss: Training a General-Purpose Vision-Language Model for Biomedicine

Biomedical multimodal assistants have the potential to unify radiology, pathology, and clinical-text reasoning, yet a critical deployment gap remains: top-performing systems are either closed-source or computationally prohibitive, precluding the on-premises deployment required for patient privacy and PHI compliance. We introduce MEDGPT-OSS, an open-weight, 20B-parameter generalist vision-language model designed to facilitate open research in clinical AI. Rather than relying on architectural complexity, MEDGPT-OSS pairs the GPT-oss language backbone with a visual front-end via a optimized, three-stage training curriculum. By progressively domain-adapting these modules through rigorous data curation and long-context multimodal alignment, we demonstrate that a 20B model can bridge the capacity gap. It successfully outperforms larger open medical models on out-of-distribution (OOD) multimodal reasoning and complex text-only clinical tasks. By unifying diverse modalities under a single instruction-following interface, MEDGPT-OSS maintains a parameter-efficient footprint fully compatible with commodity GPUs. We release the complete training recipe, open-weight checkpoints, and a rigorous evaluation harness to serve as a verifiable foundation for privacy-preserving, institution-specific clinical AI research.

Kai Zhang, Zhengqing Yuan, Cheng Peng +10

Department of Computer Science and Engineering, Lehigh University · Department of Computer Science and Engineering, University of Notre Dame · Department of Health Outcomes & Biomedical Informatics, University of Florida +3

Healthcare Multimodal Pretraining Medical VLMs Clinical Reasoning Multimodal Foundation Models

Feb 27, 2026cs.AI

SleepLM: Natural-Language Intelligence for Human Sleep

We present SleepLM, a family of sleep-language foundation models that enable human sleep alignment, interpretation, and interaction with natural language. Despite the critical role of sleep, learning-based sleep analysis systems operate in closed label spaces (e.g., predefined stages or events) and fail to describe, query, or generalize to novel sleep phenomena. SleepLM bridges natural language and multimodal polysomnography, enabling language-grounded representations of sleep physiology. To support this alignment, we introduce a multilevel sleep caption generation pipeline that enables the curation of the first large-scale sleep-text dataset, comprising over 100K hours of data from more than 10,000 individuals. Furthermore, we present a unified pretraining objective that combines contrastive alignment, caption generation, and signal reconstruction to better capture physiological fidelity and cross-modal interactions. Extensive experiments on real-world sleep understanding tasks verify that SleepLM outperforms state-of-the-art in zero-shot and few-shot learning, cross-modal retrieval, and sleep captioning. Importantly, SleepLM also exhibits intriguing capabilities including language-guided event localization, targeted insight generation, and zero-shot generalization to unseen tasks. All code and data will be open-sourced.

Zongzhe Xu, Zitao Shuai, Eideen Mozaffari +3

University of California, Los Angeles

Multimodal Pretraining Cross-Modal Retrieval Language Modeling

Feb 26, 2026cs.CV

PRIMA: Pre-training with Risk-integrated Image-Metadata Alignment for Medical Diagnosis via LLM

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.

Yiqing Wang, Chunming He, Ming-Chen Lu +4

Department of Biomedical Engineering, Duke University, Durham, NC, USA · Department of Ophthalmology and Visual Sciences, University of Michigan, Ann Arbor, MI, USA

Cross-Modal Alignment Multimodal Pretraining Medical Image Classification Medical VLMs

Feb 18, 2026cs.CV

Xray-Visual Models: Scaling Vision models on Industry Scale Data

We present Xray-Visual, a unified vision model architecture for large-scale image and video understanding trained on industry-scale social media data. Our model leverages over 15 billion curated image-text pairs and 10 billion video-hashtag pairs from Facebook and Instagram, employing robust data curation pipelines that incorporate balancing and noise suppression strategies to maximize semantic diversity while minimizing label noise. We introduce a three-stage training pipeline that combines self-supervised MAE, semi-supervised hashtag classification, and CLIP-style contrastive learning to jointly optimize image and video modalities. Our architecture builds on a Vision Transformer backbone enhanced with efficient token reorganization (EViT) for improved computational efficiency. Extensive experiments demonstrate that Xray-Visual achieves state-of-the-art performance across diverse benchmarks, including ImageNet for image classification, Kinetics and HMDB51 for video understanding, and MSCOCO for cross-modal retrieval. The model exhibits strong robustness to domain shift and adversarial perturbations. We further demonstrate that integrating large language models as text encoders (LLM2CLIP) significantly enhances retrieval performance and generalization capabilities, particularly in real-world environments. Xray-Visual establishes new benchmarks for scalable, multimodal vision models, while maintaining superior accuracy and computational efficiency.

Shlok Mishra, Tsung-Yu Lin, Linda Wang +24

Meta-AI · MIT (work done while at Meta AI) · University of Maryland (work done while at Meta AI)

Vision Foundation Models Multimodal Pretraining Video Representation Learning Vision-Language Pretraining

Nov 21, 2025cs.LG

PrismSSL: One Interface, Many Modalities; A Single-Interface Library for Multimodal Self-Supervised Learning

We present PrismSSL, a Python library that unifies state-of-the-art self-supervised learning (SSL) methods across audio, vision, graphs, and cross-modal settings in a single, modular codebase. The goal of the demo is to show how researchers and practitioners can: (i) install, configure, and run pretext training with a few lines of code; (ii) reproduce compact benchmarks; and (iii) extend the framework with new modalities or methods through clean trainer and dataset abstractions. PrismSSL is packaged on PyPI, released under the MIT license, integrates tightly with HuggingFace Transformers, and provides quality-of-life features such as distributed training in PyTorch, Optuna-based hyperparameter search, LoRA fine-tuning for Transformer backbones, animated embedding visualizations for sanity checks, Weights & Biases logging, and colorful, structured terminal logs for improved usability and clarity. In addition, PrismSSL offers a graphical dashboard - built with Flask and standard web technologies - that enables users to configure and launch training pipelines with minimal coding. The artifact (code and data recipes) will be publicly available and reproducible.

Melika Shirian, Kianoosh Vadaei, Kian Majlessi +3

dept. Computer Engineering University of Isfahan Isfahan, Iran · dept. Computer Engineering University of Texas at Dallas Isfahan, Iran · dept. Artificial Intelligence University of Isfahan Isfahan, Iran

Self-Supervised Learning Multimodal Learning Multimodal Pretraining

Oct 17, 2025cs.LG

Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity

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.

Naoki Yoshida, Satoshi Hayakawa, Yuhta Takida +3

The University of Tokyo · Sony Group Corporation · Sony AI

Cross-Modal Learning Kernel Mean Embeddings Multimodal Pretraining Cross-Modal Retrieval Multimodal Classification Kernel Methods+2