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

Aug 5, 2026cs.LG

Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Language

Training multimodal models to align time series with language runs into a self-supervision trap. The usual recipe asks an LLM to read a series and write a description, so label quality is capped by the perceptual skill the model is supposed to learn. The data can never teach more than the labeler already knows. A second gap makes this worse: most datasets use a single variable, but the patterns that matter (cross-channel correlation, lead-lag structure, co-occurring anomalies) appear only with several variables, right where the labeling LLM's limits are most exposed. These two problems create a trilemma: existing methods are reliable, realistic, or scalable, but none achieves all three. We resolve this by decoupling perception from description. Deterministic code computes a set of statistics from real, open-source multivariate series; the LLM verbalizes those precomputed facts. Perception, which LLMs do poorly, is handled by computation, while the LLM handles expression. This produces CGTime, our 4B-parameter computation-grounded time-series-language model. CGTime outperforms far larger general-purpose models on multivariate understanding tasks: it attains the best multivariate fact score on our held-out benchmark (0.283 vs. 0.173 for GPT-4o-mini and 0.203 for GPT-5.4-nano), a gap that survives Holm-corrected paired significance tests against every baseline. It also states verifiable numerical facts in generated captions more accurately and covers a broader range of statistical properties.

Xinran Feng, Yi Xie, Chao Zhang +4

Thrust of Financial Technology, The Hong Kong University of Science and Technology (Guangzhou) · Technical University of Munich · Heilbronn Data Science Center, Munich Data Science Institute +1

Cross-Modal Representation Learning Multimodal Pretraining

Aug 3, 2026cs.CV

ReMiX-MAE: Learning Missing-Channel Cross-Modal Representations from RGB-Only Clinical Facial Videos for Sympathetic-Mediated Pain Assessment

Automated pain assessment in real clinics is limited by scarce clinically grounded facial video data with weak labels (often sequence-level self-report) and by the fact that pain cues can be subtle or near-neutral in RGB, while thermal and depth signals are informative yet impractical to deploy routinely. To address these challenges, we propose ReMiX-MAE (Reconstructing Missing Channel Cross-Modal Masked Autoencoder), a self-supervised multimodal masked pretraining framework that learns transferable facial representations from synchronized RGB, thermal, and depth videos and explicitly trains robustness to missing modalities, enabling RGB-only deployment. To fill the gap of clinically grounded facial pain data with video-level self-report and longitudinal treatment trajectories, we collect the Sympathetic Mediated Pain (SMP) dataset with paired pre- and post-recordings across multiple visits. Under RGB-only deployment, we evaluate ReMiX-MAE using both direct feature extraction and pseudo-multimodal features decoded from RGB. ReMiX-MAE consistently outperforms an RGB-only masked autoencoder baseline on SMP, with pseudo-multimodal features providing additional gains in the challenging five-class setting. Across external datasets, ReMiX-MAE further shows more robust and label-efficient transfer than RGB-only baselines, highlighting its advantage in data-limited clinical settings.

Nan Bi, Taoyue Wang, Lijun Yin +1

School of Computing, Binghamton University, Binghamton, NY, USA · Department of Anesthesiology, SUNY Upstate Medical University, Syracuse, NY, USA

Missing-Modality Learning Masked Autoencoders Multimodal Robustness Multimodal Pretraining

Aug 3, 2026cs.CV

HarMoE: Multi-Source Chest Radiograph Pretraining with Dataset-Disentangled Experts

Recent vision-language models for chest X-ray understanding are largely built on image-report alignment and therefore rely heavily on MIMIC-CXR as the dominant pretraining source. While effective at scale, this paradigm underexplores an important alternative source of supervision: a range of existing multi-label classification datasets, which provide cleaner and more explicit disease signals than free-text reports, and can offer broader pathology coverage when combined across sources. However, learning from such heterogeneous datasets is nontrivial, as differences in label ontologies, annotation protocols, acquisition pipelines, and report styles can cause models to entangle clinical semantics with dataset identity, leading to poor transfer despite increased scale. In this work, we revisit radiology VLM construction from the perspective of harmonized multi-source learning. We propose HarMoE, a dataset-aware mixture-of-experts framework that learns shared cross-dataset medical semantics while confining source-specific variation to lightweight residual experts in deeper decoder layers. To further exploit clean supervision from labeled datasets, we train in a unified disease vocabulary with masked multi-dataset supervision, enabling the model to leverage complementary annotations without introducing false negatives. Experiments on large-scale chest X-ray benchmarks show that HarMoE consistently improves zero-shot classification, out-of-distribution transfer, and grounding over strong baselines. Our results suggest that building robust radiology VLMs requires moving beyond single-source image-report alignment toward structured knowledge construction from heterogeneous datasets with cleaner supervision and broader coverage. Code and the 873k harmonized dataset will be released at https://github.com/Roypic/harmoe.

Haozhe Luo, Ziyu Zhou, Shelley Zixin Shu +1

ARTORG Center for Biomedical Engineering Research, University of Bern · Kaiko.AI, Zurich, Switzerland · Shanghai Jiao Tong University, Shanghai, China

Multi-Source Domain Adaptation Chest X-Ray Classification Radiology VLMs Mixture of Experts Multimodal Pretraining

Aug 3, 2026cs.IR

Douyin Multimodal Embedding Model Technical Report

Multimodal representation learning is a cornerstone of modern AI. By encoding multimodal queries and targets into vectors, it powers industrial search and recommendation and underpins modern agents. Real-world platforms with complex modalities and massive-scale content, such as Douyin, Xiaohongshu, and YouTube, demand both efficiency under billion-scale indexing and fine-grained discrimination for hard matching. Existing MLLM embedding models rarely satisfy both. Contrastive models are efficient but rely on pair-level supervision too coarse for fine-grained distinctions, while CoT-based models improve discrimination through explicit generation impractical to serve online. We present Douyin Multimodal Embedding (DME), a model trained in two stages to combine both strengths. Stage 1 performs large-scale contrastive pre-training that establishes a unified multimodal embedding space with broad modality and task coverage. Stage 2 supplements semantic sufficiency, the property that an embedding is grounded in retrieval-relevant evidence and preserves fine-grained counterpart-side semantics, via two mechanisms. Evidence-Grounded Typed Latent Reasoning organizes retrieval evidence through hidden-space latent reasoning, and Cross-Conditional Reconstruction enforces counterpart-side semantics through cross-directional autoregressive reconstruction. Both act only during training and add only marginal query-side overhead, so DME serves as efficiently as a standard contrastive encoder. On MMEB-v2, DME reaches state-of-the-art results at comparable scales for its 2B and 9B variants (74.8 and 78.4), with especially strong video and visual-document tasks. In production, DME delivers a 2.92% relative gain on Douyin's in-house offline evaluation set, is deployed across Douyin scenarios such as generative, image, and AI search, and yields a 0.1% Lifetime (LT) gain in online A/B testing on Douyin search.

Haonan Chen, Chu Li, Zhicheng Wang +4

ByteDance Douyin Search Multimodal Team · Renmin University of China GSAI

Multimodal IR Multimodal Pretraining Multimodal Embedding Multimodal Contrastive Learning

Jul 31, 2026cs.IR

GALA: Generative Aligned Learning for Adaptive Multimodal Representation in the Taobao Shangou Recommender System

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.

Jiping Liu, Zhongmin Zhang, Zisen Sang +7

Rajax Network Technology (Taobao Shangou of Alibaba) · Shanghai & Beijing, China · Central South University +1

Cross-Modal Alignment Multimodal Pretraining Multimodal Embedding Multimodal Recommendation

Jul 27, 2026cs.RO

Data Pyramid for Embodied Manipulation: A Survey

Multimodal foundation models learned to see and to speak by consuming the whole internet. Embodied agents admit no such shortcut, since they require data that couple observations with physical states and actions. These signals can be provided, to varying degrees, by multiple data sources. In this work, we organize the embodied data ecosystem as a "pyramid" spanning five complementary sources: real-robot data, UMI-style data, egocentric and exocentric data, simulation data, and general vision-language data. We organize the pyramid around the tension between scalability and robot alignment, and further characterize each source in terms of data quality, diversity, reusability, and physical fidelity. We then analyze recent embodied foundation models through the lens of their data recipes, examining how different sources are selected, aligned, and mixed during pretraining. For embodied brain models, vision-language-action models, and world-action models alike, we relate data composition to capabilities in perception, reasoning, planning, action generation, and world prediction. We close by discussing six open challenges: building large-scale tactile datasets, collecting failure and recovery data, developing scalable data-collection pipelines, aligning actions across embodiments, leveraging egocentric data for dexterous manipulation, and designing principled data recipes for robot learning. We hope this work paves the foundation for the design of next-generation embodied systems.

Yifan Ye, Yankai Fu, Yaoxu Lv +26

PKU · NTU · HKUST +8

Robotic Data Collection Robot Foundation Models Multimodal Pretraining Robotic Manipulation Robot Learning

Jul 27, 2026cs.AI

Scaling GUI Agents with Visual State Transitions

We introduce State Transition Pretraining (STP) as a new scaling axis for GUI agents. During the STP stage, we continually pretrain a unified multimodal model on visual state transitions by jointly optimizing inverse dynamics (predicting actions from state changes) and forward dynamics (predicting next states from current states and actions). This optimization equips the model with better action-grounded visual representations and an internal world model of GUI dynamics. When subsequently fine-tuned on trajectories with task instructions, our STP-trained models consistently outperform baselines trained solely via direct trajectory fine-tuning across agent benchmarks in both desktop and mobile GUI scenarios (AgentNetBench, AndroidControl, and GUIOdyssey). Further empirical studies show that joint dynamics optimization yields stable improvements over single-objective training, and downstream performance scales steadily with the volume of transition data.

Xiangyan Liu, Kaixin Li, Haonan Wang +6

NUS · UTS · University of Liverpool +1

World Models GUI Agents Multimodal Pretraining State Representation Learning

Jul 25, 2026cs.CV

mmSimPrior: Learning Simulation Priors for Data-Efficient and Generalizable Real-World Radar-based Human Motion Reconstruction

Millimeter-wave (mmWave) radar enables privacy-preserving and illumination-robust human motion reconstruction, but training generalizable models typically requires costly paired radar-motion recordings. Simulation can scale such supervision, yet even physics-based simulators cannot fully reproduce real-world multipath, clutter, hardware-specific response statistics, or distance-dependent resolution degradation, leaving a sim-to-real gap. We present mmSimPrior, a simulation-pretrained framework that factorizes transferable knowledge into signal, motion, and radar-to-motion mapping priors. To learn transferable signal and motion priors, we pretrain a multimodal radar encoder with a physics-informed domain-randomization curriculum designed to mitigate the sim-to-real gap by approximating real-world propagation- and acquisition-level variations, while a joint-temporal tokenizer learns a discrete prior over plausible human motion. A dual-mode mapping module predicts either motion-code distributions for structurally constrained zero-shot reconstruction or continuous motion parameters for flexible adaptation from limited real data. We further construct a 4.2M-frame, 31K-sequence dataset suite and introduce a No-Overlap Setting that prevents any exact subject-environment-location-motion tuple from appearing in both the adaptation and test sets. Experiments on mmSimPrior-Real and RT-Pose demonstrate consistent gains: with only 24 paired real sequences, mmSimPrior-Reg reduces MPJPE by 24.7-39.0% over the strongest baseline across the three environments, while mmSimPrior-Cls reduces zero-shot MPJPE by 8.5% without fine-tuning.

Cheng Guo, Qiming Cao, Shengkai Xu +4

University of North Carolina at Charlotte, Charlotte, NC, USA · Purdue University, West Lafayette, IN, USA

Synthetic Data Pretraining Sim-to-Real Transfer Multimodal Pretraining Millimeter-Wave Radar mmWave Radar Sensing

Jul 24, 2026cs.LG

LunarFM: A Shared Multimodal Representation of the Moon's Surface

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/

Marc Girona-Mata, Jakob Gawlikowski, Sumit Goski +6

German Aerospace Center (DLR) · European Space Resources Innovation Center (ESRIC) · Universidad de Antioquia

Geospatial Representation Learning Multimodal Pretraining Remote Sensing Multimodal Embedding Multimodal Foundation Models

Jul 24, 2026cs.CL

Scaling Native Multimodal Pre-Training From Scratch

Although large language models (LLMs) exhibit remarkable reasoning capabilities, their reliance on text-only pre-training restricts the perception of the multimodal physical world. Native multimodal pre-training avoids this limitation by training models from scratch on multimodal inputs, thereby achieving deep cross-modal integration and mitigating optimization asymmetries inherent to traditional late-fusion architectures. Despite these advantages, the scaling properties of this paradigm remain incompletely characterized. To address this gap, we investigate the optimal model size and token count for training a Transformer-based vision-language model under a fixed computational budget. Our study demonstrates that minimal objective loss adheres to a predictable compute law, whereas compute-optimal model sizes and token counts scale as power laws. Notably, language and multimodal objectives manifest distinct allocation trends. The language allocation exponents lie in a similar range across the different data mixtures. The multimodal model-allocation exponent decreases modestly with the multimodal token ratio, indicating a relative shift toward token allocation. Additionally, our scaling analysis yields a budget-compensation rule. Specifically, an additional multimodal-token budget can offset the text-efficiency penalty caused by incorporating visual information into native multimodal pre-training under a fixed compute budget. Downstream evaluations further reveal that native multimodal pre-training is associated with improved spatial reasoning and multimodal few-shot learning. Generally, this empirical research establishes the essential groundwork for predictably scaling multimodal foundation models.

Haoyuan Wu, Aoqi Wu, Hai Wang +3

The Chinese University of Hong Kong · LLM Department, Tencent

Cross-Modal Learning Multimodal Pretraining Scaling Laws Multimodal Foundation Models

Jul 23, 2026cs.AI

Multimodal Pretraining for Generalizable EEG Representation Learning

Electroencephalography (EEG) models used for epilepsy are often limited to specific datasets and tasks. This limited approach can make it challenging to apply these models across different datasets or in various situations. However, recent studies in foundation models and self-supervised learning suggest that an adaptable EEG backbone could support a range of EEG related tasks. In this study, we have developed a multimodal EEG foundation model that combines a raw signal encoder based on the Mamba architecture, a Vision Transformer (ViT)-style encoder for time-frequency data, and a lightweight encoder for text, all within a shared embedding space. The pretraining process relies on several innovative techniques, such as masked modeling, cross-view contrastive alignment, and temporal consistency losses. These methods are designed to create rich, seizure-relevant representations without requiring labeled data. To assess the efficacy and generalization of our pretrained model, we fine-tuned it on the canonical CHB-MIT seizure detection benchmark and additional seizure detection datasets, and conducted extensive experiments comparing different model variants. On the standard CHB-MIT split, our best single model achieved an AUROC of 0.874, and an ensemble variant reached 0.878 AUROC, representing state-of-the-art performance on this benchmark. In addition to standard train-test splits, we evaluated performance under a leave-one-subject-out (LOSO) protocol, which is rarely reported in prior EEG seizure modeling work and highlights the difficulty of patient-independent seizure detection, with a mean LOSO balanced accuracy of 0.558 across 19 subjects. Across datasets and evaluation settings, our multimodal foundation model enabled robust seizure detection and straightforward adaptation to new seizure detection scenarios, while also supporting interpretable seizure localization.

Targol Bakhtiarvand, Jugal Kalita, Adham Atyabi

Department of Computer Science, University of Colorado Colorado Springs, Colorado Springs, CO, USA

Cross-Subject EEG Decoding Electroencephalography EEG Seizure Detection Self-Supervised Pre-Training Multimodal Pretraining EEG Foundation Models

Jul 22, 2026q-bio.BM

Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design

Antibodies are essential proteins that play a central role in immune recognition by binding specific antigen molecules. Although recent protein language models have enabled progress in single-chain protein modeling and generation, they often fall short in antigen-specific antibody design, where effective modeling requires explicit pairing between antibody and antigen, particularly at the epitope level. To address these limitations, we introduce AAMFM, an Antigen-specific Antibody Multimodal Foundation Model that learns unified representations of antibody sequences and structures conditioned on antigen context. AAMFM incorporates rich antigen information including geometric interfaces and epitope annotations via a cross-modal adapter, enabling joint modeling of antibody-antigen interactions in a shared latent space. To further guide the model toward functional relevance, we fine-tune AAMFM using Calibrated Direct Preference Optimization (Cal-DPO), leveraging preference signals extracted from a strong structural prior to align learning with binding-specific objectives. Extensive experiments demonstrate that AAMFM achieves state-of-the-art performance in functional antibody design, revealing its potential for antigen-specific antibody engineering. Our code is available at https://github.com/XL-S224/AAMFM.

Xiaoliang Shi, Zichen Wang, Runze Ma +2

Shanghai Jiao Tong University

Multimodal Pretraining Protein Design Protein Representation Learning

Jul 21, 2026cs.CV

scMIR: a vision-language foundation model for single-cell light microscopy image representation

Single-cell light microscopy images have become an important data source for characterizing cell phenotypes, but their complexity and heterogeneity pose challenges to high-throughput automated analysis. Existing representation learning methods mostly rely on task-oriented modeling, which is limited by specific datasets and predefined tasks, making them difficult to generalize across different cell types and microscopy modalities, and experimental conditions. Although general-purpose methods have improved the generalization ability of image representation in recent years, their limited utilization of experimental background and biological context information still poses challenges in complex phenotypic analysis. Here, we propose scMIR, a vision-language foundation model for single-cell light microscopy image representation. By synergistically combining self-supervised image reconstruction with text-guided cross-modal alignment, scMIR can simultaneously encode morphological and biological semantic information in a unified representation space. scMIR is pre-trained on 207,957 image-text pairs, covering various cell types, microscopy modalities, and perturbation conditions. scMIR outperforms existing general models and task-oriented methods as systematically evaluated on various complex tasks using 16 benchmark datasets, including cell classification, clustering, phenotype inference, and batch effect correction tasks. Furthermore, scMIR shows a strong generalization ability across various tasks without requiring task-specific fine-tuning. With its unique advantages, we envision scMIR may promote the standardization and automation of high-throughput phenotyping workflows through supporting various downstream analysis tasks.

Yifan Shang, Jiahui Tan, Xiangxiang Zeng +1

Laser Metrology and Biomedicine Lab, Department of Biomedical Engineering, The Chinese University of Hong Kong, Hong Kong, China · State Key Laboratory of Chemo and Biosensing, College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China

Cross-Modal Representation Learning Visual Representation Learning Multimodal Pretraining Self-Supervised Visual Representation Learning Microscopy Image Analysis

Jul 20, 2026cs.AI

Pailitao-MMSearch: Building Native E-Commerce Multimodal Search Foundation

The evolution of e-commerce has fundamentally transformed how users search for products, shifting from simple text-based keyword queries to complex multimodal interactions that seamlessly combine product images, natural language descriptions, and mixed-intent instructions. However, existing approaches face a critical dilemma: single-modal specialist models, deployed independently for text retrieval, visual search, and voice recognition, operate in isolation and cannot handle cross-modal queries, while general-purpose vision-language models lack the domain-specific knowledge necessary for fine-grained product understanding, user behavior modeling, and commercial intent reasoning. In this work, we present Pailitao-MMSearch, one native e-commerce multimodal search foundation model designed to bridge this gap. Our approach introduces three key innovations: (1)HybSID (Hybrid Semantic ID);(2)a two-stage continual pre-training strategy; and (3)a hybrid reasoning post-training pipeline. Built upon Qwen and deployed on Taobao's Pailitao multimodal search platform, Pailitao-MMSearch achieves substantial improvements in online A/B testing, including up to +13.61% in Gross Merchandise Volume (GMV) and +8.21% in transaction volume compared to traditional multi-modal search pipeline, demonstrating the effectiveness of our native e-commerce multimodal search large language models.

Xiaohan Ye, Xu Chen, Zihan Gong +15

Taobao & Tmall Group of Alibaba

Multimodal IR Multimodal Pretraining E-Commerce Search Multimodal Large Language Models Multimodal Reasoning

Jul 17, 2026cs.LG

Monkey King Bang: A Unified Scientific Multimodal Foundation Model

Scientific discovery is increasingly shifting from isolated disciplines to multi-domain reasoning, and AI for science faces a similar transition. Existing systems are either specialised for individual domains or unify scientific data mainly through text tokenisation and prompt-based interfaces, limiting their ability to handle diverse scientific inputs, produce modality-native outputs, and support joint understanding, reasoning, and generation across scientific domains. We introduce MKB, a unified scientific multimodal model for both understanding and generation, built around a shared Transformer backbone and modality-tailored encoders, adapters, and decoders. MKB covers six scientific branches, including DNA, RNA, proteins, small molecules, earth science, and medical images, and supports native outputs such as biological sequences, molecular strings, meteorological fields, and segmentation masks. Training follows a two-stage modality-then-language curriculum: Stage 1 aligns modality-specific components with the frozen backbone, and Stage 2 consolidates them with the language backbone using mixed scientific and general corpora. Experiments show that MKB achieves competitive scientific understanding across biological and molecular benchmarks, produces high-fidelity native outputs for weather forecasting, biological generation, and medical-image segmentation, and largely retains the general capabilities of its Qwen3-VL backbone. These results demonstrate the feasibility of the proposed paradigm, suggesting that shared-backbone models with modality-tailored components can provide a promising foundation for future cross-domain scientific multimodal exploration. The model and code are publicly available at https://github.com/Shanghai-Academy-of-AI-For-Science/MKB and https://huggingface.co/sais-org/MKB.

Hesen Chen, Xinyu Su, Xiaomeng Yang +11

SAIS Team, Shanghai Academy of AI for Science

AI for Science Unified Multimodal Models Multimodal Pretraining Multimodal Generation Multimodal Foundation Models Multimodal Learning+1

Jul 17, 2026cs.LG

Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework

Multimodal-attributed graphs (MAGs), whose nodes carry modalities such as images and text alongside topological structure, now pervade applications including social platforms, e-commerce, and biomedical networks, offering richer semantic signals than single-modality graphs. In practice, such graphs are fragmented across privacy-restricted silos owned by different platforms and institutions, so learning a broadly transferable model over them demands collaborative training that never exposes raw data. This places the task at the intersection of multimodal graph learning and federated learning, yet existing methods cover only one side of it. To address the challenges from these two perspectives, we propose FedGAMMA, casting federated multimodal graph foundation learning as a two-stage semantic-structural alignment problem of federated pre-training and prompt-based fine-tuning. During pre-training, a shared-private semantic enhancer disentangles cross-modal commonality from modality-specific information, aligning it through optimal transport, a topology-aware graph fusion module decouples semantic and structural views via semantic residual graphs and dual positional encodings, and a dual-channel affinity-aware aggregation mechanism estimates client similarity from feature and graph centroids without exposing raw data. During fine-tuning, FedGAMMA adapts the pretrained encoder through lightweight graph-aware prompts, a shared prompt pool with controlled exploration, and channel-wise prompt synchronization. Experiments on twelve multimodal graph datasets show FedGAMMA consistently surpassing a broad range of baselines across downstream tasks, with gains of up to 12.96%. FedGAMMA further outperforms competitive baselines accross multi-domain datasets on multiple tasks with up to 5.71% under few-shot learning scenario.

Xunkai Li, Guohao Fu, Yuming Ai +4

Beijing Institute of Technology, Beijing, 100811, China

Multimodal Federated Learning Cross-Modal Alignment Multimodal Pretraining Federated Graph Learning Prompt Tuning Graph Foundation Models+1

Jul 16, 2026cs.CV

Video = World + Event Stream

We present Wan-Streamer v0.3, which reframes our native-streaming interaction model under a single organizing view: a video is a world plus an event stream. The world is the persistent context in which a video unfolds, including the environment, scene, subjects, ambient acoustic conditions, voice characteristics, and other relatively stable conditions. The event stream is everything that changes over time within that world, including scene or environmental changes, subject behavior, speech, and other sounds. This yields a general-purpose pretraining task over large amounts of real video: given a world and incoming input, predict how the world moves, changes, and responds in real time. The resulting competence can be specialized to a broad family of real-time downstream tasks. We instantiate it on real-time full-duplex audio-visual interaction, where the event stream is the agent's speech together with free-form behavior. Functionally, the model's multimodal understanding process is vision-language-action-like: it maps multimodal user input to language-form speech and behavior actions. Wan-Streamer v0.3 preserves the v0.2 operating point: 640x368 video at 25 FPS, a 160 ms streaming unit, approximately 200 ms model-side response latency, and approximately 550 ms total interaction latency under a 350 ms bidirectional network budget.

Lianghua Huang, Zhi-Fan Wu, Yupeng Shi +24

Wan Team, Alibaba Group

Audio-Visual Understanding Streaming Video Understanding Multimodal Pretraining Vision-Language-Action Models Multimodal Foundation Models

Jul 16, 2026cs.LG

Multimodal Semantic-Aware Contrastive Learning For False Negative Mitigation in 3D Medical Imaging

Multimodal Contrastive Learning (CL) has shown significant performance in aligning representations across various data modalities and improving downstream tasks, especially in healthcare. It works by minimizing the distance between matched (positive) data modalities, while maximizing the distance between mismatched (negative) samples. Traditional CL frameworks typically assume instance-based correspondence within data batches, treating all non-paired samples as negatives. However, this assumption often fails in medical settings, where samples may share high-level semantic attributes, leading to false negatives that degrade representation quality. In this paper, we propose Multimodal Semantic-Aware Contrastive Learning (MseaCL), a CL framework trained on a pediatric cohort of 3D brain magnetic resonance imaging (MRI) scans and radiology reports. The goal of this framework is to mitigate the impact of semantically similar false negative samples by incorporating semantic similarity between radiology reports, as a guiding signal during the learning process. Our results indicate that applying this framework as a pretraining stage can achieve notable improvements in downstream tasks, e.g., at least a 22.6% increase in the area under the receiver operating characteristic curve (AUC) of pediatric brain tumor molecular classification, demonstrating its potential for more robust and semantically aligned multimodal representations in clinical applications.

Sara Ketabi, Matthias W. Wagner, Cynthia Hawkins +3

University of Toronto · The Hospital for Sick Children · University Hospital Augsburg +1

Contrastive Learning 3D Medical Imaging Multimodal Pretraining Multimodal Contrastive Learning Medical Image Representation Learning

Jul 16, 2026cs.CV

Multimodality as Supervision: Self-Supervised Specialization to the Test Environment via Multimodality

Cross-modal learning, i.e., learning to predict one modality from another, is a fundamental mechanism for self-supervision via leveraging multimodality. Many practical applications, e.g., deploying a household robot, involve devices that are equipped with a rich set of sensors that enable multimodal sensing in their test environment. This presents an opportunity to apply cross-modal learning to the multimodal data sensed by these devices to learn representations. Findings in developmental psychology also suggest that biological agents leverage it to build an effective representation of their surroundings. To study this, we propose a controlled setup, where we restrict a user device to just a given test environment. It results in a specialization setup where we attempt to develop a performant model for this specific test environment. Under this setup, we develop Test-Space Training (TST), which performs multimodal data collection in the test environment and performs self-supervised pre-training on it. We evaluate these models on various downstream tasks in the same environment. Under this setup, we find various interesting insights, such as collecting rich multimodal data only from the test environment and leveraging cross-modal learning, we can achieve competitive results with generalist models (e.g., DINOv2 and CLIP) pre-trained on large-scale internet datasets. This enables an alternative scenario where the need for external Internet-scale datasets for pre-training models is reduced. We also present a set of analyses and ablations that raise intriguing points on substituting data with (multi)modality, and how varying pre-training data enables a tradeoff between a model's abilities to specialise to a test environment, and generalize to held-out spaces.

Kunal Pratap Singh, Ali Garjani, Rishubh Singh +6

Swiss Federal Institute of Technology Lausanne (EPFL) · Apple

Cross-Modal Learning Cross-Modal Representation Learning Self-Supervised Pre-Training Multimodal Pretraining Domain-Adaptive Pretraining

Jul 11, 2026cs.LG

Empowering Long-form Omni-modal Understanding with Robust Audio Perception

Recent advances in large-scale multimodal models have drivenremarkable progress in vision-language tasks; however, comprehensiveomni-modal understanding remains under-explored, largely due to thescarcity of datasets with rich, explicitly aligned auditory cues. To bridgethis gap, we present AVDC (Audio-Visual Decoupled Captions), a large-scaledataset designed to disentangle visual and auditory semantics. Specifi-cally, we propose an automated pipeline that leverages off-the-shelf mod-els to annotate videos with tripartite captions: visual-only (V), audio-only (A), and joint audio-visual (AV). This decoupled structure explic-itly captures both modality-specific nuances and complex cross-modalinteractions. Building upon this, we introduce AVDC-QA-CoT, a Chain-of-Thought augmented question-answering dataset to foster audio-visualreasoning. To fully exploit these resources, we employ a two-stage train-ing paradigm: omni-modal caption generation pre-training on AVDC, fol-lowed by instruction tuning on AVDC-QA-CoT. Extensive experiments acrossdiverse downstream tasks, spanning video captioning, audio-centric anal-ysis, and omni-modal benchmarks, demonstrate consistent and signifi-cant performance gains, showing the efficacy of our proposed datasetsand training strategy in advancing omni-modal perception. Code anddataset are related on https://radiant0726.github.io/AVDC-web/.

Kaiying Yan, Luoyi Sun, Xiao Zhou +1

SAI, Shanghai Jiao Tong University, shanghai, China · Zhejiang University, Hangzhou, Zhejiang, china · Shanghai AI Lab, shanghai, China

Audio-Visual Understanding Multimodal Pretraining Multimodal QA Audio-Visual QA

Jul 10, 2026cs.LG

A Foundation Model for Multimodal Event Sequences in Financial Applications

Predictive modeling is a core component of modern financial services, where a wide range of tasks are traditionally addressed using separate models trained on manually engineered tabular features. This task-specific approach limits reuse and makes it difficult to fully exploit heterogeneous data sources such as transaction histories and digital interaction signals. In this paper, we present an approach based on pretraining a foundation transformer model on multimodal sequences of user events. Events from multiple data sources are unified into a single chronological sequence, enabling early fusion of heterogeneous modalities and learning of general-purpose representations via a next-event prediction objective. These representations are combined with existing engineered user features, on top of which lightweight neural models are trained for multiple downstream tasks. The proposed system outperforms traditional task-specific models while reducing development overhead. The approach was deployed in production at one of the biggest banks in Eastern Europe, resulting in measurable improvements in business metrics.

Nikita Rusakov, Vladislav Meshkov, Konstantin Zorin +4

Sber Moscow, Russian Federation · Sber AI Lab Moscow, Russian Federation

Financial Services Multimodal Pretraining Multimodal Foundation Models Multimodal Fusion Sequence Modeling Finance

Jul 8, 2026cs.CV

MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models

Medicine is inherently multimodal, requiring clinicians to synthesize information across diverse data streams. Yet the development of multimodal foundation models is constrained by limited access to large-scale, high-quality clinical data. Although PubMed Central (PMC) offers a complementary source of expert-authored image-text data, existing PMC-derived resources remain limited in fidelity, reproducibility, and clinical validation. We introduce MedPMC, an automated, continuously updatable framework that transforms permissively licensed literature into high-fidelity infrastructure for medical multimodal models. Applied to 6.1 million PMC articles, MedPMC curated 11 million medical image-text pairs. Component evaluations showed strong performance for initial screening (F1 = 93.2), multi-panel figure detection (F1 = 96.5), figure separation (mAP = 89.8), caption separation and alignment (F1 = 81.4; ROUGE-L = 85.3), and medical figure classification (F1 = 96.5). Manual review by five annotators, three with medical training, found 95.3% of MedPMC images medically relevant, versus 19.7% in a prior PMC-derived dataset. Across 26 benchmarks spanning 11 specialties, a MedPMC-trained CLIP-style model improved average zero-shot AUC by 7.1 percentage points over the strongest architecture-matched biomedical CLIP baseline despite using fewer than half as many image-text pairs. As the vision encoder in a multimodal large language model, it improved medical visual question-answering by 1.9 and 16.9 percentage points across two benchmarks. In 10,524 Yale New Haven Health System dermatology photographs, it improved morphology-to-image retrieval Recall@5 by 11.7 percentage points. These findings show that high-fidelity literature curation strengthens medical multimodal foundation models across benchmark and clinical settings. We publicly release the framework, corpus, benchmarks, and pretrained models.

Hyunjae Kim, Dain Kim, Pan Xiao +25

Yale University, New Haven, CT, USA · Korea University, Seoul, South Korea · Washington University in St. Louis, St. Louis, MO, USA +4

Medical Imaging Foundation Models Training Data Curation Multimodal Pretraining Medical VLMs Multimodal Foundation Models Medical Image Benchmarks

Jul 7, 2026cs.CV

GaussFusion: Towards Multimodal 3D Gaussian Pretraining

3D Gaussian Splatting provides an explicit representation that jointly models geometry and appearance, serving as a scalable foundation for 3D representation learning. Existing pre-training methods for Gaussian representations, such as masked Gaussian reconstruction, primarily capture local structures but offer limited semantic supervision. In this paper, we propose GaussFusion, a multimodal pre-training framework for 3D Gaussian representations. GaussFusion integrates image and text supervision into masked Gaussian modeling through cross-modal semantic alignment, enabling the Gaussian encoder to learn both visual and language-level semantic information during pre-training. To better adapt masked modeling to the non-uniform distribution of Gaussian primitives, we further propose Gaussian Salience-guided Multi-scale Hole Masking (GSHM). GSHM constructs spatially continuous masked regions based on Gaussian salience. By applying hole masks at multiple scales, GSHM encourages the encoder to capture both fine-grained local patterns and broader structural dependencies. Extensive experiments on downstream tasks demonstrate that GaussFusion improves the transferability of Gaussian representations. Notably, GaussFusion outperforms Gaussian-MAE on ModelNet40 and ScanObjectNN (PB-T50-RS) by 0.61% and 3.85%, respectively.

Zhixuan You, Jihua Zhu, Yiding Sun +5

School of Software Engineering, Xi’an Jiaotong University, Xi’an, 710100, Shaanxi, China · Wuhu HIT Robot Technology Research Institute Co., Ltd., Wuhu, Anhui, China

3D Gaussian Splatting Cross-Modal Representation Learning Multimodal Pretraining 3D Representation Learning

Jul 3, 2026cs.CV

Moonstone: A Multimodal Foundation Model and Benchmark for Lunar Remote Sensing

Decades of orbital missions have produced multi-modal remote sensing data for the Moon, spanning optical imagery, spectroscopy, thermal emission, radar, gravity, and elemental composition. Yet these datasets remain fragmented across archives, and no benchmark exists for evaluating machine learning on lunar data. We introduce Moonstone, the first multi-modal foundation model benchmark for lunar remote sensing. Our contributions are: (1) a 28-channel, 128 pixels-per-degree (~237 m) global lunar pretraining dataset from seven instrument families across five missions, (2) MG-MAE, a modality-grouped masked autoencoder with per-group convolutional tokenizers, a shared Vision Transformer encoder, attention masking for missing modalities, coverage-adaptive masking for heterogeneous spatial coverage, and spectral continuity regularization for physically plausible reconstructions, and (3) a benchmark of six downstream tasks covering classification, regression, and segmentation. MG-MAE pretrained features outperform scratch baselines on all tasks and surpass both ImageNet-pretrained and vanilla MAE baselines by large margins. Data and code are available at https://huggingface.co/datasets/ayushprd/Moonstone and https://github.com/ayushprd/Moonstone .

Ayush Prasad, Swarnalee Mazumder

Space and Earth Observation Centre, Finnish Meteorological Institute, Finland · Data Management, German Climate Computing Centre, Germany

Missing-Modality Learning Masked Autoencoders Multimodal Pretraining Remote Sensing Remote Sensing Benchmarks

Jul 1, 2026cs.CV

Rosetta: Composable Native Multimodal Pretraining

Achieving true artificial general intelligence requires foundation models capable of integrating new modalities without forgetting prior knowledge. However, accommodating continuous generative objectives alongside discrete understanding tasks causes severe gradient conflicts. Existing architectures, including standard Mixture-of-Experts (MoE), are highly susceptible to representation overwriting. Even structurally partitioned paradigms like Mixture-of-Transformers (MoT) remain vulnerable to catastrophic forgetting, severely impeding multimodal scalability. In this work, we introduce Rosetta, a composable native multimodal pretraining framework designed for seamless and non-destructive modality expansion. Rosetta adopts a modular paradigm where core foundational knowledge is preserved within global shared experts, while modality-specific capabilities are distributed across plug-and-play experts. To guarantee non-destructive composition, we propose Momentum-Anchored Orthogonal Projection (MAOP). MAOP leverages the optimizer's momentum state as an implicit semantic anchor, selectively neutralizing conflicting gradient components from new modalities while preserving synergistic updates. Extensive evaluations demonstrate that, while standard MoE and MoT architectures suffer catastrophic forgetting of previously acquired knowledge, Rosetta robustly preserves established language and visual understanding. Furthermore, it delivers superior image generation and unlocks cross-modal synergy, paving the way for truly composable and unified multimodal foundation models. To facilitate further multimodal research, we release our code and checkpoints to the community. Project page at https://rosetta-lmm.github.io/.

Xiangyue Liu, Zijian Zhang, Miles Yang +3

HKUST · Tencent Hunyuan

Unified Multimodal Models Multimodal Pretraining Multimodal Generation Gradient Projection Multimodal Foundation Models Continual Learning for VLMs+2

Jun 29, 2026cs.CV

Orca: The World is in Your Mind

We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it through multimodal readout interfaces. Rather than optimizing isolated next-token, next-frame, or next-action prediction, we are centered on Next-State-Prediction modeling, offering a unified state-transition modeling route toward understanding, predicting, and acting upon the world. Orca learns through two complementary paradigms: unconscious learning captures dense natural state transitions from continuous videos, and conscious learning models sparse meaningful state transitions by language-described events and VQA supervision. For pre-training, we construct a large-scale world-learning inventory data, including 125K hours of video data and 160M event annotations. After pre-training, Orca learns a unified world latent space. To examine whether the learned latent supports downstream, we evaluate it by three representative downstream readouts: text generation, image prediction, and embodied action generation. Orca's backbone is frozen, and only the lightweight modality-specific decoders are trainable. Experiments show the scalability of the proposed paradigm and verify that stronger world latent enables stronger downstream readouts. Orca outperforms similar-sized specialized baselines. These results show that Orca, as a general world foundation model, presents a promising approach to understanding, predicting, and acting upon the world. Finally, we discuss the current limitations, aiming to provide useful insights and inspiration for the community.

Yihao Wang, Yuheng Ji, Mingyu Cao +54

World Model Learning Multimodal Pretraining Latent World Models Multimodal Foundation Models Embodied World Models Multimodal Understanding

Jun 29, 2026cs.RO

Heterogeneous Tactile Transformer

Tactile sensors are inherently heterogeneous: a model trained on one sensor cannot be directly used on another, which limits learning contact-rich manipulation policies from diverse tactile data at scale. To bridge this gap, we propose the Heterogeneous Tactile Transformer (HTT), a framework that learns shared tactile representations across heterogeneous sensors. HTT consists of sensor-specific encoders and a shared transformer trunk, and is pretrained with per-modality masked reconstruction together with cross-modal alignment between paired sensors. Pretraining uses our novel Heterogeneous Paired Tactile (HPT) dataset, containing 1.6M synchronized paired frames across four vision- and array-based tactile sensors. Across distinct tactile perception and real-world manipulation tasks, HTT is shown to learn transferable representations that adapt to new tasks and previously unseen sensors. Dataset, code, and model checkpoints will be released upon publication at https://jxbi1010.github.io/htt-gh-page/.

Jianxin Bi, Qiang Wang, Jayaram Reddy +4

National University of Singapore · Carnegie Mellon University · 3Smart Systems Institute, NUS

Representation Learning Multimodal Pretraining Cross-Domain Transfer Learning Tactile Sensing for Robotic Manipulation

Jun 26, 2026cs.LG

NIVA: A Multimodal Foundation Model for Actionable Earth System Intelligence

Recent advances in AI-driven weather and climate modeling have improved forecast skill while reducing computational cost. However, existing data-driven approaches are limited in their ability to model coupled Earth system dynamics, which is required for extending predictability beyond the ~2-week horizon. To address this, we introduce NIVA, a multimodal foundation model designed to learn unified representations across Earth system components. While the full framework targets atmosphere, ocean, ice, and land interactions, we focus here on a two-modality setting (ocean and atmosphere) as a controlled proof of concept to evaluate whether foundation models can learn coupled dynamics. Trained on large-scale Earth system simulations, NIVA learns physically meaningful cross-modal structure, providing a foundation for subseasonal-to-seasonal prediction. As initial validation, we show that NIVA captures key modes of climate variability through accurate prediction of major climate indices.

Anisha Pal, Aodhan Sweeney, Kyle Heyblom +1

Independent Researcher · Work done while at Planette AI · Planette AI, USA.

Climate Science Multimodal Pretraining Time Series Forecasting Climate Modeling Time-Series Foundation Models

Jun 25, 2026cs.CV

ViQ: Text-Aligned Visual Quantized Representations at Any Resolution

A unified representation for text and vision is a natural pursuit, as it enables simpler multimodal modeling and more efficient training. However, representing images as discrete signals in the same way as text inevitably introduces severe information loss. Existing work struggles to balance low-level details and high-level semantics in discrete representations: reconstruction-oriented representations often lack semantic information, whereas semantically stronger features typically suffer from severe loss of detail. We present ViQ, a Visual Quantized Representations framework, which is designed to balance semantics and details in discrete representations while supporting inputs at native resolutions, thereby enabling it to serve as a unified and general discrete representation for arbitrary visual inputs. Our approach structures quantization learning into two stages: text-aligned pre-training and feature discretization. With text-aligned pre-training, we enhance the visual encoder semantic-rich supervision from the pretrained language model and enable it to process native-resolution visual inputs. During discretization, we propose a proximal representation learning strategy to progressively compact the feature space, along with a position-aware head-wise quantization mechanism that enables flexible processing of arbitrary resolutions. Extensive experiments on multimodal tasks demonstrate that ViQ achieves competitive performance compared to state-of-the-art multimodal vision encoders with continuous and high-dimensional visual features, while maintaining high precision in low-level reconstruction. We also show that multimodal training with visual quantized representations largely improves efficiency, yielding up to 20%-70% acceleration with different base LLMs and training recipes.

Xumin Yu, Zuyan Liu, Zhenyu Yang +5

Tencent HY Vision Team · Tsinghua University · Institute of Automation, CAS +1

Visual Representation Learning Multimodal Pretraining Vision-Language Alignment Visual Token Compression Multimodal Understanding

Jun 23, 2026cs.CV

MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning

Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning. Since audio and visual streams naturally co-occur in video data, extending this success to jointly learn from both modalities is a natural next step, yet it remains challenging. Existing audio-visual self-supervised methods rely on modality-specific encoders and complex combinations of contrastive or reconstruction objectives, limiting cross-modal synergy and scalability. Joint Embedding Predictive Architectures (JEPAs) offer a simple, modality-agnostic alternative, but have to date been applied primarily to individual modalities. We introduce MJEPA, a joint-embedding predictive architecture for audio-visual learning that uses a single, unified encoder for both modalities. Our approach uses only a single predictive objective, applied both within and across modalities. We show that cross-modal prediction is critical: without it, a shared encoder degrades below unimodal baselines; with it, each modality's representation benefits from the other. Our frozen ViT-g model outperforms the best prior frozen baseline by over 6.8 mAP on AudioSet-20K, surpasses fully finetuned models on ESC-50 and FSD50K, and is competitive on video benchmarks despite using 10x less video data.

Revant Teotia, Adrien Bardes, Michael Rabbat +3

1FAIR at Meta · 2New York University

Audio-Visual Representation Learning Joint-Embedding Predictive Architecture Multimodal Pretraining