Multimodal Contrastive Learning

Recent advancements in integrating tactile sensing into vision-language-action (VLA) models have demonstrated transformative potential for robotic perception. However, existing tactile representations predominantly rely on qualitative descriptors (e.g., texture), neglecting quantitative contact states such as force magnitude, contact geometry, and principal axis orientation, which are indispensable for fine-grained manipulation. To bridge this gap, we propose FG-CLTP, a fine-grained contrastive language tactile pretraining framework. We first introduce a novel dataset comprising over 100k tactile 3D point cloud-language pairs that explicitly capture multidimensional contact states from the sensor's perspective. We then implement a discretized numerical tokenization mechanism to achieve quantitative-semantic alignment, effectively injecting explicit physical metrics into the multimodal feature space. The proposed FG-CLTP model yields a 95.9% classification accuracy and reduces the regression error (MAE) by 52.6% compared to state-of-the-art methods. Furthermore, the integration of 3D point cloud representations establishes a sensor-agnostic foundation with a minimal sim-to-real gap of 3.5%. Building upon this fine-grained representation, we develop a 3D tactile-language-action (3D-TLA) architecture driven by a flow matching policy to enable multimodal reasoning and control. Extensive experiments demonstrate that our framework significantly outperforms strong baselines in contact-rich manipulation tasks, providing a robust and generalizable foundation for tactile-language-action models.

Brain imaging classification is commonly approached from two perspectives: modeling the full image volume to capture global anatomical context, or constructing ROI-based graphs to encode localized and topological interactions. Although both representations have demonstrated independent efficacy, their relative contributions and potential complementarity remain insufficiently understood. Existing fusion approaches are typically task-specific and do not enable controlled evaluation of each representation under consistent training settings. To address this gap, we propose a unified cross-view contrastive framework for joint imaging-ROI representation learning. Our method learns subject-level global (imaging) and local (ROI-graph) embeddings and aligns them in a shared latent space using a bidirectional contrastive objective, encouraging representations from the same subject to converge while separating those from different subjects. This alignment produces comparable embeddings suitable for downstream fusion and enables systematic evaluation of imaging-only, ROI-only, and joint configurations within a unified training protocol. Extensive experiments on the ADHD-200 and ABIDE datasets demonstrate that joint learning consistently improves classification performance over either branch alone across multiple backbone choices. Moreover, interpretability analyses reveal that imaging-based and ROI-based branches emphasize distinct yet complementary discriminative patterns, explaining the observed performance gains. These findings provide principled evidence that explicitly integrating global volumetric and ROI-level representations is a promising direction for neuroimaging-based brain disorder classification. The source code is available at https://anonymous.4open.science/r/imaging-roi-contrastive-152C/.

Open-domain visual entity recognition (VER) seeks to associate images with entities in encyclopedic knowledge bases such as Wikipedia. Recent generative methods tailored for VER demonstrate strong performance but incur high computational costs, limiting their scalability and practical deployment. In this work, we revisit the contrastive paradigm for VER and introduce WikiCLIP, a simple yet effective framework that establishes a strong and efficient baseline for open-domain VER. WikiCLIP leverages large language model embeddings as knowledge-rich entity representations and enhances them with a Vision-Guided Knowledge Adaptor (VGKA) that aligns textual semantics with visual cues at the patch level. To further encourage fine-grained discrimination, a Hard Negative Synthesis Mechanism generates visually similar but semantically distinct negatives during training. Experimental results on popular open-domain VER benchmarks, such as OVEN, demonstrate that WikiCLIP significantly outperforms strong baselines. Specifically, WikiCLIP achieves a 16% improvement on the challenging OVEN unseen set, while reducing inference latency by nearly 100 times compared with the leading generative model, AutoVER. The project page is available at https://artanic30.github.io/project_pages/WikiCLIP/

Cross-modal Geo-localization (CMGL) matches ground-level text descriptions with geo-tagged aerial imagery, which is crucial for pedestrian navigation and emergency response. However, existing studies are constrained by narrow geographic coverage and simplistic scene diversity, failing to reflect the immense spatial heterogeneity of global architectural styles and topographic features. To bridge this gap and facilitate universal positioning, we introduce CORE, the first million-scale dataset dedicated to global CMGL. CORE comprises 1,034,786 cross-view images sampled from 225 distinct geographic regions across six continents, offering an unprecedented variety of perspectives in varying environmental conditions and urban layouts. We leverage the zero-shot reasoning of Large Vision-Language Models (LVLMs) to synthesize high-quality scene descriptions rich in discriminative cues. Furthermore, we propose a physical-law-aware network (PLANET) for cross-modal geo-localization. PLANET introduces a novel contrastive learning paradigm to guide textual representations in capturing the intrinsic physical signatures of satellite imagery. Extensive experiments across varied geographic regions demonstrate that PLANET significantly outperforms state-of-the-art methods, establishing a new benchmark for robust, global-scale geo-localization. The dataset and source code will be released at https://github.com/YtH0823/CORE.

Contrastive learning has become a fundamental approach in both uni-modal and multi-modal frameworks. This learning paradigm pulls positive pairs of samples closer while pushing negatives apart. In the uni-modal setting (e.g., image-based learning), previous research has shown that the strength of these forces can be controlled through the temperature parameter. In this work, we propose Multi-Modal Temperature and Margin Schedules (MM-TS), extending the concept of uni-modal temperature scheduling to multi-modal contrastive learning. Our method dynamically adjusts the temperature in the contrastive loss during training, modulating the attraction and repulsion forces in the multi-modal setting. Additionally, recognizing that standard multi-modal datasets often follow imbalanced, long-tail distributions, we adapt the temperature based on the local distribution of each training sample. Specifically, samples from dense clusters are assigned a higher temperature to better preserve their semantic structure. Furthermore, we demonstrate that temperature scheduling can be effectively integrated within a max-margin framework, thereby unifying the two predominant approaches in multi-modal contrastive learning: InfoNCE loss and max-margin objective. We evaluate our approach on four widely used image- and video-language datasets, Flickr30K, MSCOCO, EPIC-KITCHENS-100, and YouCook2, and show that our dynamic temperature and margin schedules improve performance and lead to new state-of-the-art results in the field.

Contrastive Language-Image Pre-training (CLIP) has shown impressive performance in aligning visual and textual representations. Recent studies have extended this paradigm to 3D vision to improve scene understanding for autonomous driving. A common strategy is to employ pairwise cosine similarity between modalities to guide the training of a 3D encoder. However, considering the similarity between individual modality pairs rather than all modalities jointly fails to ensure consistent and unified alignment across the entire multimodal space. In this paper, we propose a Contrastive Tensor Pre-training (CTP) framework that simultaneously aligns multiple modalities in a unified embedding space to enhance end-to-end autonomous driving. Compared with pairwise cosine similarity alignment, our method extends the 2D similarity matrix into a multimodal similarity tensor. Furthermore, we introduce a tensor loss to enable joint contrastive learning across all modalities. For experimental validation of our framework, we construct a text-image-point cloud triplet dataset derived from existing autonomous driving datasets. The results show that our proposed unified multimodal alignment framework achieves favorable performance for both scenarios: (i) aligning a 3D encoder with pretrained CLIP encoders, and (ii) pretraining all encoders from scratch.

Astronomers have acquired vast repositories of multimodal data, including images, spectra, and time series, complemented by decades of literature that analyzes astrophysical sources. Still, these data sources are rarely systematically integrated. This work introduces a contrastive learning framework designed to align X-ray spectra with domain knowledge extracted from scientific literature, facilitating the development of shared multimodal representations. Establishing this connection is inherently complex, as scientific texts encompass a broader and more diverse physical context than spectra. We propose a contrastive pipeline that achieves a 20% Recall@1% when retrieving texts from spectra, proving that a meaningful alignment between these modalities is not only possible but capable of accelerating the interpretation of rare or poorly understood sources. Furthermore, the resulting shared latent space effectively encodes physically significant information. By fusing spectral and textual data, we improve the estimation of 20 physical variables by 16-18% over unimodal spectral baselines. Our results indicate that a Mixture of Experts (MoE) strategy, which leverages both unimodal and shared representations, yields superior performance. Finally, outlier analysis within the multimodal latent space identifies high-priority targets for follow-up investigation, including a candidate pulsating ULX (PULX) and a gravitational lens system. Importantly, this framework can be extended to other scientific domains where aligning observational data with existing literature is possible.

Image--text contrastive pretraining has become a dominant paradigm for visual representation learning, yet existing methods often yield representations that remain partially organized by modality rather than by semantics. We propose ITO, a framework addressing this limitation through two complementary mechanisms with distinct roles. Multimodal multiple alignment enriches supervision by constructing diverse cross-modal correspondences from multi-view image augmentations, providing the primary source of discriminative gain. A lightweight training-time multimodal fusion module then acts as a training-time regularizer, encouraging the encoders to produce features that are compatible under fusion. Crucially, the fusion module is discarded at inference, preserving the efficiency of standard dual-encoder architectures while incurring training-time overhead only. Extensive experiments across pretraining scales from millions to billions of image--text pairs show that ITO outperforms strong contrastive baselines at moderate scale and yields consistent gains over CLIP under identical data, backbone, and compute at the 100M--1B scale, on classification, retrieval, and multimodal benchmarks. Controlled comparisons show that these gains are not explained by additional training compute or image augmentation alone. Our analysis further reveals that the contribution of fusion grows with data scale and that it stabilizes optimization, mitigating the late-stage overfitting commonly observed in aggressive contrastive learning. Code is available at https://github.com/showstarpro/ITO.

Unifying text-image contrastive learning and text-to-image (T2I) generation in a single end-to-end model is challenging because the two objectives demand opposing masking regimes: contrastive alignment needs near-complete visible tokens, while masked generative modeling needs heavy corruption. We introduce DREAM, a unified framework that resolves this conflict through Masking Warmup, a schedule that shifts the center of the masking distribution over training, so low and high masking ratios coexist at every step. This co-exposure lets a single jointly-trained encoder serve both objectives. The resulting stable optimization unlocks Semantically Aligned Decoding at inference: the text encoder, trained against visual embeddings at all masking ratios, can score partially generated images and select the best trajectory with as little as 12.5% of the image decoded, improving both FID and throughput. DREAM outperforms its single-objective baselines, CLIP and FLUID: on ImageNet linear-probing (+1.1%), 5-shot transfer (+4.1%), ADE20K segmentation (+1.9%), and NYU depth estimation (+6.25%) over CLIP, and on CC12M FID (+6.2%) over FLUID while maintaining CLIP Score. Together, these gains show that text-image contrastive and generative objectives, when properly unified, are synergistic rather than competing.

Recent multimodal systems often rely on separate expert modality encoders which cause linearly scaling complexity and computational overhead with added modalities. While unified Omni-models address this via Mixture-of-Expert (MoE) architectures with specialized experts and routing, they still inflate parameter counts and introduce routing overhead. In this paper, we propose Omni-C (Omni-Compress), a single dense Transformer-based encoder that learns competitive shared representations across heterogeneous modalities--images, audio, and text--through unimodal contrastive pretraining on large-scale unaligned data. By maximizing parameter sharing in the backbone and using lightweight modality-specific projection heads, Omni-C effectively mitigates inter-modality conflicts without requiring MoE, paired supervision, or routing. This design supports efficient deployment on memory-constrained systems via sequential modality processing and low-memory inference, eliminating the need for parallel expert loading or specialized hardware. Experiments show Omni-C achieves performance comparable to expert models in unimodal and cross-model tasks, with modest zero-shot degradation on audio and text that is largely recovered through lightweight linear probing or parameter efficient fine-tuning. The unified architecture substantially reduces inference memory usage compared to multi-encoder baselines, advancing efficient and scalable multimodal learning.

Electroencephalography (EEG) foundation models have shown promise for learning generalizable representations, yet they remain sensitive to channel heterogeneity, such as changes in channel composition or ordering. We propose channel-aware multimodal EEG-text alignment contrastive language image pretraining (CAMEL-CLIP), a contrastive EEG-text multimodal foundation model designed to be robust to heterogeneous channel configurations and widely applicable to diverse downstream tasks. CAMEL-CLIP combines three components: (1) channel attribute-based positional encoding, which identifies channels using their anatomical attributes and reference type; (2) dynamic channel projection, which preserves channel-specific information across varying numbers of EEG channels and combines textual reports with channel information to support channel-wise EEG-text matching; and (3) dual-level contrastive learning, which aligns EEG signals with text at both the individual-channel and whole-sample levels. Experimental results show that CAMEL-CLIP achieves the highest mean balanced accuracy among the evaluated baselines across multiple datasets under linear probing. CAMEL-CLIP also shows high classification performance when transferred between different channel configurations without classifier retraining.

Recent multimodal models such as Contrastive Language-Image Pre-training (CLIP) have shown remarkable ability to align visual and linguistic representations. However, domains where small visual differences carry large semantic significance, such as diagram understanding, remain challenging due to the models' limited sensitivity to fine-grained structural variations. We propose a new training paradigm designed to enhance diagram comprehension in vision-language models. Our approach introduces pseudo contrastive samples generated by a diagram renderer that creates synthetic diagrams using randomly picked text elements. These samples highlight structural differences in diagrammatic imagery without requiring any modification or editing of the original data. By incorporating these pseudo contrastive samples into the training objective, the model learns to capture more precise and semantically consistent diagram structures. Empirical evaluations on a benchmark dataset of flowcharts demonstrate substantial improvements over standard CLIP and hard-negative CLIP training in both image-text matching and visual question answering tasks. The results underscore the value of domain-specific training strategies and contribute to advancing diagrammatic understanding within the broader context of vision-language learning.

Accurate interpretation of electrocardiogram (ECG) signals is crucial for diagnosing cardiovascular diseases. Recent multimodal approaches that integrate ECGs with accompanying clinical reports show strong potential, but they still face two main concerns from a modality perspective: (1) intra-modality: existing models process ECGs in a lead-agnostic manner, overlooking spatial-temporal dependencies across leads, which restricts their effectiveness in modeling fine-grained diagnostic patterns; (2) inter-modality: existing methods directly align ECG signals with clinical reports, introducing modality-specific biases due to the free-text nature of the reports. In light of these two issues, we propose CG-DMER, a contrastive-generative framework for disentangled multimodal ECG representation learning, powered by two key designs: (1) Spatial-temporal masked modeling is designed to better capture fine-grained temporal dynamics and inter-lead spatial dependencies by applying masking across both spatial and temporal dimensions and reconstructing the missing information. (2) A representation disentanglement and alignment strategy is designed to mitigate unnecessary noise and modality-specific biases by introducing modality-specific and modality-shared encoders, ensuring a clearer separation between modality-invariant and modality-specific representations. Experiments on three public datasets demonstrate that CG-DMER achieves state-of-the-art performance across diverse downstream tasks.

Edge-based representations are fundamental cues for visual understanding, a principle rooted in early vision research and still central today. We extend this principle to vision-language alignment, showing that isolating and aligning structural cues across modalities can greatly benefit fine-tuning on long, detail-rich captions, with a specific focus on improving cross-modal retrieval. We introduce StructXLIP, a fine-tuning alignment paradigm that extracts edge maps (e.g., Canny), treating them as proxies for the visual structure of an image, and filters the corresponding captions to emphasize structural cues, making them "structure-centric". Fine-tuning augments the standard alignment loss with three structure-centric losses: (i) aligning edge maps with structural text, (ii) matching local edge regions to textual chunks, and (iii) connecting edge maps to color images to prevent representation drift. From a theoretical standpoint, while standard CLIP maximizes the mutual information between visual and textual embeddings, StructXLIP additionally maximizes the mutual information between multimodal structural representations. This auxiliary optimization is intrinsically harder, guiding the model toward more robust and semantically stable minima, enhancing vision-language alignment. Beyond outperforming current competitors on cross-modal retrieval in both general and specialized domains, our method serves as a general boosting recipe that can be integrated into future approaches in a plug-and-play manner. Code and pretrained models are publicly available at: https://github.com/intelligolabs/StructXLIP.

In multimodal learning, CLIP has emerged as the de-facto approach for mapping different modalities into a shared latent space by bringing semantically similar representations closer while pushing apart dissimilar ones. However, CLIP-based contrastive losses exhibit unintended behaviors that negatively impact true semantic alignment, leading to sparse and fragmented latent spaces. This phenomenon, known as the modality gap, has been partially mitigated for standard text and image pairs but remains unknown and unresolved in more complex multimodal settings, such as the medical domain. In this work, we study this phenomenon in the latter case, revealing that the modality gap is present also in medical alignment, and we propose a modality-agnostic framework that closes this gap, ensuring that semantically related representations are more aligned, regardless of their source modality. Our method enhances alignment between radiology images and clinical text, improving cross-modal retrieval and image captioning.

Foundation models are transforming Earth Observation (EO), yet the diversity of EO sensors and modalities makes a single universal model unrealistic. Multiple specialized EO foundation models (EOFMs) will likely coexist, making efficient knowledge transfer across modalities essential. Most existing EO pretraining relies on masked image modeling, which emphasizes local reconstruction but provides limited control over global semantic structure. To address this, we propose a dual-teacher contrastive distillation framework for multispectral imagery that aligns the student's pretraining objective with the contrastive self-distillation paradigm of modern optical vision foundation models (VFMs). Our approach combines a multispectral teacher with an optical VFM teacher, enabling coherent cross-modal representation learning. Experiments across diverse optical and multispectral benchmarks show that our model adapts to multispectral data without compromising performance on optical-only inputs, achieving state-of-the-art results in both settings, with an average improvement of 3.64 percentage points in semantic segmentation, 1.2 in change detection, and 1.31 in classification tasks. This demonstrates that contrastive distillation provides a principled and efficient approach to scalable representation learning across heterogeneous EO data sources. Project page: \textcolor{magenta}{https://wolfilip.github.io/DEO/}.

The Platonic Representation Hypothesis posits that learned representations from models trained on different modalities converge to a shared latent structure of the world. However, this hypothesis has largely been examined in vision and language, and it remains unclear whether time series participate in such convergence. We first examine this in a trimodal setting and find that independently pretrained time series, vision, and language encoders exhibit near-orthogonal geometry in the absence of explicit coupling. We then apply post-hoc alignment by training projection heads over frozen encoders using contrastive learning, and analyze the resulting representations with respect to geometry, scaling behavior, and dependence on information density and input modality characteristics. Our investigation reveals that overall alignment in contrastive representation spaces improves with model size, but this alignment is asymmetric: time series align more strongly with visual representations than with text, and images can act as effective intermediaries between time series and language. We further see that richer textual descriptions improve alignment only up to a threshold; training on denser captions does not lead to further improvement. Analogous effects are observed for visual representations. Our findings shed light on considerations for building multimodal systems involving non-conventional data modalities beyond vision and language.

Audio-text retrieval is crucial for bridging acoustic signals and natural language. While contrastive dual-encoder architectures like CLAP have shown promise, they are fundamentally limited by the capacity of small-scale encoders. Specifically, the text encoders struggle to understand complex queries that require reasoning or world knowledge. In this paper, we propose AuroLA, a novel contrastive language-audio pre-trained model that re-purposes Multimodal Large Language Models (MLLMs) as a unified backbone for audio-text retrieval. Specifically, we make the following contributions: (i) we construct a scalable data pipeline that curates diverse audio from multiple sources and generates multi-granular captions, ranging from long descriptions to structured tags, via automated annotation; (ii) we adapt an MLLM for retrieval by prompting it to summarise the audio/text input and using the hidden state of a special token as audio/text embeddings. (iii) extensive experiments demonstrate that AuroLA consistently outperforms state-of-the-art dual-encoder models, including the recent PE-AV. This validates the effectiveness of MLLM as a unified backbone for audio-text retrieval.

As models and data scale, independently trained networks often induce analogous notions of similarity. But, matching similarities is weaker than establishing an explicit correspondence between the representation spaces, especially for multimodal models, where consistency must hold not only within each modality, but also for the learned image-text coupling. We therefore ask: given two independently trained multimodal contrastive models (with encoders $(f, g)$ and $(\widetilde{f},\widetilde{g})$) -- trained on different distributions and with different architectures -- does a systematic geometric relationship exist between their embedding spaces? If so, what form does it take, and does it hold uniformly across modalities? In this work, we show that across model families such as CLIP, SigLIP, and FLAVA, this geometric relationship is well approximated by an orthogonal map (up to a global mean shift), i.e., there exists an orthogonal map $Q$ where $Q^\top Q = I$ such that $\widetilde{f}(x)\approx Q f(x)$ for paired images $x$. Strikingly, the same $Q$ simultaneously aligns the text encoders i.e., $\widetilde{g}(y)\approx Q g(y)$ for texts $y$. Theoretically, we prove that if the multimodal kernel agrees across models on a small anchor set i.e. $\langle f(x), g(y)\rangle \approx \langle \widetilde{f}(x), \widetilde{g}(y)\rangle$, then the two models must be related by a single orthogonal map $Q$ and the same $Q$ maps images and text across models. More broadly, this finding enables backward-compatible model upgrades, avoiding costly re-embedding, and has implications for the privacy of learned representations. Our project page: https://canonical-multimodal.github.io/

Predicting survival outcomes for non-small cell lung cancer (NSCLC) patients is challenging due to the different individual prognostic features. This task can benefit from the integration of whole-slide images, bulk transcriptomics, and DNA methylation, which offer complementary views of the patient's condition at diagnosis. However, real-world clinical datasets are often incomplete, with entire modalities missing for a significant fraction of patients. State-of-the-art models rely on available data to create patient-level representations or use generative models to infer missing modalities, but they lack robustness in cases of severe missingness. We propose a Multimodal Contrastive Variational AutoEncoder (MCVAE) to address this issue: modality-specific variational encoders capture the uncertainty in each data source, and a fusion bottleneck with learned gating mechanisms is introduced to normalize the contributions from present modalities. We propose a multi-task objective that combines survival loss and reconstruction loss to regularize patient representations, along with a cross-modal contrastive loss that enforces cross-modal alignment in the latent space. During training, we apply stochastic modality masking to improve the robustness to arbitrary missingness patterns. Extensive evaluations on the TCGA-LUAD (n=475) and TCGA-LUSC (n=446) datasets demonstrate the efficacy of our approach in predicting disease-specific survival (DSS) and its robustness to severe missingness scenarios compared to two state-of-the-art models. Finally, we bring some clarifications on multimodal integration by testing our model on all subsets of modalities, finding that integration is not always beneficial to the task.

Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence. Existing methods often fail under strong detection or continuous fine-tuning, largely due to (1) cross-modal inconsistency that exposes trigger patterns and (2) gradient dilution at low poisoning rates that accelerates backdoor forgetting. These coupled causes remain insufficiently modeled and addressed. We propose BadCLIP++, a unified framework that tackles both challenges. For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions, preserving clean-data statistics while producing compact trigger distributions. We further apply target-aligned subset selection to strengthen signals at low injection rates. For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment, and stabilize model parameters through curvature control and elastic weight consolidation, maintaining solutions within a low-curvature wide basin resistant to fine-tuning. We also provide the first theoretical analysis showing that, within a trust region, gradients from clean fine-tuning and backdoor objectives are co-directional, yielding a non-increasing upper bound on attack success degradation. Experiments demonstrate that with only 0.3% poisoning, BadCLIP++ achieves 99.99% attack success rate (ASR) in digital settings, surpassing baselines by 11.4 points. Across nineteen defenses, ASR remains above 99.90% with less than 0.8% drop in clean accuracy. The method further attains 65.03% success in physical attacks and shows robustness against watermark removal defenses.

Emotional expression underpins natural communication and effective human-computer interaction. We present Emotion Collider (EC-Net), a hyperbolic hypergraph framework for multimodal emotion and sentiment modeling. EC-Net represents modality hierarchies using Poincare-ball embeddings and performs fusion through a hypergraph mechanism that passes messages bidirectionally between nodes and hyperedges. To sharpen class separation, contrastive learning is formulated in hyperbolic space with decoupled radial and angular objectives. High-order semantic relations across time steps and modalities are preserved via adaptive hyperedge construction. Empirical results on standard multimodal emotion benchmarks show that EC-Net produces robust, semantically coherent representations and consistently improves accuracy, particularly when modalities are partially available or contaminated by noise. These findings indicate that explicit hierarchical geometry combined with hypergraph fusion is effective for resilient multimodal affect understanding.

Multimodal learning seeks to integrate information from heterogeneous sources, where signals may be shared across modalities, specific to individual modalities, or emerge only through their interaction. While self-supervised multimodal contrastive learning has achieved remarkable progress, most existing methods predominantly capture redundant cross-modal signals, often neglecting modality-specific (unique) and interaction-driven (synergistic) information. Recent extensions broaden this perspective, yet they either fail to explicitly model synergistic interactions or learn different information components in an entangled manner, leading to incomplete representations and potential information leakage. We introduce COrAL, a principled framework that explicitly and simultaneously preserves redundant, unique, and synergistic information within multimodal representations. COrAL employs a dual-path architecture with orthogonality constraints to disentangle shared and modality-specific features, ensuring a clean separation of information components. To promote synergy modeling, we introduce asymmetric masking with complementary view-specific patterns, compelling the model to infer cross-modal dependencies rather than rely solely on redundant cues. Extensive experiments on synthetic benchmarks and diverse MultiBench datasets demonstrate that COrAL consistently matches or outperforms state-of-the-art methods while exhibiting low performance variance across runs. These results indicate that explicitly modeling the full spectrum of multimodal information yields more stable, reliable, and comprehensive embeddings.

Online handwriting recognition using inertial measurement units opens up handwriting on paper as input for digital devices. Doing it on edge hardware improves privacy and lowers latency, but entails memory constraints. To address this, we propose Error-enhanced Contrastive Handwriting Recognition (ECHWR), a training framework designed to improve feature representation and recognition accuracy without increasing inference costs. ECHWR utilizes a temporary auxiliary branch that aligns sensor signals with semantic text embeddings during the training phase. This alignment is maintained through a dual contrastive objective: an in-batch contrastive loss for general modality alignment and a novel error-based contrastive loss that distinguishes between correct signals and synthetic hard negatives. The auxiliary branch is discarded after training, which allows the deployed model to keep its original, efficient architecture. Evaluations on the OnHW-Words500 dataset show that ECHWR significantly outperforms state-of-the-art baselines, reducing character error rates by up to 7.4% on the writer-independent split and 10.4% on the writer-dependent split. Finally, although our ablation studies indicate that solving specific challenges require specific architectural and objective configurations, error-based contrastive loss shows its effectiveness for handling unseen writing styles.

Tactile feedback is important for contact-rich robotic manipulation, yet effective use of tactile observations remains challenging when tactile signals are image-like, hardware-dependent, and only weakly aligned with external visual observations. This study addresses this representation-learning problem by proposing a visuo-tactile contrastive learning framework for imitation-based manipulation. The method aligns external RGB observations and calibrated tactile images in a shared embedding space using a CLIP-style objective, and integrates the resulting representation into an Action Chunking Transformer (ACT) policy. A low-cost visuo-tactile gripper (LVTG) is proposed to provide a modular and durable sensing platform for reproducible data collection, supplying tactile observations that can be used by downstream manipulation algorithms. Experiments on contact-rich manipulation tasks show that tactile feedback improves the average task completion rate from 30% for a vision-only ACT baseline to 42%, and that the proposed contrastive pretraining further increases the completion rate to 54%. These results indicate that explicitly aligning visual and tactile observations provides more useful contact-aware features for downstream policy learning than directly adding tactile images without pretraining.

While InfoNCE underlies modern contrastive learning, its geometric mechanisms remain under-characterized beyond the canonical alignment--uniformity decomposition. We develop a measure-theoretic framework in which representation measures evolve on a fixed embedding manifold. In the large-batch limit, we prove value and gradient consistency, linking the stochastic objective to explicit deterministic energy landscapes and revealing a geometric bifurcation between unimodal and symmetric multimodal regimes. In the unimodal case, the intrinsic energy is strictly convex and admits a unique Gibbs equilibrium, showing that entropy acts as a tie-breaker within the aligned basin. In the multimodal case, the intrinsic geometry becomes cross-coupled and contains a persistent negative symmetric divergence term: each modality's marginal reshapes the effective landscape of the other, allowing strong pairwise alignment to coexist with a persistent modality gap. Controlled synthetic experiments and analyses of pretrained CLIP representations support these predictions. Overall, our results shift the analytical lens from pointwise discrimination to population geometry, showing that pairwise alignment alone is insufficient to control cross-modal marginal structure.

Contrastive Language-Image Pre-training (CLIP) relies on Vision Transformers whose attention mechanism is susceptible to spurious correlations, and scales quadratically with resolution. To address these limitations, We present CLIMP, the first fully Mamba-based contrastive vision-language model that replaces both the vision and text encoders with Mamba. The new architecture encodes sequential structure in both vision and language, with VMamba capturing visual spatial inductive biases, reducing reliance on spurious correlations and producing an embedding space favorable for cross-modal retrieval and out-of-distribution robustness-surpassing OpenAI's CLIP-ViT-B by 7.5% on ImageNet-O. CLIMP naturally supports variable input resolutions without positional encoding interpolation or specialized training, achieving up to 6.6% higher retrieval accuracy at 16x training resolution while using 5x less memory and 1.8x fewer FLOPs. The autoregressive text encoder further overcomes CLIP's fixed context limitation, enabling dense captioning retrieval. Our findings suggest that Mamba exhibits advantageous properties for vision-language learning, making it a compelling alternative to Transformer-based CLIP.The code and models are publicly available at https://github.com/NimrodShabtay/CLIMP}

Multimodal survival analysis aims to improve cancer prognosis using heterogeneous biomedical data, such as histopathology images and genomic profiles. A common strategy is to align representations across modalities so that shared signals can be captured. However, strong cross-modal alignment can also remove modality-specific evidence that is critical for survival prediction. In this paper, we revisit multimodal survival learning from a simple observation: effective models should first discover shared patterns across modalities, and then preserve modality-specific signals. This motivates a representation learning principle that we refer to as Together Then Apart. Based on this idea, we propose TTA, a framework that balances cross-modal alignment and representation distinctiveness. TTA first performs prototype-based alignment to capture shared survival-related structures between modalities. It then encourages modality-specific distinctiveness through an anchor-guided contrastive objective. To further account for modality imbalance and noisy correspondences, we model cross-modal interactions using unbalanced optimal transport. We evaluate the proposed approach on multiple TCGA cancer cohorts with paired histopathology and genomic data. TTA consistently improves survival prediction over recent multimodal survival models. Moreover, the learned prototype structures reveal interpretable cross-modal patterns associated with clinical outcomes.

Audio-language pretraining (ALP) holds promise for learning general-purpose audio representation, yet remains underexplored. Crucially, there is no consensus on whether audio-language models can build effective general-purpose audio encoders, nor a systematic understanding of how pretraining objectives behave across diverse tasks and scales. We identify three key barriers: limited scale of audio-text corpora, limited coverage of audio attributes in existing caption corpora, and lack of systematic exploration and evaluation. To fill this gap, we present the first principled empirical study of ALP. We first introduce CaptionStew, a 10.7M caption dataset aggregating open-source audio-text corpora across multiple domains and captioning focuses. We then conduct the first comprehensive evaluation comparing contrastive and captioning objectives for learning audio representation across speech, music, and environmental sound tasks. Our results not only demonstrate that ALP yields competitive, transferable representations, but reveal critical trade-offs: contrastive learning offers superior data efficiency, while captioning exhibits better scalability. Furthermore, we find that the benefits of supervised initialization often diminish at larger scales, challenging common practices. By grounding these claims in empirical evidence, we establish a viable pathway toward general-purpose audio representation learning, guiding future research.

Contrastive vision-language models continue to be the dominant approach for image-text retrieval. Contrastive Language-Image Pre-training (CLIP) trains two neural networks to align their image and text embeddings in a shared latent space. As a challenging case-study for neurosymbolic AI, recent results evaluating CLIP on negated or paraphrased text have shown mixed performance as these are difficult to define formally for text data. Negation produces the opposite meaning using various possible but small lexical changes. Paraphrasing may use very different textual expressions to denote essentially the same thing. As a result, learning of paraphrasing and negation together poses a significant challenge because of the above mismatch between changes in syntax and intended meaning expected to be captured by distances in embedding space. This paper proposes a new CLIP contrastive loss function capable of balancing the requirements of having both paraphrasing and negation. It applies training triplets consisting of original, paraphrased and negated text generated by multiple large language models to the evaluation of CLIP models. The approach, called SemCLIP, aims to learn semantically-relevant and simple embeddings, placing paraphrased captions nearer to the original image embeddings while at the same time pushing negated captions farther away. Empirically, SemCLIP is shown to be capable of preserving roughly the same performance as CLIP augmented with either negation or paraphrasing. Although direct comparisons are difficult to make because the problem of learning with both negation and paraphrasing is different, an expected benefit of SemCLIP should be robustness when applied zero-shot to downstream image classification tasks. Our experiments confirm such robustness as measured by difference in accuracy (mean-accuracy delta) between original and negated captions on five downstream datasets.