Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System

While unified multimodal models (UMMs) jointly perform visual understanding and generation within a single model, functional unification does not guarantee learning synergy: the two objectives may reinforce each other, compete for capacity, or merely coexist. We investigate their relationship at the representation, task, and system levels in a controlled, structurally native setting without pretrained vision priors. At the representation level, we find that each objective provides useful signal to the other: generation enriches the visual features learned for understanding, while understanding strengthens vision--language alignment for generation. However, when both objectives are forced through the same computation path, one tends to dominate. A task-decoupled architecture that specializes conflicting visual computation while preserving semantic interaction avoids this asymmetric degradation. At the task level, through three case studies, we find positive bidirectional transfer when understanding and generation tasks rely on shared knowledge. At the system level, we show that an end-to-end UMM outperforms a matched planner--executor pipeline on complex tasks that explicitly require both image understanding and generation. Together, these results show that the value of UMMs extends beyond a unified interface: appropriate specialization, shared task knowledge, and end-to-end optimization can turn coexistence into synergy.

Omni-Interactive Universal Embedder

Multimodal representation learning has been shifting from traditional two-tower architectures to large language model (LLM)-based embedders due to their strong instruction-following capabilities. Despite this progress, existing approaches primarily focus on language and image modalities, which also remain the dominant modalities for user-conditioned interactions in current embedders. In this paper, we propose the first Omni-Interactive Universal Embedder (OmniUE), which not only learns a unified embedding space across text, video, and audio by leveraging intermediate-layer representations from dedicated learnable tokens, but also supports omni-interactive querying, enabling users to provide inputs in the form of text, visual regions of interest, and audio spans. Within OmniUE, visual and audio segmenters process diverse user interactions and integrate them with an omni-LLM to produce user-conditioned any-to-any embeddings via context aggregation. To evaluate OmniUE's omni-interactive capabilities, we introduce OmniCHOIR, benchmarking models for omni-interactive compositional audio retrieval based on the given text, video, and audio as well as unimodal or multimodal interaction prompts. OmniUE consistently surpasses state-of-the-art baselines across diverse modalities, with average improvements of 10.5% on textual-interactive video benchmarks (MMEB-v2-video), 1.1% on audio tasks (MAEB), 83.7% on visual-interactive benchmarks (SCaR), and 24.1% on our omni-interactive OmniCHOIR benchmark. We believe that jointly advancing omni-modal representation learning and omni-interactive querying paves the way toward universal embedders.

Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching

Stochastic masking, cropping, or modality removal makes deterministic reconstruction an incomplete target: one observation can admit many clean completions. This work takes the corresponding posterior $P(X\mid C)$ as the common statistical object for conditional generation and generatively sufficient representation learning. Drift Variation autoencoder trains a masked encoder $Z=E(C)$ and a conditional flow decoder with one clean-prediction Flow Matching loss. The analysis first decomposes the ideal conditional KL into generator approximation and the representation deficiency $I(X;C\mid Z)$. It then derives orthogonal risk decompositions for conditional Flow Matching. For an affine Gaussian path, the clean-prediction representation gap is zero if and only if $P(X\mid Z)=P(X\mid C)$. Thus the encoder-dependent excess clean-prediction risk induced by Flow Matching and the profiled ideal conditional KL have the same posterior-sufficient zero set, without being numerically equal objectives. An exact conditional field with a zero-noise endpoint then generates $P(X\mid Z)$ and hence $P(X\mid C)$ at a joint ideal optimum. The result extends to continuous multimodal product spaces when the complete modality tuple remains the Flow target for every observation mask. On CrossGeom-4, an 18-run controlled benchmark, observable factors have linear-probe $R^2$ of $0.9990$-$0.9992$, shuffling the joint model's encoder condition increases conditional error by $13.5\times$-$15.7\times$, and joint target attention reduces disagreement on an unobserved factor shared by two outputs by $90.1$-$92.8\%$ relative to independent target decoders. Visible modalities are also generated and reconstructed, directly validating the full-tuple objective. Unconditional mode balance remains imperfect, delimiting the empirical claim to a controlled multimodal proof of concept.

Expressivity In Multimodal Contrastive Learning

Contrastive learning has become a cornerstone of modern representation learning, powering CLIP-style models that underpin text-to-image generation, vision-language models, and retrieval across a rapidly growing range of modalities. Despite this empirical success, the expressive power of these architectures remains poorly understood. To gain insight, we study expressivity by adopting a population-level, density-estimation viewpoint: each architecture comprises a parameterized set of densities whose parameters may be chosen to approximate the joint distribution of the modalities. This isolates a question of pure representational capacity: which joint distributions can a given contrastive family of parameterizations approximate to arbitrary accuracy? We show that expressivity is sharply architecture-dependent. For two modalities, the simple two-tower CLIP architecture is a universal approximator. A natural generalization of CLIP, widely used in practice when three or more modalities are present, is based on a loss found by summing over all pairwise similarities. This provably cannot represent arbitrary joint distributions, although we prove that it remains expressive enough to match all pairwise conditionals. Motivated by this gap, we propose Hadamard-CLIP, which adds a single learned weight vector on top of the existing encoders and restores universal approximation of the joint for any number of modalities while preserving CLIP's fast, precomputable-embedding retrieval.

Gloss-Free Representation Learning for Cross-Dataset Sign Spotting

Sign-language research for resource-constrained languages is often limited by the cost of dense linguistic labels such as glosses, temporal boundaries, and sign order. Broadcast news offers a practical alternative by pairing continuous signing with spoken-language transcripts, but this supervision is weak since text and signing are loosely aligned. Morphologically rich languages such as Turkish add further difficulty, as the same lexical meaning can appear in many inflected forms while some derived forms should remain distinct. We study whether weak transcript-based supervision can pretrain a reusable sign encoder in this setting, where poor text normalization can fragment pseudo-gloss targets and weaken representation learning. Unlike prior pseudo-gloss pipelines designed mainly to improve translation, we test whether the pretrained encoder transfers as a reusable representation for cross-dataset sign spotting. We pretrain on TSL-News, a new Turkish broadcast corpus, using pseudo-gloss labels derived from transcripts rather than manual annotation, comparing rule-based morphological lemmatization with constrained LLM-assisted normalization over a fixed vocabulary. We evaluate the learned representations via cross-dataset sign spotting on a new TSL Spotting Benchmark built from the TSL Dictionary corpus. The LLM-assisted encoder raises top-5 temporal localization mean IoU from 0.235 to 0.465, with 56.2% of examples reaching an IoU of at least 0.50; a frequency analysis suggests this gain is not mainly driven by memorizing frequent pseudo-gloss labels. In a downstream translation check, the same pretraining improves BLEU-4 from 9.60 to 11.04 and ROUGE from 23.48 to 27.43. These results show that loosely aligned broadcast data can provide effective weak supervision for learning sign representations that capture both lexical content and temporal structure.

Multimodal Alignment Through Joint Kernel Entropic Gromov--Wasserstein Optimal Transport

We study the problem of aligning data from multiple modalities into a shared representation space, focusing on settings where strong pretrained unimodal encoders are available but cross-modal paired data are scarce. We propose a structure-preserving alignment framework, joint kernel entropic Gromov--Wasserstein Optimal Transport (JK-EGW), which maps multiple modalities into a common latent space by minimizing a quadratic optimal transport objective. JK-EGW leverages fine-grained similarity relationships within and across modalities to construct a global affinity kernel instead of relying on raw feature-space distances. Our framework naturally provides explicit control over the geometry and distribution of the latent embedding. On the theory side, we establish parametric sample complexity rate of $n^{-1/2}$, matching the corresponding rates for standard, entropic and Gromov--Wasserstein optimal transport. On the algorithmic side, we derive a scalable alternating procedure to solve JK-EGW with entropic optimal transport (EOT) updates through a low-rank kernel approximation and a variational lifting. This lifting scheme effectively relieves the burden of a quadratic objective, and allowing us to take the advantage of existing EOT solvers. Empirically, we focus on post-hoc alignment of embeddings from pretrained encoders in data-scarce regimes, and show that our proposed method achieves improved multimodal retrieval performance compared to existing alignment baselines.

Semantically Calibrated Evidence Composition for CT Vision-Language Learning

Learning transferable representations from CT-report pairs requires combining whole-volume context with anatomy-specific evidence. Existing methods typically emphasize either global CT-report alignment or fine-grained anatomy-level correspondence. Global alignment preserves broad study context but leaves the contribution of localized evidence implicit, whereas anatomy-level alignment explicitly grounds local findings but does not specify how independently represented evidence should interact, acquire study-level meaning, and contribute to a global CT representation. To address this gap, we propose SCOPE (Semantic Calibration Of comPosed Evidence), a framework for semantically calibrated evidence composition in CT vision-language learning. Under organ-specific report supervision, mask-guided queries with fixed anatomical identities extract context-aware organ evidence from shared, uncropped volumetric features, while an unrestricted global query retains access to whole-volume context. The global query then drives Local-Global Coupling to compose the organ evidence into a unified evidence representation. The composed evidence is subsequently calibrated using the diagnostic summary, providing study-level semantic supervision beyond local organ descriptions, and is finally integrated as a controlled residual into a context-preserving whole-volume representation aligned with the complete report. This progressive pathway connects localized evidence with study-level semantics without reducing the CT representation to a predefined set of organs. On CT-RATE and RadChestCT, SCOPE achieves macro AUCs of 85.0 and 72.2, respectively, outperforming the previous SOTA by 7.2 and 4.2, while also yielding substantial gains in linear probing and cross-modal retrieval. These results demonstrate the effectiveness of semantically calibrated evidence composition.

KALE: Kernel Alignment with Loss Equilibration for Stable CLIP-DINOv2 Alignment at Web Scale

Kernel-based alignment of CLIP toward a vision centric teacher such as DINOv2 (KUEA) improves CLIP's visual representations while preserving text-encoder compatibility, using a fixed trade-off weight tuned on curated ImageNet-1K. We ask whether this transfers to noisy, web-scale data (CC12M) and find that it does not: the alignment term's weighted contribution falls to about 0.2% of the clean term, so under any fixed weight its gradient is effectively inert. We introduce KALE, a loss-equilibration controller that tracks both losses and adaptively rescales the alignment weight toward a target ratio, restoring the signal with no per-dataset tuning; reaching balance requires increasing the weight by roughly four orders of magnitude, and the required value is configuration-dependent, so no fixed scalar suffices. We characterize the resulting regime: a bounded high learning rate and a decaying schedule with a moderate floor are needed for stability, and the controller equilibrates rather than diverging. On a 3.3M-image CC12M subset, the aligned model preserves image-text retrieval and reproducibly improves SVHN linear probing; zero-shot improves by +2.00 over CLIP on the standard 11-dataset average, exceeding KUEA's +1.29. We report all results with explicit run-to-run variance and base our conclusions on the metrics that are stable across runs.

Learning to Detect Cross-Modal Negation: An Analysis of Latent Representations and an Attention-Based Solution

Detecting high-level semantic concepts like negation across modalities remains a challenge for current multimodal systems. We analyze this as a fundamental representation learning problem, providing the first evidence that negation does not form a linearly or non-linearly separable class in the latent spaces of standard vision-language models (VLMs). We demonstrate that pretrained embeddings primarily encode modality-specific features, lacking a generalizable negation signal. To overcome this, we propose a novel cross-modal attention architecture that explicitly models inter-modal dependencies, achieving performance gains of up to +7.03% F1 over unimodal baselines. Our analysis reveals a key asymmetry: while textual negation often appears independently, visual negation is semantically dependent on linguistic context, a finding validated through our statistical analysis of 3,222 political video-text pairs automatically annotated via \textsc{Qwen2.5-VL}. By combining this analysis with self-supervised video representations (JEPA2), we advance the modeling of temporal negation. This work provides new methods and insights for learning robust, semantically-aligned representations in multimodal systems.

Beyond Objective Expressivity: Geometry Preservation in Multimodal Contrastive Learning

Contrastive learning is increasingly moving toward settings with three or more modalities instead of image-text pairs. Yet, extending models from pairwise to higher-order multimodal alignment can introduce optimization and representation challenges. We identify encoder Jacobian conditioning as a key factor in trimodal contrastive learning: poorly conditioned encoders exhibit collapsing or amplified singular-value spectra, leading to exploding Jacobian condition numbers and degraded multimodal alignment. We introduce geometry-preserving encoders (GPEs) by directly conditioning the Jacobian through regularization and demonstrating that simple modifications like LeakyReLU activations and residual paths recover these geometric benefits. Across a synthetic benchmark and four real-world datasets including missing modalities, improving Jacobian conditioning boosts retrieval and linear probe performance across multiple contrastive objectives, whereas expressive objectives yield little benefit in linear probes. More broadly, our results show that multimodal contrastive learning depends not only on objective expressivity, but also on the geometric and optimization properties of the underlying encoders.

MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning

Real-world perception and decision making are inherently multimodal, integrating complementary signals across modalities. However, training multimodal models faces two main obstacles. First, collecting large-scale, well-aligned paired multimodal datasets is often impractical, making end-to-end multimodal training difficult. Second, existing multimodal representations frequently entangle information shared across modalities with modality-specific information, hindering interpretability and control. We introduce MultiLoReFT, an efficient and scalable low-rank representation fine-tuning framework for multimodal learning with pretrained unimodal models. MultiLoReFT extends low-rank adaptation to the multimodal setting and learns interpretable projection subspaces that decouple shared and modality-specific information. Across simulated and real-world benchmarks, it produces representations that support multimodal prediction while explicitly revealing how shared and modality-specific information is distributed across modalities.

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.

AspectCLIP: Optimizing CLIP Representation Space via Aspect-Guided Consistency Regularization

Contrastive Language-Image Pretraining learns a shared representation space through large-scale contrastive learning. However, existing methods that enforce global consistency regularization overlook a key challenge: the inherent information asymmetry between images and text: captions typically describe only one specific aspect of an image, thus images with similar visual content can be paired with completely divergent textual content and semantic information. Consequently, global regularizers inadvertently impose constraints between visually similar images whose captions describe divergent aspects, introducing semantic distortion into the representation space. We propose AspectCLIP, a framework that reformulates consistency regularization to respect this one-to-many structure. AspectCLIP first partitions training samples into attribute clusters based on textual similarity to identify aspect-coherent groups, then applies full cyclic consistency within each cluster while restricting cross-cluster regularization to prototype-level comparisons. This aspect-guided regularization enforces strict geometric alignment only when images and texts describe a consistent facet, while allowing flexibility across divergent aspects. Extensive experiments on downstream tasks demonstrate that AspectCLIP consistently outperforms traditional methods and achieves a more structured representation space.

Gen4U: Unifying Video Generation and Understanding via Diffusion

Prior work suggests that diffusion representations capture low-level geometry but struggle with high-level semantics. We demonstrate that state-of-the-art video diffusion models overcome this limitation. By systematically probing their intermediate activations using recent mutual-kNN alignment metrics, we reveal a highly structured latent space where visual representations evolve across both network depth and noise levels. We show that while moderate noise levels yield linearly separable global semantics, fine-grained details persist at lower noise levels but become spatially scattered, requiring attention mechanisms to decode. Building on these insights, we introduce Gen4U (Generation for Understanding), a framework that repurposes these generative representations with a single forward pass. Our experiments establish that frozen, large-scale video diffusion models function as highly competitive video encoders across a wide spectrum of tasks, spanning semantic and non-semantic objectives (video classification, depth estimation, camera pose estimation, image and video captioning). Bypassing fine-tuning, Gen4U unifies the generation and understanding paradigms, achieving strong perception performance while fully preserving the model's ability to generate high-quality video.

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.

Information-Regularized Attention for Visual-Centric Reasoning

Vision-language models (VLMs) have become a paradigm for multimodal learning, yet remain unstable due to object hallucination, weak visual grounding, and catastrophic forgetting after full-parameter instruction tuning. We claim these failures result from a lack of explicit control over visual representation learning during the standard next-token prediction objective. As a result, visual embeddings thus become passively optimized and prone to injecting redundant or spurious signals. To counter this, we introduce Information-Regularized Attention (IRA), a stochastic attention mechanism that explicitly regulates the amount of visual information injected into the hidden states of intermediate transformer layers. This local reparameterization translates uncertainty about visual representations into local noise that is independent across data points. Beyond evaluating model performance, we also quantify embedding properties, where IRA produces smoother curvature trajectories and suppresses attention-sink across all layers, indicating a more stable transformation of the visual signal. Our results suggest that stochastic attention is not merely a regularizer but a key contributor to representation learning in a generative architecture, offering a new direction for building more reliable VLMs.

Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation

Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs that can efficiently train contrastive vision-language models under strict data and compute budgets. Most existing methods match expert trajectories or cross-modal statistics, yet still enforce full-dimensional alignment in a Euclidean embedding space. This is often overly restrictive due to rank-deficient image--text correlation, with shared semantics concentrated in a low-dimensional range and remaining variation spread across a weakly correlated residual subspace. LoRS relaxes alignment at the similarity level by low-rank factorization, but does not explicitly control dominant alignment capacity and structure in the representation space. We thus propose a rank-aware hyperbolic alignment (RAHA) that combines hierarchical geometry with explicit alignment-capacity control. RAHA lifts multimodal representations to hyperbolic space and optimizes distilled pairs with asymmetric objectives that enforce geodesic alignment in the shared range while regularizing the residual subspace to preserve modality-private diversity and improve transfer robustness. Experiments on benchmarks show that RAHA demonstrates competitive cross-modal retrieval and improved transfer indicators under fixed budgets.

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.

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.

DiT-Reward: Generative Representations for Text-to-Image Reward Modeling

Can representations learned for image generation also support the evaluation of generated images? We study text-to-image reward prediction as a downstream task of generative representation learning. To this end, we introduce DiT-Reward, which converts a pretrained text-to-image Diffusion Transformer into a reward model by processing near-clean image latents and aggregating text-conditioned image representations across transformer layers. Under the same training data mixture as HPSv3, DiT-Reward outperforms HPSv3 on all four evaluated preference benchmarks, reaching 85.6% on HPDv2 and 77.6% on HPDv3. When the generative backbone is frozen, a lightweight learned head can still extract meaningful preference predictions from its representations. Probing across depth further reveals that downstream reward performance is strongest in the middle-to-late layers and benefits from combining representations across different stages. We also observe consistent positive scaling with generative backbone capacity. Finally, when used to optimize Stable Diffusion 3.5 Large with Flow-GRPO, DiT-Reward outperforms HPSv3 along the matched training trajectory, with particularly clear gains in realism. Direct latent scoring also achieves a 1.65x inference speedup over HPSv3 with comparable peak memory. These results show that pretrained generative DiTs provide transferable representations for reward modeling and policy optimization.

Data-Driven Decoding of Russell's Circumplex Model of Affect

Affective computing increasingly relies on deep learning to represent emotions, yet latent spaces often remain opaque, high-dimensional black boxes. This paper investigates whether Transformers' embeddings recover the geometric regularities of Russell's circumplex model. We unify two complementary experiments testing the hypothesis that, after training models on text and speech, their resulting latent spaces encode a topology consistent with valence-arousal and reproduce human-like neighborhood relations. Specifically, we evaluate deep representations extracted from Transformer-based text (RoBERTa) and speech (wav2vec 2.0) encoders, along with a multimodal Transformer fusion architecture, across naturalistic datasets like MSP-Podcast and controlled LLM-generated stimuli. Our analysis reveals that multimodal fusion of text and audio yields perfect topological alignment with Russell's primary emotion ordering. Furthermore, in a zero-shot setting using generic text embeddings, projected fine-grained emotion terms fall close to their established human-mapped coordinates. Our contribution is a novel, data-driven framework for validating emotion models, demonstrating that Russell's circumplex structure is intrinsically encoded in the embeddings of these modalities rather than being solely an artifact of human labeling, thereby bridging the gap between psychological theory and representation learning.

Hölder++: Improving the Quality-Coherence Trade-off in Multimodal VAEs

Existing approaches for multimodal variational autoencoders (VAEs) face a trade-off between generative quality and coherence-i.e., they struggle to generate realistic and diverse samples that, at the same time, are semantically consistent across modalities. A recent work shows that using a simple approximation to Hölder pooling as an aggregation method improves coherence over the SOTA MMVAE+, despite assuming a single shared representation across all modalities. Yet, it slightly compromises sample diversity. Inspired by this insight, we propose Hölder++, a novel multimodal VAE that improves the generative quality-coherence trade-off through: (i) the first implementation of Hölder pooling without any approximation for multimodal VAEs; (ii) an extended architecture that models distinct shared and private (i.e., modality-specific) representations (Hölder+); and (iii) hierarchical inference that further enhances the disentanglement between the shared and private representations (Hölder++). Our experiments corroborate that Hölder++ consistently improves the generative quality-coherence trade-off, yields more structured latent spaces, and learns shared representations that are informative for downstream tasks.

Tac-DINO: Learning Vision-Tactile Features with Patch Alignment

Touch is the primary medium through which humans interact with the environment. Currently, tactile learning mainly focuses on image-level pretraining or alignment. However, tactile signals correspond to local object contact, while research into scale alignment and holographic matching remains limited and proper datasets and benchmarks also lack. To bridge this gap, we first construct a data collection system to acquire a large-scale tactile dataset, with over 20 K tactile contacts from 505 real-world objects. Building on this dataset, we design a Vis-Tac Holographic Matching Benchmark to evaluate vision-tactile local-to-global alignment ability. Then we propose Vision-Tactile Patch Alignment (VTPA) methods for vision-tactile representation learning. Experiments demonstrate that these exceed the performance of methods without alignment and align with whole-object images.

Frozen Multimodal Embeddings for Personality and Cognitive Ability Assessment in Asynchronous Video Interviews

Predicting psychological traits from asynchronous video interviews (AVIs) is a challenging multimodal learning problem because labeled datasets are limited while each response contains high-dimensional visual, acoustic, and verbal signals. This paper presents our solution for the ACM Multimedia AVI Challenge 2026, which evaluates two tasks: Track~1 predicts self-reported HEXACO personality traits from personality-related interview responses, and Track~2 classifies cognitive ability levels from structured AVI responses. We treat the problem as a small-sample representation learning task. Instead of fine-tuning large pretrained models, we use frozen multimodal encoders, including CLIP for visual features, Whisper for acoustic features and transcripts, and RoBERTa, E5, and DeBERTaV3 for textual representations, followed by low-capacity downstream models. For Track~1, our trait-specific regression and late-fusion system achieves an average validation MSE of 0.2696, improving over the official baseline of 0.3334. Ablation results show a three-step improvement from a global model (0.3189), to per-trait modeling (0.2871), to per-trait late fusion (0.2696), corresponding to a 19.1\% relative MSE reduction over the official baseline. For Track~2, a compact subject-attribute baseline reaches 0.5781 accuracy, while our multimodal ensemble reaches 0.5313, both above the official baseline of 0.4062. We interpret this result as evidence of possible subject-attribute shortcuts in the validation split rather than robust cognitive inference from AVI content. Overall, our findings suggest that AVI-based psychological assessment benefits from trait-specific multimodal modeling, but cognitive ability prediction requires careful control of dataset shortcuts.

When to Align, When to Predict: A Phase Diagram for Multimodal Learning

Cross-modal alignment (CA) and cross-modal prediction (CP) are the dominant paradigms for multimodal representation learning, yet there is no systematic understanding of when each succeeds, when each fails, and when cross-modal training helps at all -- a gap that leaves practitioners, especially in scientific domains like biomedicine or astrophysics, with heterogeneous instruments and multiple levels of organization and measurement, unable to diagnose why standard methods underperform the best single modality. We develop a unified linear framework that addresses both questions. Under a spiked signal-plus-noise model with structured cross-modal nuisance correlation, we derive separation ratios for both objectives that expose complementary failure modes: alignment whitens each modality and fails when nuisance is strongly correlated across views; prediction encodes whatever is cross-predictable through a one-sided whitening, with recovery governed by source-modality quality. The resulting phase diagram partitions multimodal problems into four regimes: Both, CA only, CP only, and Neither. We present a data-driven procedure to locate real-world datasets in this diagram using a small labeled subsample, identifying the preferred objective and prediction direction before any cross-modal training. Experiments on synthetic data, stereo-vision benchmarks, image-caption pairs, and real astrophysical data validate the predictions in the nonlinear regime, including the Neither regime where cross-modal training is actively harmful. Our framework lets practitioners diagnose their multimodal problem and choose the right objective before committing to training. Code to reproduce the results is available at https://github.com/IlayMalinyak/mm_align_vs_pred.

KODA: Contrastive Representation Comparison and Alignment for Vision-Language Foundation Models

Vision-language foundation models such as CLIP and SigLIP provide widely used representations for multimodal learning systems. While these models are typically compared through downstream performance, such evaluations often do not explain how their representations differ structurally. In this work, we study this problem through the task of Contrastive Embedding Clustering: identifying sample subsets that are weakly clustered under one representation but strongly clustered under another. We propose \emph{Kernel Optimization for Discrepancy Analysis (KODA)}, a kernel-based framework for contrastive representation comparison and alignment. KODA constructs unified multimodal kernels through modality-wise kernel composition and formulates discrepancy discovery as a constrained optimization problem that searches for coherent structures in one representation while suppressing coherence in a reference representation. This yields interpretable discrepancy directions associated with specific sample subsets and modality interactions. To scale KODA to large vision-language datasets, we develop randomized low-dimensional approximations of joint kernels using random projections, including Random Fourier Features for shift-invariant kernels. Empirically, KODA identifies consistent and interpretable discrepancy structures across vision-language representations and provides sample subsets for representation alignment. The code is available at https://github.com/yokiwuuu/KODA.

TextTeacher: What Can Language Teach About Images?

The platonic representation hypothesis suggests that sufficiently large models converge to a shared representation geometry, even across modalities. Motivated by this, we ask: Can the semantic knowledge of a language model efficiently improve a vision model? As an answer, we introduce TextTeacher, a simple auxiliary objective that injects text embeddings as additional information into image classification training. TextTeacher uses readily available image captions, a pre-trained and frozen text encoder, and a lightweight projection to produce semantic anchors that efficiently guide representations during training while leaving the inference-time model unchanged. On ImageNet with standard ViT backbones, TextTeacher improves accuracy by up to +2.7 percentage points (p.p.) and yields consistent transfer gains (on average +1.0 p.p.) under the same recipe and compute. It outperforms vision knowledge distillation, yielding more accuracy at a constant compute budget or similar accuracy, but 33% faster. Our analysis indicates that TextTeacher acts as a feature-space preconditioner, shaping deeper layers in the first stages of training, and aiding generalization by supplying complementary semantic cues. TextTeacher adds negligible overhead, requires no costly multimodal training of the target model and preserves the simplicity and latency of pure vision models. Project page with code and captions: https://nauen-it.de/publications/text-teacher

Multimodal LLMs under Pairwise Modalities

Despite the impressive results achieved by multimodal large language models (MLLMs), their training typically relies on jointly curated multimodal data, requiring substantial human effort to construct multi-way aligned datasets and thereby limiting scalability across domains. In this work, we explore training MLLMs by only leveraging multiple paired modalities as a surrogate for the full joint multimodal distribution. Specifically, we first provide a theoretical analysis of the conditions under which the representations are identifiable with only observing pairwise modalities. Building on this analysis, we propose a representation learning framework for aligning latent representations across modalities using only pairwise data. The framework consists of two stages: latent representation alignment and cross-modal recomposition. Specifically, in the first stage, we learn the shared latent space across modalities by both self-modal reconstruction and pair-wise contrastive learning. We also incorporate an inductive bias in the contrastive learning process by partially aligning and minimal latent specification. In stage two, we integrate the encoder of newly introduced modalities with the decoders of the pre-trained modalities to facilitate cross-modal transfer and generation. We evaluate our method by newly adding 3D point clouds and tactile modalities into pre-trained MLLMs with three modality pairs and show that, by learning an aligned latent representation space, our model achieves strong cross-modal performance.