Seeing frames in order does not mean representing time. Modern VideoLMs receive ordered video streams, yet their main supervision acts on generated text rather than video-token representations where event dynamics should first emerge. This mismatch allows models to learn temporal answers from shortcuts such as objects, scenes, and language priors, without requiring internal video representations to capture event progression. To address this, we propose VT-Contrast, a representation-level temporal counterfactual objective for VideoLMs. Its design asks where temporal supervision should act and what temporal differences it should expose. VT-Contrast supervises selected late-layer last-frame video tokens, where temporal information is expected to be integrated before language generation, and contrasts order-preserving views with same-video reordered counterfactuals graded by Kendall tau distance. It requires no architectural changes, is compatible with diverse VideoLM training tasks, and improves overall performance across temporal understanding benchmarks. Our code is available at https://github.com/ANDgate99/VT-Contrast.
Contrastive language-image learning (CLIP) has become a key paradigm for remote sensing vision-language understanding. However, existing remote sensing contrastive learning methods are mostly built on RGB-oriented CLIP architectures, making it difficult to exploit heterogeneous sensors such as SAR, multi-spectral imaging (MSI), and hyperspectral imaging (HSI). To address this limitation, we propose OmniRSCLIP, an end-to-end contrastive learning framework that supports multi-source sensor inputs for remote sensing vision-language modeling. The key idea is to extend CLIP beyond its fixed RGB input interface without breaking the pretrained visual knowledge. To this end, OmniRSCLIP introduces Spectral-Spatial Basis Decomposition (SSBD), which formulates arbitrary-channel adaptation as a basis recomposition problem: pretrained CLIP patch embeddings provide transferable spatial bases, while wavelength-conditioned coefficients span sensor-specific embedding kernels within a constrained visual prior space. This design avoids forcing heterogeneous sensors into a fixed-channel input space, while aligning them in a unified image-text semantic space. We further introduce a spectral-context-aware mask-based contrastive learning scheme to suppress modality-specific redundant features and enhance fine-grained image-text alignment. Finally, to support multi-modal training, we construct OmniRS5M, the first large-scale remote sensing image-text corpus covering RGB, SAR, MSI, and HSI. Experiments on retrieval, zero-shot classification, and semantic localization show that OmniRSCLIP preserves strong RGB-domain performance while effectively extending CLIP to heterogeneous remote sensing modalities.
Using a zoom-in tool is an important foundational part of modern visual agents, because it allows to efficiently handle tasks involving high-resolution images. Most previous methods need an extensive warm-start supervised fine-tuning phase for teaching models zoom-in. We show that this is not necessary by proposing a new intrinsic reward for learning tool use in MLLMs without the need for additional labels or warm-start SFT. Our InfoNCE-style reward uses a curriculum of increasingly hard negative tool calls as a contrastive training signal. Empirical experiments on $V^*$, HRBench and MME-RealWorld show that our approach is competitive while being more efficient. When used as a drop-in replacement for SFT, we even outperform all baselines. To directly measure the zoom-in ability of models, we further introduce the scalable synthetic Muffin&Chihuahua (M&C) dataset. Each image consists of a grid with every cell either showing a muffin or chihuahua. Leveraging the M&C dataset's unique region of interest labels, we find that recall is the metric that most strongly correlates the zoom-in region with final task performance. Our model and code for reproduction is publicly available under https://github.com/UKPLab/emnlp2026-zoom-in
Text-rich visual inputs require models that can read, retrieve, and compress language directly in pixel space, yet existing pixel-text encoders struggle with fixed resolution pretraining, visual shortcut learning, weak visual grounding, and multilingual visual text understanding. In this work, we investigate the fundamental design principles required for robust visual text representation learning. Through systematic controlled ablations, we identify four critical components: variable image resolutions and rendered font sizes provide spatial proxies for high-resolution document generalization; natural image-text pairs are indispensable for grounding and prevent text-only collapse; layout-aware rendering helps prevent pixel-level shortcuts; and a two-stage multilingual curriculum enables effective cross-lingual alignment. By integrating these principles into a scalable training recipe, we train Pixel Linguist II, a native-resolution vision encoder trained with on-the-fly rendering, unified contrastive grounding, and a multilingual curriculum over 280M training examples. Pixel Linguist II sets new state-of-the-art results on English, cross-lingual, and multilingual Visual STS and ViDoRe, while also enabling better MLLM downstream evaluation. Notably, Pixel Linguist II remains robust under 80\% visual token compression, showing great promise for optical context compression. Our code and resources are available at https://github.com/Pixel-Linguist/Pixel-Linguist-II.
An image may be worth a thousand words, but most captioning models describe it in only a few. Modern vision-language models produce fluent high-level captions, yet routinely miss the attributes, counts, textures, materials, and spatial relations that make an image visually specific. Recent multi-stage systems recover some of these details through generation, decomposition, verification, and rewriting, but they do so at the expense of substantially higher inference latency. We propose SimLoss, a reference-free embedding-space objective for single-pass fine-grained image captioning. SimLoss trains a vision-language model to align its projected hidden-state representation with a frozen image embedding through an InfoNCE contrastive loss, supplying a dense visual supervision signal before any text is decoded, and requiring neither human-written fine-grained captions nor pseudo-captions from a multi-stage pipeline. We instantiate it as SimLoss FFT, which backpropagates through a locally available embedding model, and SimLoss GRPO, which treats that model as a black-box reward. Compared with single-pass, multi-stage verification, reward-optimized, and perception-aware baselines, the fully differentiable fine-tuning variant, SimLoss FFT, achieves the highest precision while nearly matching the F1 score of the multi-stage method, all while retaining single-pass inference and running roughly 20 times faster than the multi-stage pipeline. The reward-based variant SimLoss GRPO attains the strongest recall. Together, these results show that embedding-space supervision can recover the quality of multi-stage verification at the latency of a single-pass captioner.
Multimodal Sentiment Analysis (MSA) is a fundamental component of affective computing that aims to decipher complex emotional states by integrating verbal content with non-verbal cues including vocal intonation and facial micro-expressions. While recent disentanglement-based approaches have advanced the field, their potential is hindered by two methodological challenges. First, static computation graphs process all samples indiscriminately regardless of semantic complexity, which leads to suboptimal representation for diverse emotional expressions and contextual scenarios. Second, generic contrastive objectives often neglect the intrinsic ordinal hierarchy of sentiment intensities. To systematically address these limitations, we introduce Multimodal Adaptive Expert Selection with Text Routing and Ordinal prototype optimization (MAESTRO), a novel framework designed to dynamically orchestrate and refine multimodal representations. Drawing inspiration from an orchestra conductor, we design a Text-Guided Hybrid Mixture-of-Experts (MoE) mechanism. Unlike static fusion, this module utilizes linguistic context as a routing signal to dynamically activate specific audio-visual experts, thereby resolving cross-modal ambiguity through adaptive feature enhancement. Furthermore, to capture fine-grained sentiment gradations, we propose an Ordinal-aware Prototype Contrastive Learning (O-PCL). By incorporating distance-based penalties into the prototype learning objective, O-PCL enforces a structured latent space that preserves the natural order of emotion. Extensive experiments on the CMU-MOSI and CMU-MOSEI benchmarks demonstrate that MAESTRO achieves state-of-the-art performance, and qualitative analysis further confirms the interpretability of our dynamic routing paradigm.
Vision-language retrieval with CLIP-style dual encoders achieves strong cross-modal performance, yet practical accuracy often hinges on localized semantic distinctions where top-ranked near misses differ from the true match by a single critical detail. Hard-sample mining can select confusable candidates but cannot construct corrected counterparts; synthetic augmentation can generate novel samples but, without conditioning on actual model failures, targets irrelevant dimensions of hardness. We observe that a top-ranked false positive is a counterfactual scaffold---sharing most of the query's semantics while differing in a localized failure-causing residual. Minimally correcting this residual yields a hard positive of the ground truth in the same modality; the corrected and unedited versions form a hard negative pair that straddles the decision boundary, producing complementary pull--push supervision. We introduce RePair, guided by three principles---Validity, Minimality, and Locality---which mines false positives bidirectionally, applies LLM-guided counterfactual editing, and trains with a local hard-pair contrastive objective. On Flickr30K and COCO30K, RePair outperforms controlled augmentation baselines with only 107K synthetic samples---26\%--75\% fewer than comparable methods---confirming failure-conditioned repair is more data-efficient than error-agnostic augmentation.
Matin Mahmood, Antonio Rueda-Toicen, Mohamed ElBassat +3cs.CV cs.AI
CLIP-like vision-language models (VLMs) trained with contrastive objectives learn strong global image-text representations, but their Euclidean embeddings and global pooling fail to encode relational structure such as part-whole and parent-child relations. Hyperbolic VLMs address this gap with entailment-based objectives, and text-conditioned variants improve fine-grained alignment through sentence- and phrase-level queries. However, these two lines of work remain separate: hyperbolic VLMs use static image and region features, while query-conditioned methods lack hierarchical geometric structure. We present Hyper3-CLIP, a hierarchy-conditioned hyperbolic VLM that combines global, local, and global-local contrastive learning with query-conditioned visual pooling. To train the model, we construct lightweight query hierarchies from text, comprising full captions, sentence fragments, localized part descriptions, and extracted phrases. Each query conditions the pooling of visual patches, and the resulting representations support image-text, whole-part, and parent-child entailment losses. Query-conditioned pooling is active only during training. Hyper3-CLIP improves R@5 and R@10 retrieval on COCO and Flickr, as well as multi-label classification on VOC and COCO, while remaining competitive on hierarchy metrics. We also audit zero-shot prompt sensitivity under fixed prompt regimes and study the effect of the localized GRIT part budget used during training. Code is available at https://github.com/Hyper3Labs/hyper3-clip.
Unmanned aerial vehicle (UAV) multimodal perception integrates visible (RGB), infrared (IR), synthetic aperture radar (SAR), and depth sensors for scene understanding under diverse conditions. However, differences in optics, resolution, and mounting often limit practical systems to global or image-center alignment. After tokenization, parallax, platform motion, and lens distortion can shift corresponding patch centers across modalities, weakening the spatial correspondence assumed by dense contrastive learning and cross-modal fusion. We propose GAAT (Geometry-Aware Alignment Transformer), an alignment-first pretrained model that estimates local correspondence reliability before cross-modal interaction. GAAT introduces syncPATC, which learns patch-center consistency under synchronized view transformations without correspondence annotations. It emits geometric priors, including token and query confidence, query centers, and sub-token offsets, that identify reliable local anchors across residual misalignment. Guided by these priors, MG-Sparse-MMA performs query-mediated sparse fusion over top-K_s reliable regions, replacing dense all-patch interaction with geometry-calibrated local updates. RA-QCGCL aligns pretraining supervision with this sparse query bottleneck through reliable patch-to-patch, patch-to-query, and query-to-query contrastive branches. We introduce UAVMeta and StateBench, which provide four acquisition-state scores derived from platform telemetry and image statistics: camera reliability, observation scale, viewpoint stability, and flight maneuver complexity. Extensive experiments across six downstream tasks demonstrate consistently superior transfer performance, establishing GAAT as a state-of-the-art multimodal foundation model for UAV perception. StateBench further enables a systematic diagnosis of real-world acquisition conditions.
Multi-vector representations have emerged as an effective paradigm for multimodal retrieval, representing each sample with multiple complementary embeddings to capture fine-grained cross-modal information. However, existing approaches typically employ a fixed representation capacity, assigning the same number of vectors to all samples regardless of their individual retrieval demands. Such a fixed-capacity formulation overlooks the fact that different samples may require different amounts of representation capacity for effective retrieval. In this work, we introduce \emph{Sample-Adaptive Multi-Vector Representation} (SAMVR), a new problem setting for multimodal retrieval that studies how multi-vector representation capacity can be allocated at the sample level. Under SAMVR, each sample is represented by a \emph{content-adaptive embedding set} (CAES), whose capacity is determined according to the sample-specific retrieval utility of additional representation vectors. To instantiate SAMVR, we propose \emph{AdaptiveEmbed}, a unified framework for learning sample-adaptive multi-vector representations. AdaptiveEmbed learns structured multi-vector representations through \emph{Multi-Group Contrastive Learning} (MGCL) with the symmetric \emph{set-to-set similarity} (SetSim), and further employs \emph{Utility Policy Optimization} (UPO) to determine sample-specific representation capacity via \emph{Marginal Utility Allocation} (MUA). Experiments across multimodal retrieval benchmarks involving image, text, video, and audio show that sample-adaptive capacity allocation achieves overall better retrieval performance than fixed-capacity multi-vector representations, validating the effectiveness of SAMVR for multimodal retrieval. These results establish SAMVR as a viable formulation for adaptive capacity allocation in multi-vector multimodal retrieval.
Although recent Multimodal Large Language Models (MLLMs) have advanced general product understanding, they implicitly encode product information into global embeddings, thereby limiting their ability to capture fine-grained attributes. This limitation hinders performance in tasks requiring precise attribute discrimination, such as distinguishing subtle material differences among visually similar products. To address this challenge, we propose HMGCLIP, a unified multimodal embedding framework. By constructing a heterogeneous hypergraph, we leverage hypergraph topology to mine structure-aware hard negatives and align multi-granular semantics at both relation and hyperedge levels. This design enables a dual-granularity inference mechanism that dynamically fuses attribute evidence for both fine-grained and coarse-grained downstream tasks. Furthermore, we release a comprehensive fine-grained e-commerce dataset to facilitate future benchmarking. Extensive experiments on this new dataset and the public MAVE benchmark show that HMGCLIP outperforms strong multimodal encoders, MLLMs, and e-commerce baselines, validating the superiority of HMGCLIP.
Chenghua Zhu, Zhaolu Kang, Qifan Shi +8cs.CV cs.CL cs.LG
Video multimodal large language models have advanced significantly, yet fine-grained motion-temporal understanding remains fragile. The core bottleneck is not only sparse frame sampling, but also the lack of a complete temporal modeling pipeline for explicitly representing frame-to-frame change, enabling appearance-motion interaction, and optimizing temporal direction sensitivity. We propose COMET, a temporally grounded framework that systematically strengthens video MLLMs through explicit temporal representation, appearance-motion fusion, and direction-aware optimization. Architecturally, COMET introduces a temporal motion branch built on Taylor frame differences and injects its motion evidence into the appearance stream via temporal attention bias-enhanced cross-attention. For optimization, COMET combines temporal prior distillation with a forward-reverse TC-GRPO stage that turns temporal order into a direct learning signal and strengthens the model's use of directional motion patterns encoded by the temporal motion branch. The method achieves consistent overall improvements with a pronounced motion-temporal bias: on Qwen3-VL-8B, action-centric tasks (STAR, SSv2) improve by 4.9% on average, temporal reasoning tasks (NExT-QA, CLEVRER, LLaVA-178K) by 2.1% over BL-GRPO, while static perception tasks (PerceptionTest) remain on par. The same gain pattern also transfers to InternVL2.5-8B, indicating that COMET generalizes across model families.
Incomplete multimodal sentiment analysis has garnered significant attention in recent years. Existing approaches typically assume that data is missing at random or are designed specifically for certain missing patterns, ignoring the modality combination inconsistency between training and testing phases. However, in real-world scenarios, the testing phase often encounters modal combinations that were not present during the training phase, which leads to insufficient generalization capabilities and unstable performance. In this paper, we introduce the problem of Incomplete Multimodal Sentiment Analysis with Unseen Modality Combinations (IMSAUMC), aiming to enhance model generalization for unseen modality combinations. To address this challenge, we propose the model named $\textbf{C}$ontrastive $\textbf{M}$ixed $\textbf{P}$rompt $\textbf{L}$earning ($\textsf{CMPL}$) for IMSAUMC. It introduces a label-guided contrastive feature learning mechanism to learn robust and discriminative cross-modal representations. Additionally, we design modality-combination prompts with a soft router to facilitate better learning of various modality combinations. Furthermore, we introduce three prompt contrastive learning strategies, which enable effective learning of prompts corresponding to unseen modality combinations, thereby significantly strengthening the model's generalization capabilities in diverse testing scenarios. Extensive experiments on three widely used datasets demonstrate that $\textsf{CMPL}$ achieves more than a 5% improvement in accuracy compared to state-of-the-art approaches.
Multimodal sarcasm detection aims to identify sarcastic intent from multimodal content, where inconsistencies between literal meaning and contextual cues often signal irony. This task has attracted increasing research attention. However, accurate detection remains challenging due to instance-dependent modality contributions and misleading semantic consistency, where surface-level alignment masks underlying contradictory intent. Existing methods often rely on fixed fusion strategies and treat sarcasm as generic cross-modal mismatch, limiting their ability to capture subtle sarcasm cues and instance-specific modality interactions. To address these challenges, we propose a novel MSD framework that integrates Dynamic Gated Cross-Modal Fusion with Sarcastic-aware Contrastive Regularization (SaCR). Specifically, a bidirectional gated interaction module performs cross-modal feature filtering and adaptively calibrates textual and visual contributions at the instance level. A dynamic fusion gate further balances modality importance to generate more robust multimodal representations. Furthermore, SaCR is introduced as a label-aware contrastive regularization objective that encourages semantic consistency for non-sarcastic samples while suppressing misleading consistency in sarcastic cases. The proposed framework is trained end-to-end with a multi-objective learning strategy that jointly optimizes multimodal classification and auxiliary unimodal supervision. Extensive experiments on MMSD and MMSD2.0 demonstrate that the proposed method consistently outperforms strong baselines.
4D understanding and reasoning is a fundamental capability for embodied AI agents operating in dynamic physical environments. However, existing vision encoders are largely limited to static 2D images or 3D point clouds without temporal modeling, or to 2D videos that lack accurate geometric depth reasoning. Consequently, current approaches fail to jointly capture spatial structure and motion evolution in dynamic scenes. We present CL4D, the first foundational 4D vision encoder that directly operates on dynamic point clouds, trained with a contrastive learning objective to align spatio-temporal geometric representations with natural language descriptions. By learning a shared embedding space between text and 4D scene dynamics, CL4D enables zero-shot motion-to-text and text-to-motion retrieval in dynamic environments and serves as a foundational 4D vision encoder for downstream 4D vision-language tasks. Building on this encoder, we introduce 4DVLM, a 4D vision-language model that conditions language generation on dynamic geometric representations. 4DVLM is the first VLM designed to operate directly on 4D point clouds without relying on 2D images, 2D videos, or static 3D point clouds. We train CL4D and subsequently 4DVLM on a newly constructed dataset termed DynAction4D capturing diverse human motions across varying object interactions and scene environments. Extensive experiments across multiple 4D human action benchmarks demonstrate that CL4D achieves state-of-the-art performance, with improvements of approximately ~16.75% over prior methods. Furthermore, 4DVLM outperforms frontier video VLMs such as Gemini and GPT-5 even when these models are provided with RGB video sequences corresponding to the same scenes represented as 4D point clouds for 4DVLM.
Dense-caption retrieval has recently been improved by introducing segmentation, edge maps, LLM-filtered captions, and cross-modal modules into contrastive fine-tuning. However, these methods largely inherit the same InfoNCE objective, whose optimization can prematurely saturate under a strong pre-trained initialization: on dense captions, the loss falls below 10^{-3} on 80% of batches within the first epoch, while its gradient reaches exact zero in fp32 in 47% of measurements. We find that this behavior is closely related to the large number of near-duplicate captions in dense-caption benchmarks, where a few highly similar negatives remain unresolved after the easy majority has already been separated. As a remedy, we introduce HN-CLIP, which uses the text encoder's own text-text geometry to construct per-negative adaptive similarity margins. Specifically, a detached caption-similarity matrix is added to the negative logits, assigning larger margins to more similar captions without mining, synthesizing, or resampling negatives. The resulting objective requires only one caption-similarity matrix and a masked logit addition during training, with no auxiliary data, additional parameters, offline preprocessing, or inference-time overhead. Extensive experiments on four dense-caption retrieval benchmarks show that HN-CLIP improves over the strongest competitors by +2.4--+4.3 R@1 while training 2.4x faster than GOAL and 5.4x faster than StructXLIP. Moreover, the proposed objective improves all six tested fine-tuning frameworks on the in-domain benchmarks and reaches the strongest full-data baseline with only 20% of the training data.
Vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities yet remain sensitive to real-world distribution shifts during inference. Although significant efforts are devoted to adapting VLMs at test time, they rely heavily on noisy pseudo-labels predicted directly from raw embedding similarities during inference, which are unreliable under distribution shift and mislead the adaptation. To avoid noise amplification, existing works craft coarse-grained surrogate objectives during adaptation, which fail to explicitly model sample-level relationships across different modalities, creating objective mismatch with inference, thus leading to marginal performance improvement. In this work, we aim to bridge the detached objectives of inference and adaptation for VLMs, and propose a principled VLM TTA method called \algname. For VLM inference, we formulate the zero-shot image classification task as a cross-modal alignment problem encoded via a Wasserstein OT formulation, providing robust pseudo-labels at the sample-level to effectively adapt VLMs. For VLM adaptation, we adopt a soft-label InfoNCE loss to adapt VLMs based on the OT-induced pseudo-labels, leveraging fine-grained supervisions to explicitly model relationships of individual image-text pairs via contrastive learning, which empowers accurate inference at the same granularity. Moreover, we theoretically reveal that the InfoNCE loss can be neatly reformulated as a Wasserstein OT formulation, thereby unifying the objectives of the inference and adaptation of VLMs to achieve their mutual benefits. Extensive experiments demonstrate the effectiveness and efficiency of our methods, outperforming the best-performing methods by up to 7% with state-of-the-art efficiency.
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.
This paper studies the problem of molecule-text alignment, which aims to project molecules and their textual descriptions into a joint latent space for downstream tasks including molecule search and molecular property prediction. Previous approaches typically combine graph structure mining with contrastive learning to enhance joint representation learning. However, they typically neglect fine-grained semantic relationships between substructures and texts, leading to suboptimal performance on downstream tasks. Towards this end, we propose a novel approach named Retrieval-guided Twin Fusion with Similarity-aware Contrast (RISEN) for molecule-text alignment. The core idea of RISEN is to construct a latent twin molecule for each substructure with cross-modal retrieval for semantic enhancement. In particular, for each substructure query, we retrieve relevant textual descriptions and sample several molecules that share similar descriptions of substructures. Then, we aggregate their representations via attention pooling for a twin latent representation, which would be further fused with the original substructure for representation enrichment. In addition, we measure the similarity across substructures and texts, which would further guide cross-modal contrastive learning with soft thresholding. Extensive experiments on benchmark datasets validate the superiority of the proposed RISEN in comparison with existing baselines.
Synchronized camera and wireless measurements observe the same scene through different physical channels. The central difficulty is that a representation learned in one deployment can fail when viewpoint, traffic, illumination, and propagation geometry change. This paper presents CM-MAE, a self-supervised vision--wireless pretraining framework for cross-scenario representation transfer. The evaluated real-data model uses only RGB frames and the measured 64-beam received-power vector available in DeepSense 6G; it does not use ray-traced paths, calibrated depth, or beam-index labels during pretraining. Its central pretraining term is a \emph{soft contrastive alignment loss}. Instead of making the synchronized image--wireless pair the only positive pair, this loss builds a target distribution from similarities between measured beam-power profiles, so nonidentical samples with similar directional responses are not forced apart as false negatives. A masked joint decoder provides the complementary local objective by reconstructing hidden visual patches and wireless angular clusters under modality dropout. After pretraining, a differential-rate fine-tuning rule lets a new fusion head adapt quickly while the encoders move slowly. Under a sequence-disjoint DeepSense 6G protocol, adding the soft alignment loss improves a matched linear-probe transfer average from 24.88\% to 29.49\%. Mild fusion fine-tuning reaches 77.38\% Top-1 accuracy on unseen Scenarios 6--8, and optional transductive normalization adaptation reaches 78.69\%. Since the fusion setting uses the contemporaneous 64-beam power vector at inference, these results should be read as representation-transfer diagnostics, not as proactive beam-prediction or reduced-sweeping claims.
Multimodal dialogue retrieval aims to retrieve dialogues from multimodal dialogue banks that are similar to a target dialogue in terms of both textual semantics and acoustic conversational styles. Such dialogue-level retrieval is crucial for many dialogue-related tasks, including Emotion Recognition in Conversation, Spoken Dialogue Systems, and Conversational Speech Synthesis, where external dialogue examples can provide valuable semantic and stylistic references. However, existing retrieval methods are still largely limited to utterance-level or unimodal matching, and often fail to capture the global semantic coherence and stylistic consistency of an entire dialogue. To address this gap, we propose S2Dialog, a unified framework for dialogue-level semantic-style retrieval from multimodal dialogue banks. Specifically, S2Dialog consists of a Dialogue-level Textual Retriever and a Dialogue-level Acoustic Retriever, which encode the textual and acoustic modalities of a dialogue into dialogue-level representations, respectively. To further enhance multimodal retrieval, we introduce Dialogue-level Textual-Acoustic Contrastive Learning, which aligns semantically and stylistically similar dialogues while distinguishing unrelated ones. Extensive experiments on the multimodal dialogue dataset DailyTalk demonstrate that S2Dialog achieves outstanding retrieval performance.
Haochen Zhang, Gengwei Zhang, Laura Yao +2cs.CL cs.LG
Synthesizing time series from natural language is emerging as the most expressive form of controllable time series generation. However, existing text-conditioned generators either take caption embeddings frozen from off-the-shelf text encoders, or adapt the encoder end-to-end, letting the denoising loss shape the embeddings only as a by-product. In either case, the conditioning representation is never deliberately matched to the signal modality, leaving it ill-suited to guide generation. We address this by introducing GALA: Generation-Aware cross-modaL Alignment for text conditional time series generation. GALA is a two-stage approach that first contrastively couples a pretrained text encoder with a time-series foundation model into a shared embedding space with both encoders adapted to generation by an auxiliary generative loss, and then freezes the resulting caption embedding to drive a flow-matching generator. On TSFragment-600K, spanning four domains and three fragment lengths, GALA sets a new state of the art, ranking first in 30 of 36 metric columns and reaching an average rank of 1.08/1.08/1.42 at lengths 24/48/96 against 1.92/2.00/1.75 for the strongest baseline. We further find that generator-internal text encoders force a trade-off between fidelity and caption adherence, whereas conditioning on the aligned embedding breaks it: FID, CTTP, and JFTSD all improve at once. Ablating the auxiliary loss degrades FID, CTTP and JFTSD together, it indicates the generative term is a necessary component of the alignment rather than an add-on.
Mahyar Ghazanfari, Amin Tabrizian, Arsyi Aziz +2cs.CV
Contrastive vision-language models such as CLIP and BLIP are typically trained on short image captions, limiting their ability to retrieve images from detailed textual descriptions. While methods such as Long-CLIP extend the token limit through positional embedding interpolation, we ask a simpler question: does training text granularity alone determine long-text retrieval performance? We present a systematic study of supervision ranging from single captions to multi-sentence paragraphs for contrastive image-text retrieval. Using a synthetic pipeline based on Qwen2-VL and Llama 3.2 Vision, we generate diverse captions, hard negatives, and quality-scored paragraphs for 500K CC3M images. To isolate the effect of text granularity, we fine-tune only the BLIP text encoder while keeping the vision encoder frozen across 10 training configurations. Our paragraph-supervised models match Long-CLIP-L on ShareGPT4V and outperform it by more than 14 points on DOCCI for image-to-text retrieval, without architectural changes. We further show that paragraph supervision enables effective use of long token sequences, whereas caption-only training degrades beyond 60 tokens. Increasing caption diversity improves short-caption retrieval with diminishing returns, while paragraph supervision consistently benefits long-description benchmarks and hard negatives prove detrimental in text-only fine-tuning. Evaluations on Flickr30k, COCO, ShareGPT4V, and DOCCI provide a comprehensive analysis of the trade-offs between text granularity, retrieval direction, and description length.
Bo Kong, Liruiz Jia, Yi Liang +5cs.CV cs.CL cs.IT cs.MM
Unified Multimodal Relation Extraction (UMRE) aims to identify intra-modal and cross-modal relations between textual entities and visual objects. However, existing UMRE studies still encounter two critical issues: ignoring inherent aleatoric uncertainty causes noise propagation, and deep-seated heterogeneity between distinct modal distributions hinders alignment. To address these issues, we propose the Uncertainty-Guided UMRE Network (UG-UMRE). Specifically, we design an Uncertainty-Driven Unimodal Augmentation (UDUA) module, which models features as Gaussian distributions based on the Variational Information Bottleneck. By incorporating an uncertainty-aware self-supervised contrastive learning mechanism, UDUA effectively filters out noise while maintaining semantic consistency. Furthermore, we introduce the Joint Aleatoric Uncertainty Alignment (JAUA) module as a global semantic pre-calibration mechanism. JAUA leverages probabilistic distribution consistency to construct a shared latent space, eliminating the distributional gap by synchronizing cross-modal statistical properties, thereby laying a robust foundation for fine-grained interaction. Experiments on three benchmark datasets (UMRE, MORE, and MNRE) demonstrate that UG-UMRE achieves state-of-the-art performance. Further analysis validates the pluggable and effective performance of the proposed UDUA and JAUA modules.
Multimodal retrievers are essential for knowledge-based visual question answering, where they retrieve external evidence for image-question pairs. However, existing contrastive training methods typically treat all unmatched query-document pairs as equally informative negatives, which is problematic because many unmatched documents may still be semantically relevant or partially useful. We propose Bayesian Data Reweighting, a probabilistic framework that models query-document importance as latent variables and adaptively infers posterior weights to downweight likely false negatives. With closed-form posterior updates under conjugate priors and stochastic EM optimization, our method consistently improves retrieval accuracy across three retrievers and seven knowledge-based VQA benchmarks.
Haonan Chen, Chu Li, Zhicheng Wang +4cs.IR cs.CL cs.CV
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.
Scaling the corpus is the default remedy when a contrastive representation lacks an attribute. We report a case where it does nothing, and identify what does: adding a lexical-speech round to a frozen-base multimodal embedding model raises zero-shot keyword spotting by 76 points while reducing speech-emotion recognition by 14. The loss is not a capacity limit: fine-tuning on 7,442 clips from a prosody-controlled corpus recovers emotion past its pre-speech level at a five-point keyword cost. Nor is it data volume: 29,428 mined clips whose captions explicitly name emotions, at matched exposure, move emotion by -0.0007. The difference is structural: a contrastive objective encodes an attribute only when the in-batch negatives cannot be separated without it; the controlled corpus holds sentence content fixed, so prosody is the only separating signal, whereas mined captions name emotion yet remain separable by scene content. Intervention on the same audio confirms causality: raising caption similarity does not recover emotion, but collapsing caption diversity so that emotion becomes the only separating axis recovers it by 8.9 points across three seeds, with a smaller, same-signed gain on a non-acted corpus, while keyword accuracy trades back. Corpus structure, not size or caption vocabulary, controls what a contrastive audio embedding encodes.
Recent radiology-adapted vision-language models have achieved strong performance on standard report generation benchmarks, yet their robustness and generalization remain constrained by imperfect alignment and correlation between visual and textual features. Existing methods connect image and text either implicitly through autoregressive report supervision or explicitly through contrastive learning. However, autoregressive supervision alone is insufficient to establish reliable image-text alignment, while contrastive learning can push apart unpaired reports that describe related pathologies simply because they are not paired with the same image. This is problematic in radiology, where different reports may share compatible pathology semantics rather than being true negatives. As a result, the learned representation may fail to organize images and reports around shared pathology concepts, causing the decoder to rely on pretrained language priors and generate clinically plausible reports that are not fully supported by radiographic evidence. To address this issue, we propose PALM, a pathology-aware alignment framework for radiology report generation. Instead of directly matching each image-report pair while separating all others, PALM aligns visual and textual features through shared pathology prototypes. These prototypes provide a clinically meaningful bridge between radiographic evidence and textual findings, allowing cases with similar pathology semantics to move toward common concepts without separating compatible cases. In addition, we introduce Masked Evidence Modeling to strengthen the image encoder sensitivity to local radiographic evidence by learning semantic changes caused by masked image regions. Experiments on MIMIC-CXR, IU X-Ray, and MIMIC-ABN show that PALM consistently improves both report generation and abnormality-focused robustness.
Large chest radiography archives are difficult to search because most studies are paired only with free-text reports rather than structured clinical annotations. Vision-language models offer a natural interface for text-to-image retrieval, but current biomedical models are primarily optimized for report-to-image matching rather than for satisfying short clinical search queries. This creates an objective mismatch: a model may retrieve images related to words in the query while failing to satisfy the full clinical constraint, especially for conjunctions and negations such as ``atelectasis and no pneumonia.'' We introduce CXR-Retrieve, a structured benchmark for compositional chest X-ray text-to-image retrieval. The benchmark contains 5,159 test images from the official test-split of MIMIC-CXR-JPG and 145 textual queries spanning single and conjunction findings, both positive and negative. Relevance is defined by whether a retrieved image satisfies all asserted pathology constraints, rather than by whether it matches a paired report. We further propose a label-aware contrastive fine-tuning objective for clinical retrieval. Our method attracts image-text pairs with compatible asserted pathology constraints, including shared confirmed absences, while explicitly repelling contradictory pairs. Starting from the in-domain CXR-CLIP checkpoint, our method improves Precision@5 over CXR-CLIP by 8.5 percentage points on two-pathology conjunctions and by 22.0 percentage points on negation queries. These results show that reliable chest X-ray retrieval requires training objectives that model not only which findings are mentioned, but also how they are clinically asserted.
Automating radiology report generation is important for improving reporting consistency and clinical workflows . While Contrastive Language--Image Pretraining (CLIP) has advanced medical vision language modeling, existing CLIP-style approaches may still provide insufficient fine-grained semantic supervision for complex report generation. Standard CLIP primarily optimizes cross-modal alignment, without explicitly structuring the textual embedding space that guides visual representation learning. To address this limitation, we propose TextSLIP, a general medical vision-language pretraining framework that augments CLIP with intra-modal text contrastive learning. By improving textual embedding discriminability through self-supervised augmented text pairs, TextSLIP is designed to provide finer-grained linguistic supervision to the visual encoder. As an initial validation, we pretrain TextSLIP on a curated dataset of 7 million brain MRI image-text pairs and fine-tune the pretrained visual encoder within a report generation architecture. In controlled comparisons with CLIP-style baselines, TextSLIP shows consistent improvements on report generation metrics. Ablation studies further suggest that text-side self-supervision contributes to the observed gains. These results indicate that text-level contrastive learning is a promising direction for improving medical visual-textual alignment, while broader validation across additional medical domains remains an important next step.