Spatial grounding, the process of associating natural language expressions with corresponding image regions, has rapidly advanced due to the introduction of transformer-based models, significantly enhancing multimodal representation and cross-modal alignment. Despite this progress, the field lacks a comprehensive synthesis of current methodologies, dataset usage, evaluation metrics, and industrial applicability. This paper presents a systematic literature review of transformer-based spatial grounding approaches from 2018 to 2025. Our analysis identifies dominant model architectures, prevalent datasets, and widely adopted evaluation metrics, alongside highlighting key methodological trends and best practices. This study provides essential insights and structured guidance for researchers and practitioners, facilitating the development of robust, reliable, and industry-ready transformer-based spatial grounding models.
EEG-based brain-computer interfaces (BCIs) have shown promise in various applications, such as motor imagery and cognitive state monitoring. However, decoding visual representations from EEG signals remains a significant challenge due to their complex and noisy nature. We thus propose a novel 5-stage framework for decoding visual representations from EEG signals: (1) an EEG encoder for concept classification, (2) cross-modal alignment of EEG and text embeddings in CLIP feature space, (3) caption refinement via re-ranking, (4) weighted interpolation of concept and caption embeddings for richer semantics, and (5) image generation using a pre-trained Stable Diffusion model. We enable context-aware EEG-to-image generation through cross-modal alignment and re-ranking. Experimental results demonstrate that our method generates high-quality images aligned with visual stimuli, outperforming SOTA approaches by 13.43% in Classification Accuracy, 15.21% in Generation Accuracy and reducing Fr\'echet Inception Distance by 36.61%, indicating superior semantic alignment and image quality.
With the advent of vision-language models (e.g., CLIP) in zero- and few-shot settings, CLIP has been widely applied to zero-shot anomaly detection (ZSAD) in recent research, where the rare classes are essential and expected in many applications. This study introduces \textbf{FiSeCLIP} for ZSAD with training-free \textbf{CLIP}, combining the feature matching with the cross-modal alignment. Testing with the entire dataset is impractical, while batch-based testing better aligns with real industrial needs, and images within a batch can serve as mutual reference points. Accordingly, FiSeCLIP utilizes other images in the same batch as reference information for the current image. However, the lack of labels for these references can introduce ambiguity, we apply text information to \textbf{fi}lter out noisy features. In addition, we further explore CLIP's inherent potential to restore its local \textbf{se}mantic correlation, adapting it for fine-grained anomaly detection tasks to enable a more accurate filtering process. Our approach exhibits superior performance for both anomaly classification and segmentation on anomaly detection benchmarks, building a stronger baseline for the direction, e.g., on MVTec-AD, FiSeCLIP outperforms the SOTA AdaCLIP by +4.6\%$\uparrow$/+5.7\%$\uparrow$ in segmentation metrics AU-ROC/$F_1$-max.
Despite the rapid advances in Text-to-Image (T2I) generation models, their evaluation remains challenging in domains like fashion, involving complex compositional generation. Recent automated T2I evaluation methods leverage pre-trained vision-language models to measure cross-modal alignment. However, our preliminary study reveals that they are still limited in assessing rich entity-attribute semantics, facing challenges in attribute confusion, i.e., when attributes are correctly depicted but associated to the wrong entities. To address this, we build on a Visual Question Answering (VQA) localization strategy targeting one single entity at a time across both visual and textual modalities. We propose a localized human evaluation protocol and introduce a novel automatic metric, Localized VQAScore (L-VQAScore), that combines visual localization with VQA probing both correct (reflection) and miss-localized (leakage) attribute generation. On a newly curated dataset featuring challenging compositional alignment scenarios, L-VQAScore outperforms state-of-the-art T2I evaluation methods in terms of correlation with human judgments, demonstrating its strength in capturing fine-grained entity-attribute associations. We believe L-VQAScore can be a reliable and scalable alternative to subjective evaluations.
Referring Remote Sensing Image Segmentation provides a flexible and fine-grained framework for remote sensing scene analysis via vision-language collaborative interpretation. Current approaches predominantly utilize a three-stage pipeline encompassing dual-modal encoding, cross-modal interaction, and pixel decoding. These methods demonstrate significant limitations in managing complex semantic relationships and achieving precise cross-modal alignment, largely due to their coupled processing mechanism that conflates target localization with boundary delineation. This architectural coupling amplifies error propagation under semantic ambiguity while restricting model generalizability and interpretability. To address these issues, we propose RSRefSeg 2, a decoupling paradigm that reformulates the conventional workflow into a collaborative dual-stage framework: coarse localization followed by fine segmentation. RSRefSeg 2 integrates CLIP's cross-modal alignment strength with SAM's segmentation generalizability through strategic foundation model collaboration. Specifically, CLIP is employed as the dual-modal encoder to activate target features within its pre-aligned semantic space and generate localization prompts. To mitigate CLIP's misactivation challenges in multi-entity scenarios described by referring texts, a cascaded second-order prompter is devised, which enhances precision through implicit reasoning via decomposition of text embeddings into complementary semantic subspaces. These optimized semantic prompts subsequently direct the SAM to generate pixel-level refined masks, thereby completing the semantic transmission pipeline. Extensive experiments (RefSegRS, RRSIS-D, and RISBench) demonstrate that RSRefSeg 2 surpasses contemporary methods in segmentation accuracy (+~3% gIoU) and complex semantic interpretation. Code is available at: https://github.com/KyanChen/RSRefSeg2.
We introduce DeSTA2.5-Audio, a general-purpose Large Audio Language Model (LALM) designed for robust auditory perception and instruction-following, without requiring task-specific audio instruction-tuning. Recent LALMs typically augment Large Language Models (LLMs) with auditory capabilities by training on large-scale, manually curated or LLM-synthesized audio-instruction datasets. However, these approaches have often suffered from the catastrophic forgetting of the LLM's original language abilities. To address this, we revisit the data construction pipeline and propose DeSTA, a self-generated cross-modal alignment strategy in which the backbone LLM generates its own training targets. This approach preserves the LLM's native language proficiency while establishing effective audio-text alignment, thereby enabling zero-shot generalization without task-specific tuning. Using DeSTA, we construct DeSTA-AQA5M, a large-scale, task-agnostic dataset containing 5 million training samples derived from 7,000 hours of audio spanning 50 diverse datasets, including speech, environmental sounds, and music. DeSTA2.5-Audio achieves state-of-the-art or competitive performance across a wide range of audio-language benchmarks, including Dynamic-SUPERB, MMAU, SAKURA, Speech-IFEval, and VoiceBench. Comprehensive comparative studies demonstrate that our self-generated strategy outperforms widely adopted data construction and training strategies in both auditory perception and instruction-following capabilities. Our findings underscore the importance of carefully designed data construction in LALM development and offer practical insights for building robust, general-purpose LALMs.
Benefiting from the advances in large language models and cross-modal alignment, existing multimodal large language models have achieved prominent performance in image and short video understanding. However, the understanding of long videos is still challenging, as their long-context nature results in significant computational and memory overhead. Most existing work treats long videos in the same way as short videos, which is inefficient for real-world applications and hard to generalize to even longer videos. To address these issues, we propose Flash-VStream, an efficient video language model capable of processing extremely long videos and responding to user queries in real time. Particularly, we design a Flash Memory module, containing a low-capacity context memory to aggregate long-context temporal information and model the distribution of information density, and a high-capacity augmentation memory to retrieve detailed spatial information based on this distribution. Compared to existing models, Flash-VStream achieves significant reductions in inference latency. Extensive experiments on long video benchmarks and comprehensive video benchmarks, i.e., EgoSchema, MLVU, LVBench, MVBench and Video-MME, demonstrate the state-of-the-art performance and outstanding efficiency of our method. Code is available at https://github.com/IVGSZ/Flash-VStream.
We introduce Skywork-R1V3, an advanced, open-source vision-language model (VLM) that pioneers a new approach to visual reasoning. Its key innovation lies in effectively transferring reasoning skills from text-only Large Language Models (LLMs) to visual tasks. The strong performance of Skywork-R1V3 primarily stems from our elaborate post-training RL framework, which effectively activates and enhances the model's reasoning ability, without the need for additional continue pre-training. Through this framework, we further uncover the fundamental role of the connector module in achieving robust cross-modal alignment for multimodal reasoning models. In addition, we introduce a unique indicator of reasoning capability, the entropy of critical reasoning tokens, which has proven highly effective for checkpoint selection during RL training. Skywork-R1V3 achieves state-of-the-art results on MMMU, significantly improving from 64.3% to 76.0%. This performance matches entry-level human capabilities. Remarkably, our RL-powered post-training approach enables even the 38B parameter model to rival top closed-source VLMs. The implementation successfully transfers mathematical reasoning to other subject-related reasoning tasks. We also include an analysis of curriculum learning and reinforcement finetuning strategies, along with a broader discussion on multimodal reasoning. Skywork-R1V3 represents a significant leap in multimodal reasoning, showcasing RL as a powerful engine for advancing open-source VLM capabilities.
Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, facing two critical challenges:cross-modal misalignment bias and intra-modal semantic divergence, which significantly degrade sentence representation quality. To address these challenges, we propose DALR (Dual-level Alignment Learning for Multimodal Sentence Representation). For cross-modal alignment, we propose a consistency learning module that softens negative samples and utilizes semantic similarity from an auxiliary task to achieve fine-grained cross-modal alignment. Additionally, we contend that sentence relationships go beyond binary positive-negative labels, exhibiting a more intricate ranking structure. To better capture these relationships and enhance representation quality, we integrate ranking distillation with global intra-modal alignment learning. Comprehensive experiments on semantic textual similarity (STS) and transfer (TR) tasks validate the effectiveness of our approach, consistently demonstrating its superiority over state-of-the-art baselines.
The rapid advancement of 3D vision-language models (VLMs) has spurred significant interest in interactive point cloud processing tasks, particularly for real-world applications. However, existing methods often underperform in point-level tasks, such as segmentation, due to missing direct 3D-text alignment, limiting their ability to link local 3D features with textual context. To solve this problem, we propose TSDASeg, a Two-Stage model coupled with a Direct cross-modal Alignment module and memory module for interactive point cloud Segmentation. We introduce the direct cross-modal alignment module to establish explicit alignment between 3D point clouds and textual/2D image data. Within the memory module, we employ multiple dedicated memory banks to separately store text features, visual features, and their cross-modal correspondence mappings. These memory banks are dynamically leveraged through self-attention and cross-attention mechanisms to update scene-specific features based on prior stored data, effectively addressing inconsistencies in interactive segmentation results across diverse scenarios. Experiments conducted on multiple 3D instruction, reference, and semantic segmentation datasets demonstrate that the proposed method achieves state-of-the-art performance.
Pathology is essential for cancer diagnosis, with multiple instance learning (MIL) widely used for whole slide image (WSI) analysis. WSIs exhibit a natural hierarchy -- patches, regions, and slides -- with distinct semantic associations. While some methods attempt to leverage this hierarchy for improved representation, they predominantly rely on Euclidean embeddings, which struggle to fully capture semantic hierarchies. To address this limitation, we propose HyperPath, a novel method that integrates knowledge from textual descriptions to guide the modeling of semantic hierarchies of WSIs in hyperbolic space, thereby enhancing WSI classification. Our approach adapts both visual and textual features extracted by pathology vision-language foundation models to the hyperbolic space. We design an Angular Modality Alignment Loss to ensure robust cross-modal alignment, while a Semantic Hierarchy Consistency Loss further refines feature hierarchies through entailment and contradiction relationships and thus enhance semantic coherence. The classification is performed with geodesic distance, which measures the similarity between entities in the hyperbolic semantic hierarchy. This eliminates the need for linear classifiers and enables a geometry-aware approach to WSI analysis. Extensive experiments show that our method achieves superior performance across tasks compared to existing methods, highlighting the potential of hyperbolic embeddings for WSI analysis.
Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal alignment and high-quality speech generation. In this work, we systematically investigate the impact of key components (i.e., speech tokenizers, speech heads, and speaker modeling) on the performance of LLM-centric SLMs. We compare coupled, semi-decoupled, and fully decoupled speech tokenizers under a fair SLM framework and find that decoupled tokenization significantly improves alignment and synthesis quality. To address the information density mismatch between speech and text, we introduce multi-token prediction (MTP) into SLMs, enabling each hidden state to decode multiple speech tokens. This leads to up to 12$\times$ faster decoding and a substantial drop in word error rate (from 6.07 to 3.01). Furthermore, we propose a speaker-aware generation paradigm and introduce RoleTriviaQA, a large-scale role-playing knowledge QA benchmark with diverse speaker identities. Experiments demonstrate that our methods enhance both knowledge understanding and speaker consistency.
Audio-Visual Segmentation (AVS) faces a fundamental challenge of effectively aligning audio and visual modalities. While recent approaches leverage foundation models to address data scarcity, they often rely on single-modality knowledge or combine foundation models in an off-the-shelf manner, failing to address the cross-modal alignment challenge. In this paper, we present TAViS, a novel framework that \textbf{couples} the knowledge of multimodal foundation models (ImageBind) for cross-modal alignment and a segmentation foundation model (SAM2) for precise segmentation. However, effectively combining these models poses two key challenges: the difficulty in transferring the knowledge between SAM2 and ImageBind due to their different feature spaces, and the insufficiency of using only segmentation loss for supervision. To address these challenges, we introduce a text-bridged design with two key components: (1) a text-bridged hybrid prompting mechanism where pseudo text provides class prototype information while retaining modality-specific details from both audio and visual inputs, and (2) an alignment supervision strategy that leverages text as a bridge to align shared semantic concepts within audio-visual modalities. Our approach achieves superior performance on single-source, multi-source, semantic datasets, and excels in zero-shot settings.
Mean Opinion Score (MOS) prediction for text to music systems requires evaluating both overall musical quality and text prompt alignment. This paper introduces WhisQ, a multimodal architecture that addresses this dual-assessment challenge through sequence level co-attention and optimal transport regularization. WhisQ employs the Whisper Base pretrained model for temporal audio encoding and Qwen 3, a 0.6B Small Language Model (SLM), for text encoding, with both maintaining sequence structure for fine grained cross-modal modeling. The architecture features specialized prediction pathways: OMQ is predicted from pooled audio embeddings, while TA leverages bidirectional sequence co-attention between audio and text. Sinkhorn optimal transport loss further enforce semantic alignment in the shared embedding space. On the MusicEval Track-1 dataset, WhisQ achieves substantial improvements over the baseline: 7% improvement in Spearman correlation for OMQ and 14% for TA. Ablation studies reveal that optimal transport regularization provides the largest performance gain (10% SRCC improvement), demonstrating the importance of explicit cross-modal alignment for text-to-music evaluation.
In real-word scenarios, person re-identification (ReID) expects to identify a person-of-interest via the descriptive query, regardless of whether the query is a single modality or a combination of multiple modalities. However, existing methods and datasets remain constrained to limited modalities, failing to meet this requirement. Therefore, we investigate a new challenging problem called Omni Multi-modal Person Re-identification (OM-ReID), which aims to achieve effective retrieval with varying multi-modal queries. To address dataset scarcity, we construct ORBench, the first high-quality multi-modal dataset comprising 1,000 unique identities across five modalities: RGB, infrared, color pencil, sketch, and textual description. This dataset also has significant superiority in terms of diversity, such as the painting perspectives and textual information. It could serve as an ideal platform for follow-up investigations in OM-ReID. Moreover, we propose ReID5o, a novel multi-modal learning framework for person ReID. It enables synergistic fusion and cross-modal alignment of arbitrary modality combinations in a single model, with a unified encoding and multi-expert routing mechanism proposed. Extensive experiments verify the advancement and practicality of our ORBench. A wide range of possible models have been evaluated and compared on it, and our proposed ReID5o model gives the best performance. The dataset and code will be made publicly available at https://github.com/Zplusdragon/ReID5o_ORBench.
Recent studies on end-to-end speech generation with large language models (LLMs) have attracted significant community attention, with multiple works extending text-based LLMs to generate discrete speech tokens. Existing approaches primarily fall into two categories: (1) Methods that generate discrete speech tokens independently without incorporating them into the LLM's autoregressive process, resulting in text generation being unaware of concurrent speech synthesis. (2) Models that generate interleaved or parallel speech-text tokens through joint autoregressive modeling, enabling mutual modality awareness during generation. This paper presents OmniDRCA, a parallel speech-text foundation model based on joint autoregressive modeling, featuring dual-resolution speech representations and contrastive cross-modal alignment. Our approach processes speech and text representations in parallel while enhancing audio comprehension through contrastive alignment. Experimental results on Spoken Question Answering benchmarks demonstrate that OmniDRCA establishes new state-of-the-art (SOTA) performance among parallel joint speech-text modeling based foundation models, and achieves competitive performance compared to interleaved models. Additionally, we explore the potential of extending the framework to full-duplex conversational scenarios.
Learning medical visual representations from image-report pairs through joint learning has garnered increasing research attention due to its potential to alleviate the data scarcity problem in the medical domain. The primary challenges stem from the lengthy reports that feature complex discourse relations and semantic pathologies. Previous works have predominantly focused on instance-wise or token-wise cross-modal alignment, often neglecting the importance of pathological-level consistency. This paper presents a novel framework PLACE that promotes the Pathological-Level Alignment and enriches the fine-grained details via Correlation Exploration without additional human annotations. Specifically, we propose a novel pathological-level cross-modal alignment (PCMA) approach to maximize the consistency of pathology observations from both images and reports. To facilitate this, a Visual Pathology Observation Extractor is introduced to extract visual pathological observation representations from localized tokens. The PCMA module operates independently of any external disease annotations, enhancing the generalizability and robustness of our methods. Furthermore, we design a proxy task that enforces the model to identify correlations among image patches, thereby enriching the fine-grained details crucial for various downstream tasks. Experimental results demonstrate that our proposed framework achieves new state-of-the-art performance on multiple downstream tasks, including classification, image-to-text retrieval, semantic segmentation, object detection and report generation.
Unlike traditional Multimodal Class-Incremental Learning (MCIL) methods that focus only on vision and text, this paper explores MCIL across vision, audio and text modalities, addressing challenges in integrating complementary information and mitigating catastrophic forgetting. To tackle these issues, we propose an MCIL method based on multimodal pre-trained models. Firstly, a Multimodal Incremental Feature Extractor (MIFE) based on Mixture-of-Experts (MoE) structure is introduced to achieve effective incremental fine-tuning for AudioCLIP. Secondly, to enhance feature discriminability and generalization, we propose an Adaptive Audio-Visual Fusion Module (AAVFM) that includes a masking threshold mechanism and a dynamic feature fusion mechanism, along with a strategy to enhance text diversity. Thirdly, a novel multimodal class-incremental contrastive training loss is proposed to optimize cross-modal alignment in MCIL. Finally, two MCIL-specific evaluation metrics are introduced for comprehensive assessment. Extensive experiments on three multimodal datasets validate the effectiveness of our method.
Video question grounding (VideoQG) requires models to answer the questions and simultaneously infer the relevant video segments to support the answers. However, existing VideoQG methods usually suffer from spurious cross-modal correlations, leading to a failure to identify the dominant visual scenes that align with the intended question. Moreover, vision-language models exhibit unfaithful generalization performance and lack robustness on challenging downstream tasks such as VideoQG. In this work, we propose a novel VideoQG framework named Cross-modal Causal Relation Alignment (CRA), to eliminate spurious correlations and improve the causal consistency between question-answering and video temporal grounding. Our CRA involves three essential components: i) Gaussian Smoothing Grounding (GSG) module for estimating the time interval via cross-modal attention, which is de-noised by an adaptive Gaussian filter, ii) Cross-Modal Alignment (CMA) enhances the performance of weakly supervised VideoQG by leveraging bidirectional contrastive learning between estimated video segments and QA features, iii) Explicit Causal Intervention (ECI) module for multimodal deconfounding, which involves front-door intervention for vision and back-door intervention for language. Extensive experiments on two VideoQG datasets demonstrate the superiority of our CRA in discovering visually grounded content and achieving robust question reasoning. Codes are available at https://github.com/WissingChen/CRA-GQA.
Vision-Language Navigation (VLN) enables intelligent agents to navigate environments by integrating visual perception and natural language instructions, yet faces significant challenges due to the scarcity of fine-grained cross-modal alignment annotations. Existing datasets primarily focus on global instruction-trajectory matching, neglecting sub-instruction-level and entity-level alignments critical for accurate navigation action decision-making. To address this limitation, we propose FCA-NIG, a generative framework that automatically constructs navigation instructions with dual-level fine-grained cross-modal annotations. In this framework, an augmented trajectory is first divided into sub-trajectories, which are then processed through GLIP-based landmark detection, crafted instruction construction, OFA-Speaker based R2R-like instruction generation, and CLIP-powered entity selection, generating sub-instruction-trajectory pairs with entity-landmark annotations. Finally, these sub-pairs are aggregated to form a complete instruction-trajectory pair. The framework generates the FCA-R2R dataset, the first large-scale augmentation dataset featuring precise sub-instruction-sub-trajectory and entity-landmark alignments. Extensive experiments demonstrate that training with FCA-R2R significantly improves the performance of multiple state-of-the-art VLN agents, including SF, EnvDrop, RecBERT, and HAMT. Incorporating sub-instruction-trajectory alignment enhances agents' state awareness and decision accuracy, while entity-landmark alignment further boosts navigation performance and generalization. These results highlight the effectiveness of FCA-NIG in generating high-quality, scalable training data without manual annotation, advancing fine-grained cross-modal learning in complex navigation tasks.