Multimodal Learning

This manuscript extends our previous multimodal human-robot interaction system by introducing a controlled ablation study of the three modules that most strongly influence end-to-end performance: the large language model used for action extraction, the perception system used for visual grounding, and the controller used for motion execution. The goal is not to redesign the full pipeline, but to isolate the contribution of each component under a common experimental protocol and then evaluate the best combinations end-to-end. We therefore compare three language models, five perception configurations, and three controllers, followed by a second-stage factorial study over the best candidates. The resulting analysis is intended to clarify which choices primarily affect execution time, which primarily affect success rate, and where the largest engineering gains are likely to come from in future revisions of the system.

Energy-based models (EBMs) are a flexible class of deep generative models and are well-suited to capture complex dependencies in multimodal data. However, learning multimodal EBM by maximum likelihood requires Markov Chain Monte Carlo (MCMC) sampling in the joint data space, where noise-initialized Langevin dynamics often mixes poorly and fails to discover coherent inter-modal relationships. Multimodal VAEs have made progress in capturing such inter-modal dependencies by introducing a shared latent generator and a joint inference model. However, both the shared latent generator and joint inference model are parameterized as unimodal Gaussian (or Laplace), which severely limits their ability to approximate the complex structure induced by multimodal data. In this work, we study the learning problem of the multimodal EBM, shared latent generator, and joint inference model. We present a learning framework that effectively interweaves their MLE updates with corresponding MCMC refinements in both the data and latent spaces. Specifically, the generator is learned to produce coherent multimodal samples that serve as strong initial states for EBM sampling, while the inference model is learned to provide informative latent initializations for generator posterior sampling. Together, these two models serve as complementary models that enable effective EBM sampling and learning, yielding realistic and coherent multimodal EBM samples. Extensive experiments demonstrate superior performance for multimodal synthesis quality and coherence compared to various baselines. We conduct various analyses and ablation studies to validate the effectiveness and scalability of the proposed multimodal framework.

Multimodal large language models (MLLMs) have shown strong performance on objective tasks such as video understanding and reasoning. However, it remains unclear whether they can approximate subjective human responses, which depend not only on content comprehension but also on individuals' social contexts. To address this gap, we evaluate MLLMs as synthetic participants in an emerging task: assessing perceived sensory engagement with short videos. Grounded in the Perceived Message Sensation Value (PMSV) framework, we compare ratings from recruited human participants and profile-conditioned MLLM simulations (n=673) using a 17-item scale measuring emotional arousal, dramatic impact, and novelty. We find that even leading MLLMs (Gemini 3 Flash and Qwen 3 Omni) show limited agreement with human participants. The models exhibit distinct downward mean-shift and central-tendency biases in their rating distributions. They both introduce and flatten subgroup differences, while showing inconsistent sensitivity to participant profiles. Prompting strategies affect these metrics differently, modestly improving some aspects while worsening others. These results highlight both the challenges and opportunities of developing MLLMs as synthetic participants in video-based research. Data and code: https://github.com/MINDLab25/mllm-human-simulation-eval

Unified multimodal understanding and generation models enable richer human-AI interaction. Yet jointly customizing a character's persona, dialogue style, and visual identity while maintaining output consistency across modalities remains largely unexplored. To mitigate this gap, we introduce a new task, Customized Multimodal Role-Play (CMRP). We construct the RoleScape-20 dataset comprising 20 characters, including training and evaluation data that cover persona, stylistic descriptions, visual/expressive cues, and text-image interactions. Building on a unified model, we devise UniCharacter, a two-stage training framework containing Unified Supervised Finetuning (Unified-SFT) and character-specific group relative policy optimization (Character-GRPO). Given only 10 images plus corresponding interaction examples, the model acquires the target character and exhibits coherent persona, style, and visual identity in both generated text and images. This process takes about 100 GPU hours. Experiments on the RoleScape-20 dataset show that the proposed method substantially outperforms prior approaches. Ablation studies further validate the effectiveness of our cross-modal consistency design and few-shot customization strategy. We argue that CMRP, coupled with unified modeling, provides a basis for next-generation characterful and immersive interactive agents.

With the advancement of multimodal large language models (MLLMs) and coding agents, the website development has shifted from manual programming to agent-based project-level code synthesis. Existing benchmarks rely on idealized assumptions, especially for well-structured, information-rich inputs and static execution settings. In contrast, real-world development is constrained by a critical bottleneck: the semantic misalignment between ambiguous, low-quality instructions from non-expert users and model understanding, which results in a failure mode that we term blind execution. To address this gap, we introduce InteractWeb-Bench, the first multimodal interactive benchmark for website generation under non-expert low-code user conditions. InteractWeb-Bench introduces four types of user agents and persona-driven instruction perturbations to systematically simulate diverse user behaviors, including ambiguity, redundancy, and contradiction, grounded in requirement engineering defect taxonomies. We develop an interactive execution environment for agents, featuring a unified action space comprising Clarify, Implement, Verify, and Submit, enabling iterative intent refinement, code synthesis, and visual feedback-based validation. Extensive experiments and analysis reveal that frontier MLLM-based agents remain trapped in blind execution, exposing limitations in intent recognition and adaptive interaction.

Audio-visual deepfakes have reached a level of realism that makes perceptual detection unreliable, threatening media integrity and biometric security. While multimodal detection has shown promise, most approaches are binary classification tasks that often latch onto dataset-specific artifacts rather than genuine generative traces. We argue that a detector incapable of identifying how a video was forged is likely learning the wrong signal. Unlike binary detection, attribution-guided learning imposes a stronger geometric constraint on the shared embedding space, forcing the model to encode generator-specific forensic content rather than shortcuts. We propose the Attribution-Guided Multimodal Deepfake Detection (AMDD) framework, which jointly learns to detect and attribute manipulation. AMDD treats generator attribution as a structured regularization that constrains representation geometry toward forensically meaningful features. We introduce a Cross-Modal Forensic Fingerprint Consistency (CMFFC) loss to enforce alignment between generator-induced artifacts in visual and audio streams. This exploits the fact that coherent manipulation leaves correlated traces across modalities, grounded in the physical coupling between speech and facial articulation that synthetic pipelines routinely disrupt. Architecturally, we pair a ResNet50 with temporal attention for visual encoding against a pretrained ResNet18 for mel spectrograms, closing the encoder capacity gap found in prior models. On FakeAVCeleb, AMDD achieves 99.7% balanced accuracy and 99.8% AUC with 95.9% attribution accuracy. Cross-dataset evaluation on DeepfakeTIMIT, DFDM, and LAV-DF confirms that real video detection generalizes robustly, while fake detection on unseen generators remains an open challenge that we analyze in depth.

Most enterprise document AI today is a pipeline. Parse, index, retrieve, generate. Each of those stages has been studied to death on its own -- what's still hard is evaluating the system as a whole. We built EnterpriseDocBench to take a swing at it: parsing fidelity, indexing efficiency, retrieval relevance, and generation groundedness, all on the same corpus. The corpus is built from public, permissively licensed documents across six enterprise domains (five represented in the current pilot). We ran three pipelines through it -- BM25, dense embedding, and a hybrid -- all with the same GPT-5 generator. The headline numbers: hybrid retrieval narrowly beats BM25 (nDCG@5 of 0.92 vs. 0.91), and both beat dense embedding (0.83). Hallucination doesn't grow monotonically with document length -- short documents and very long ones both hallucinate more than medium ones (28.1% and 23.8% vs. 9.2%). Cross-stage correlations are very weak: parsing->retrieval r=0.14, parsing->generation r=0.17, retrieval->generation 0.02. If quality were cascading the way most of us assume, those numbers would be much higher; they aren't. Design caveats are real (parsing fixed, generator shared, automated proxy metrics) and we don't oversell the result. One result that genuinely surprised us: factual accuracy on stated claims is 85.5%, but answer completeness averages 0.40. The system is right when it answers -- it just leaves things out. That gap matters more for real deployments than the headline accuracy number does. We also describe three reference architectures (ColPali, ColQwen2, agentic complexity-based routing) which are not yet integrated end-to-end. Framework, metrics, baselines, and collection scripts will be released open-source on acceptance.

Reliable seizure detection in mouse models is essential for preclinical epilepsy research, yet manual review of synchronized video-EEG recordings is labor-intensive and single-modality systems fail for complementary reasons: video-based methods are easily confounded by benign behaviors, whereas EEG-based methods are vulnerable to ictal motion artifacts. We present EEGVFusion, a multimodal framework that combines self-supervised EEG representation learning, spatio-temporal video encoding, optimal-transport alignment, and bidirectional cross-attention to integrate neural and behavioral evidence. We also curate an expert-annotated dataset of synchronized EEG and video recordings comprising 93 sessions from 15 mice for training and evaluation. In the random-session split, EEGVFusion achieved a Balanced Accuracy of 0.9957 with perfect event sensitivity and an Event FAR of 0.6250 FP/h, indicating strong seizure detection performance with a low false-alarm burden. In a single held-out-subject evaluation with Subject 110 reserved for testing, EEGVFusion achieved a Balanced Accuracy of 0.9718 and reduced Event FAR from 2.7250 FP/h for the EEG-only counterpart to 0.4833 FP/h while preserving perfect event sensitivity. Targeted ablations further showed that EEG pre-training and OT alignment help reduce false alarms while preserving event sensitivity.

Multimodal deep neural networks deployed in realistic environments must contend with runtime variations: changes in modality quality, overall input complexity, and available platform resources. Current networks struggle with such fluctuations -- adaptive networks cannot adhere to a strict compute budget, controller-based networks neglect to consider input complexity, and statically provisioned networks fail at all the above. Consequently, they do not extract maximum utility from the expended computational resources. We present SWAN (Sample and World-Aware Multimodal Network), the first adaptive multimodal network that accomplishes all three goals. SWAN employs a quality-aware controller to assign resources among modalities according to a variable user-specified maximum budget. Within this budget, an adaptive gating module further optimizes efficiency by scaling layer utilization according to sample complexity. For further gains, SWAN also employs a token dropping module that masks semantically irrelevant multimodal features before performing detections. We evaluate SWAN in the domain of autonomous driving with complex multi-object 3D detection, reducing FLOPs by up to 49% with minimal degradation.

Despite strong performance of deep learning models in retinal disease detection, most systems produce static predictions without clinical reasoning or interactive explanation. Recent advances in multimodal large language models (MLLMs) integrate diagnostic predictions with clinically meaningful dialogue to support clinical decision-making and patient counseling. In this study, OcularChat, an MLLM, was fine-tuned from Qwen2.5-VL using simulated patient-physician dialogues to diagnose age-related macular degeneration (AMD) through visual question answering on color fundus photographs (CFPs). A total of 705,850 simulated dialogues paired with 46,167 CFPs were generated to train OcularChat to identify key AMD features and produce reasoned predictions. OcularChat demonstrated strong classification performance in AREDS, achieving accuracies of 0.954, 0.849, and 0.678 for the three diagnostic tasks: advanced AMD, pigmentary abnormalities, and drusen size, significantly outperforming existing MLLMs. On AREDS2, OcularChat remained the top-performing method on all tasks. Across three independent ophthalmologist graders, OcularChat achieved higher mean scores than a strong baseline model for advanced AMD (3.503 vs. 2.833), pigmentary abnormalities (3.272 vs. 2.828), drusen size (3.064 vs. 2.433), and overall impression (2.978 vs. 2.464) on a 5-point clinical grading rubric. Beyond strong objective performance in AMD severity classification, OcularChat demonstrated the ability to provide diagnostic reasoning, clinically relevant explanations, and interactive dialogue, with high performance in subjective ophthalmologist evaluation. These findings suggest that MLLMs may enable accurate, interpretable, and clinically useful image-based diagnosis and classification of AMD.

Source code and its accompanying comments are complementary yet naturally aligned modalities-code encodes structural logic while comments capture developer intent. However, existing vulnerability detection methods mostly rely on single-modality code representations, overlooking the complementary semantic information embedded in comments and thus limiting their generalization across complex code structures and logical relationships. To address this, we propose MultiVul, a multimodal contrastive framework that aligns code and comment representations through dual similarity learning and consistency regularization, augmented with diverse code-text pairs to improve robustness. Experiments on widely adopted DiverseVul and Devign datasets across four large language models (LLMs) (i.e., DeepSeek-Coder-6.7B, Qwen2.5-Coder-7B, StarCoder2-7B, and CodeLlama-7B) show that MultiVul achieves up to 27.07% F1 improvement over prompting-based methods and 13.37% over code-only Fine-Tuning, while maintaining comparable inference efficiency.

Online comments play a crucial role in shaping public sentiment and opinion dynamics on social media. However, evaluating their popularity remains challenging, not only because it depends on linguistic quality, originality, and emotional resonance, but also because stylistic preferences vary widely across platforms and user groups, causing the same comment to resonate differently in different communities. In this work, we present HotComment, a multimodal benchmark integrating video and text modalities that comprehensively quantifies popularity from three enhanced aspects: (1) Content Quality, which evaluates semantic similarity with ground-truth human comments and extends quality assessment through four interpretable dimensions; (2) Popularity Prediction, based on trends from models trained on real-world interaction data; and (3) User Behavior Simulation, which models the distribution of platform users and approximates \textbf{engagement scores} through an agent-based framework. Furthermore, we propose StyleCmt, inspired by social ripple effects, where multiple stylistic dimensions align to amplify socially resonant expressions and suppress incongruent ones.

We introduce DualFact, a dual-layer, multimodal factuality evaluation framework for procedural video captioning. DualFact separates factual correctness into conceptual facts, capturing abstract semantic roles (e.g., Action, Ingredient, Tool, Location), and contextual facts, capturing their grounded predicate-argument realizations in video. To support complete and role-consistent evaluation, DualFact incorporates implicit argument augmentation (VIA) and contrastive fact sets. We instantiate DualFact in two modes: DualFact-T, which verifies facts against textual evidence, and DualFact-V, which verifies facts against video-grounded visual evidence. Experiments on YouCook3-Fact and CraftBench-Fact show that state-of-the-art multimodal language models produce fluent but often factually incomplete captions, with systematic omissions and role-level inconsistencies. DualFact correlates more strongly with human factuality judgments than standard metrics, particularly for contextual facts, and reveals that caption-only evaluation overestimates hallucinations compared to video-grounded verification. Overall, DualFact offers an interpretable and human-aligned evaluation protocol that highlights persistent challenges in multimodal factual grounding, extending beyond surface-level fluency.

We present M$^3$-VQA, a novel knowledge-based Visual Question Answering (VQA) benchmark, to enhance the evaluation of multimodal large language models (MLLMs) in fine-grained multimodal entity understanding and complex multi-hop reasoning. Unlike existing VQA datasets that focus on coarse-grained categories and simple reasoning over single entities, M$^3$-VQA introduces diverse multi-entity questions involving multiple distinct entities from both visual and textual sources. It requires models to perform both sequential and parallel multi-hop reasoning across multiple documents, supported by traceable, detailed evidence and a curated multimodal knowledge base. We evaluate 16 leading MLLMs under three settings: without external knowledge, with gold evidence, and with retrieval-augmented input. The poor results reveal significant challenges for MLLMs in knowledge acquisition and reasoning. Models perform poorly without external information but improve markedly when provided with precise evidence. Furthermore, reasoning-aware agentic retrieval surpasses heuristic methods, highlighting the importance of structured reasoning for complex multimodal understanding. M$^3$-VQA presents a more challenging evaluation for advancing the multimodal reasoning capabilities of MLLMs. Our code and dataset are available at https://github.com/CASIA-IVA-Lab/M3VQA.

Unified Multimodal Models (uMMs) aim to support both visual understanding and visual generation within a shared representation. However, existing evaluation protocols assess these two capabilities independently and do not examine whether they are semantically aligned. As a result, it remains unclear whether current uMMs learn coherent unified representations that remain consistent across tasks given a visual concept. We introduce XTC-Bench, a scene-graph-grounded evaluation framework that measures cross-task visual semantic consistency. By deriving both generation prompts and understanding queries from a structured scene graph, our framework enables fact-level alignment analysis across objects, attributes, and relations. We propose Continuous Cross-Task Agreement (CCTA), a fine-grained metric that quantifies semantic agreement between generation and understanding over matched atomic facts, isolating internal consistency from standalone task accuracy. Extensive experiments on eight open-source and one commercial unified models reveal that high generation or understanding performance does not imply strong cross-task alignment, and architectural analysis shows consistency is governed by how tightly learning objectives are coupled across modalities, not by architectural unification alone. XTC-Bench provides a reproducible and model-agnostic framework for diagnosing representation-level misalignment, offering a concrete direction for advancing unified multimodal modeling beyond isolated task performance.

We introduce Nemotron 3 Nano Omni, the latest model in the Nemotron multimodal series and the first to natively support audio inputs alongside text, images, and video. Nemotron 3 Nano Omni delivers consistent accuracy improvements over its predecessor, Nemotron Nano V2 VL, across all modalities, enabled by advances in architecture, training data and recipes. In particular, Nemotron 3 delivers leading results in real-world document understanding, long audio-video comprehension, and agentic computer use. Built on the highly efficient Nemotron 3 Nano 30B-A3B backbone, Nemotron 3 Nano Omni further incorporates innovative multimodal token-reduction techniques to deliver substantially lower inference latency and higher throughput than other models of similar size. We are releasing model checkpoints in BF16, FP8, and FP4 formats, along with portions of the training data and codebase to facilitate further research and development.

Biological function emerges from coupled constraints across sequence, structure, regulation, evolution, and cellular context, yet most foundation models in biology are trained within one modality or for a fixed forward task. We present MIMIC, a generative multimodal foundation model trained on our newly curated and aligned dataset, LORE, linking nucleic acid, protein, evolutionary, structural, regulatory, and semantic/contextual modalities within partially observed biomolecular states. MIMIC uses a split-track encoder-decoder architecture to condition on arbitrary subsets of observed modalities and reconstruct or generate missing components of molecular state across the genome, transcriptome, and proteome. Multimodal conditioning consistently improves MIMIC's sequence reconstruction relative to sequence-only inputs, while its learned representations enable state-of-the-art performance on RNA and protein downstream tasks. MIMIC achieves state-of-the-art splicing prediction, and its joint generative formulation enables isoform-aware inference that further improves performance. Beyond prediction, the same generative framework supports constrained design. For RNA, MIMIC identifies corrective edits in a clinically relevant HBB splice-disrupting mutation without reverting it by using evolutionary and structural signals. For proteins, jointly conditioning on shape and surface chemistry of PD-L1 and hACE2 binding sites produces diverse, high-confidence sequences with strong in silico support for target binding. Finally, MIMIC uses experimental context as semantic conditioning to model assay-dependent RNA chemical probing, rather than treating context as a fixed output. Together, these results position MIMIC's aligned multimodal generative modeling as a strong foundation for unifying representation learning, conditional prediction, and constrained biomolecular design within a single model.

Video-to-text summarization remains underexplored in terms of comprehensive evaluation methods. Traditional n-gram overlap-based metrics and recent large language model (LLM)-based approaches depend heavily on human-written reference summaries, limiting their practicality and sensitivity to nuanced semantic aspects. In this paper, we propose QEVA, a reference-free metric evaluating candidate summaries directly against source videos through multimodal question answering. QEVA assesses summaries along three clear dimensions: Coverage, Factuality, and Chronology. We also introduce MLVU(VS)-Eval, a new annotated benchmark derived from the MLVU dataset, comprising 800 summaries generated from 200 videos using state-of-the-art video-language multimodal models. This dataset establishes a transparent and consistent framework for evaluation. Experimental results demonstrate that QEVA shows higher correlation with human judgments compared to existing approaches, as measured by Kendall's $τ_b$, $τ_c$, and Spearman's $ρ$. We hope that our benchmark and metric will facilitate meaningful progress in video-to-text summarization research and provide valuable insights for the development of future evaluation methods.

Identifying species in biology among tens of thousands of visually similar taxa while discovering unknown species in open-world environments remains a fundamental challenge in biodiversity research. Current methods treat identification and discovery as separate problems, with classification models assuming closed sets and discovery relying on threshold-based rejection. Here we present DeepTaxon, a retrieval-augmented multimodal framework that unifies species identification and discovery through interpretable reasoning over retrieved visual evidence. Given a query image, DeepTaxon retrieves the top-$k$ candidate species with $n$ exemplar images each from a retrieval index and performs chain-of-thought comparative reasoning. Critically, we redefine discovery as an explicit, retrieval-based decision problem rather than an implicit parametric memory problem. A sample is novel if and only if the retrieval index lacks sufficient evidence for identification, so each retrieval naturally yields a classification or discovery label without manual annotation, thereby providing automatic supervision for both tasks. We train the framework via supervised fine-tuning on synthetic retrieval-augmented data, followed by reinforcement learning on hard samples, converting high-recall retrieval into high-precision decisions that scale to massive taxonomic vocabularies. Extensive experiments on a large-scale in-distribution benchmark and six out-of-distribution datasets demonstrate consistent improvements in both identification and discovery. Ablation studies further reveal effective test-time scaling with candidate count $k$ and exemplar count $n$, strong zero-shot transfer to unseen domains, and consistent performance across retrieval encoders, establishing an interpretable solution for biodiversity research.

Digital pathology has fundamentally altered diagnostic workflows by enabling the computational analysis of gigapixel Whole Slide Images (WSIs), yet effectively deciphering their complex tumor microenvironments remains a formidable challenge. Existing Multiple Instance Learning (MIL) frameworks typically treat Whole Slide Images as unstructured bags of patches, discarding critical morphological semantics and spatial geometry. This lack of inductive bias often leads to overfitting on background noise and fails to align visual features with high-level diagnostic knowledge. To overcome these limitations, we propose the Hierarchical Prototype-based Domain Priors (HPDP) framework, a unified multimodal approach for joint histopathology diagnosis and prognosis. HPDP mitigates the data-driven "black box" issue by introducing a Morphologically Anchored Prototype System (MAPS), which anchors learning to interpretable morphological clusters, and a Sinusoidal Positional Encoder (SPE) to explicitly model tissue architecture. Furthermore, we bridge the semantic gap via a Hierarchical Cross-Modal Alignment (HCMA) module, using Large Language Model (LLM)-generated descriptions to contextually refine visual representations. Extensive experiments across seven cancer cohorts demonstrate that HPDP consistently achieves state-of-the-art performance with superior robustness and interpretability.

Egocentric videos provide a distinctive setting in which sound serves as crucial cues to understand user activities and surroundings, particularly when visual information is unstable or occluded due to continuous camera movement. State-of-the-art large audio-visual language models (AV-LLMs) can generate multimodal descriptions. However, we show in this work that they are prone to audio hallucinations, often inferring sounds from visual cues that are visible but not heard. We present a systematic and automatic evaluation framework for analyzing audio hallucinations in egocentric video through a targeted question-answering (Q/A) protocol. We curate a dataset of 300 egocentric videos and design 1,000 sound-focused questions to probe model outputs. To characterize hallucinations, we propose a grounded taxonomy that distinguishes between foreground action sounds from the user activities and background ambient sounds. Our evaluation shows that advanced AV-LLMs, such as Qwen2.5 Omni, exhibit high hallucination rates, achieving only 27.3% and 39.5% accuracy on Q/As related to foreground and background sounds, respectively. With this work, we highlight the need to measure the reliability of multimodal responses, emphasizing that robust evaluation of hallucinations is essential to develop reliable AV-LLMs.

The vast and underexplored ocean plays a critical role in regulating global climate and supporting marine biodiversity, yet artificial intelligence has so far delivered limited impact in this domain due to a fundamental data bottleneck. Specifically, ocean data are highly fragmented across disparate sources and inherently exhibit multi-modal, high-noise, and weakly labeled characteristics, lacking unified schemas and semantic alignment. Although Multimodal Large Language Models (MLLMs) have achieved remarkable success in general domains, their application to ocean science remains severely constrained by the absence of large-scale, well-aligned multimodal datasets tailored to marine environments. To bridge this gap, we introduce OceanPile, a large-scale multimodal corpus designed for ocean foundation models. It comprises three key components: OceanCorpus, a unified collection integrating sonar data, underwater imagery, marine science visuals, and scientific text from diverse authoritative sources; OceanInstruction, a high-quality instruction dataset synthesized via a novel pipeline guided by a hierarchical Ocean Concept Knowledge Graph; and OceanBenchmark, a manually curated evaluation benchmark for rigorous assessment. We establish a multi-stage quality control process to ensure scientific validity and alignment across modalities. Experimental validation demonstrates significant performance improvements for models trained on our data. All datasets are publicly released to advance the field of marine artificial intelligence and empower domain-specific MLLMs.

Audio-text retrieval enables semantic alignment between audio content and natural language queries, supporting applications in multimedia search, accessibility, and surveillance. However, current state-of-the-art approaches struggle with long, noisy, and weakly labeled audio due to their reliance on contrastive learning and large-batch training. We propose a novel multimodal retrieval framework that refines audio and text embeddings using a cross-modal embedding refinement module combining transformer-based projection, linear mapping, and bidirectional attention. To further improve robustness, we introduce a hybrid loss function blending cosine similarity, $\mathcal{L}_{1}$, and contrastive objectives, enabling stable training even under small-batch constraints. Our approach efficiently handles long-form and noisy audio (SNR 5 to 15) via silence-aware chunking and attention-based pooling. Experiments on benchmark datasets demonstrate improvements over prior methods.

In this work, we present Au-M-ol, a novel multimodal architecture that extends Large Language Models (LLMs) with audio processing. It is designed to improve performance on clinically relevant tasks such as Automatic Speech Recognition (ASR). Au-M-ol has three main components: (1) an audio encoder that extracts rich acoustic features from medical speech, (2) an adaptation layer that maps audio features into the LLM input space, and (3) a pretrained LLM that performs transcription and clinical language understanding. This design allows the model to interpret spoken medical content directly, improving both accuracy and robustness. In experiments, Au-M-ol reduces Word Error Rate (WER) by 56% compared to state-of-the-art baselines on medical transcription tasks. The model also performs well in challenging conditions, including noisy environments, domain-specific terminology, and speaker variability. These results suggest that Au-M-ol is a strong candidate for real-world clinical applications, where reliable and context-aware audio understanding is essential.

Human activity recognition serves as the foundation for various emerging applications. In recent years, researchers have used collaborative sensing of multi-source sensors to capture complex and dynamic human activities. However, multimodal human activity sensing typically encounters highly heterogeneous data across modalities and label scarcity, resulting in an application gap between existing solutions and real-world needs. In this paper, we propose CLMM, a general contrastive learning framework for human activity recognition that achieves effective multimodal recognition with limited labeled data. CLMM employs a novel two-stage training strategy. In the first stage, CLMM employs a CNN-DiffTransformer encoder to capture cross-modal shared information by extracting local and global features. Meanwhile, a hard-positive samples weighting algorithm enhances gradient propagation to reinforce shared learning. In the second stage, a dual-branch architecture combining quality-guided attention and bidirectional gated units captures modality-specific information, while a primary-auxiliary collaborative training strategy fuses both shared and modality-specific information. Experimental results on three public datasets demonstrate that CLMM significantly improves state-of-the-art baselines in both recognition accuracy and convergence performance.

Video Situation Recognition (VidSitu) addresses the challenging problem of "who did what to whom, with what, how, and where" in a video. It tests thorough video understanding by requiring identification of salient actions and associated short descriptions for event roles across multiple events. Grounding with VidSitu requires spatio-temporal localization of key entities across shots and varied appearances. We posit that coherent video understanding requires consistent identification of entities that play different roles. We propose Multimodal Entity Coreference (MEC) to unite entity descriptions in text with grounding across the video. Towards this, we introduce CineMEC, a multi-stage approach that unites event role mention groups with visual clusters of entities, without explicit grounding supervision during training. Our approach is designed to exploit the synergy between visual grounding and captioning, where improving one influences the other and vice versa. For evaluation, we extend the VidSitu dataset with grounding annotations. While previous work focuses primarily on descriptions, CineMEC improves consistency across both: captioning (+2.5% CIDEr, +7% LEA) and visual grounding (+18% HOTA).

Chronic osteomyelitis presents substantial prognostic challenges due to its high recurrence risk and complex postoperative recovery trajectories. Traditional assessment often relies on manual scoring systems, which limit scalability, efficiency, and consistency in clinical practice. Furthermore, the heterogeneous nature of clinical data poses challenges for current multimodal learning approaches that require aligned inputs and large annotated datasets. In this work, we propose RAG4Outcome, a retrieval-augmented generation (RAG) framework for prognostic prediction in chronic osteomyelitis. Our method integrates multimodal clinical data, including PET-CT imaging reports, structured surgical and diagnostic records, and unstructured follow-up notes, into a unified prediction pipeline. By combining a domain-specific retrieval corpus with expert-guided prompting, the framework enables more interpretable, evidence-grounded, and clinically reliable prognosis. Preliminary results on real-world cases demonstrate promising effectiveness and clinical alignment, highlighting the potential of RAG4Outcome for AI-assisted infection management and postoperative decision support.

Social interactions dominate our perceptions of the world and shape our daily behavior by attaching social meaning to acts as simple and spontaneous as gestures, facial expressions, voice, and speech. People mimic and otherwise respond to each other's postures, facial expressions, mannerisms, and other verbal and nonverbal behavior, and form appraisals or evaluations in the process. Yet, no publicly-available dataset includes multimodal recordings and self-report measures of multiple persons in social interaction. Dyadic recordings and annotation are lacking. We present a new data corpus of multimodal dyadic interaction (45 dyads, 90 persons) that includes synchronized multi-modality behavior (2D face video, 3D face geometry, thermal spectrum dynamics, voice and speech behavior, physiology (PPG, EDA, heart-rate, blood pressure, and respiration), and self-reported affect of all participants in a communicative interaction scenario. Two types of dyads are included: persons with shared past history and strangers. Annotations include social signals, agreement, disagreement, and neutral stance. With a potent emotion induction, these multimodal data will enable novel modeling of multimodal interpersonal behavior. We present extensive experiments to evaluate multimodal dyadic communication of dyads with and without interpersonal history, and their affect. This new database will make multimodal modeling of social interaction never possible before. The dataset includes 20TB of multimodal data to share with the research community.

Understanding social dominance in animal behavior is critical for neuroscience and behavioral studies. In this work, we explore the capability of Multimodal Large Language Models(MLLMs) to analyze raw behavioral video of mice and predict their dominance hierarchy. We introduce MTT-Bench, a novel benchmark comprising annotated videos of pairwise mouse interactions for Mouse Tube Test analysis. Building on existing MLLM architectures, we fine-tune these models to perform zero-shot inference on unseen behavioral sequences, predicting social dominance without explicit labels during testing. Our framework demonstrates promising results, showing high agreement with tube test rankings. This work opens a new direction for applying foundation models to ethology and social behavior analysis, without the need to design domain-specific models.

Multimodal Large Language Models (MLLMs) have shown promising potential in diverse understanding tasks, e.g., image and video analysis, math and physics olympiads. However, they remain blank and unexplored for Small Object Understanding (SOU) tasks. To fill this gap, we introduce SOUBench, the first and comprehensive benchmark for exploring the small objects understanding capability of existing MLLMs. Specifically, we first design an effective and automatic visual question-answer generation strategy, constructing a new SOU-VQA evaluation dataset, with 18,204 VQA pairs, six relevant sub-tasks, and three dominant scenarios (i.e., Driving, Aerial, and Underwater). Then, we conduct a comprehensive evaluation on 15 state-of-the-art MLLMs and reveal their weak capabilities in small object understanding. Furthermore, we develop SOU-Train, a multimodal training dataset with 11,226 VQA pairs, to improve the SOU capabilities of MLLMs. Through supervising fine-tuning of the latest MLLM, we demonstrate that SOU-Train can effectively enhance the latest MLLM's ability to understand small objects. Comprehensive experimental results demonstrate that, the proposed SOUBench, along with the SOU-VQA and SOU-Train datasets, provides a crucial empirical foundation to the community for further developing models with enhanced small object understanding capabilities. Datasets and Code: https://github.com/Hanfj-X/SOU.

We define and investigate source-modality monitoring -- the ability of multimodal models to track and communicate the input source from which pieces of information originate. We consider source-modality monitoring as an instance of the more general binding problem, and evaluate the extent to which models exploit syntactic vs. semantic signals in order to bind words like image in a user-provided prompt to specific components of their input and context (i.e., actual images). Across experiments spanning 11 vision-language models (VLMs) performing target-modality information retrieval tasks, we find that both syntactic and semantic signals play an important role, but that the latter tend to outweigh the former in cases when modalities are highly distinct distributionally. We discuss the implications of these findings for model robustness, and in the context of increasingly multimodal agentic systems.

We present DM$^3$-Nav, a fully decentralized multi-agent semantic navigation system supporting multimodal open-vocabulary goal specification and multi-object missions. In our setting, decentralization implies operation without a central coordinator, global map aggregation, or shared global state at runtime. Robots operate autonomously and coordinate through ad-hoc pairwise communication, exchanging local maps, goal status, and navigation intent without synchronization. An implicit task allocation mechanism combining intent broadcasting and distance-weighted frontier selection reduces redundant exploration while preserving decentralized operation. Evaluations on HM3DSem scenes using the HM3Dv0.2 and GOAT-Bench datasets demonstrate that DM$^3$-Nav matches or exceeds centralized and shared-map baselines while eliminating single points of failure inherent in centralized architectures. Finally, we validate our approach in a real-world office environment using two mobile robots, demonstrating successful deployment relying entirely on onboard sensing and computation. A video of our real-world experiments is available online: https://drive.google.com/file/d/1QiUSCn5rIvtuTUqtuXLPgmt6S8x9-MCZ/view?usp=drive_link

The rapid proliferation of Vision-Language Models (VLMs) is often framed as enabling unified multimodal knowledge discovery but rests on an under-examined assumption: that current VLMs faithfully synthesise multimodal data. We argue they often do not, and this gap reflects a trustworthiness problem in the dominant Vision Encoder-Projector-LLM paradigm. Rather than extracting grounded knowledge from visual inputs, state-of-the-art models frequently exhibit functional blindness, i.e., exploiting strong language priors to bypass severe visual representation bottlenecks. In this work, we challenge the conventional methodology of multimodal evaluation, which relies on data ablation or new dataset creation and therefore conflates dataset biases with architectural incapacity. We propose an information-theoretic departure: the Modality Translation Protocol, designed to quantify what we call the Expense of Seeing. By translating semantic payloads rather than ablating them, we formulate three novel metrics -- the Toll (ToS), Curse (CoS), and Fallacy (FoS) of Seeing -- culminating in the Semantic Sufficiency Criterion (SSC). Furthermore, we hypothesise a Divergence Law of Multimodal Scaling: as the underlying language engines scale to unprecedented reasoning capabilities, the penalty of the visual knowledge bottleneck may increase rather than diminish. We argue the community should move beyond "multimodal gain" as a primary evaluation target. By elevating the SSC from a passive diagnostic constraint to an active architectural blueprint, we provide a foundation for guiding the next generation of AI systems toward genuine multimodal reasoning.

Vision-Language Models (VLMs) are frequently undermined by object hallucination, generating content that contradicts visual reality, due to an over-reliance on linguistic priors. We introduce Positive-and-Negative Decoding (PND), a training-free inference framework that intervenes directly in the decoding process to enforce visual fidelity. PND is motivated by our finding of an attention imbalance in VLMs, where visual features are under-weighted. Our framework introduces a dual-path contrast: a positive path that amplifies visual evidence and a negative path that constructs counterfactuals to penalize prior-dominant generation. By contrasting outputs from both paths during decoding, PND steers generation toward visually grounded results. Experiments on POPE, MME, and CHAIR demonstrate state-of-the-art performance without retraining.

Real-time multimodal agents transport raw audio and screenshots using networking stacks designed for human receivers, which optimize for perceptual fidelity and smooth playout. Yet agent models act as event-driven processors with no inherent sense of physical time, consuming task-relevant semantics rather than reconstructing signals in real time. This fundamental difference shifts the transport goal from the technical problem of signal fidelity (Shannon-Weaver Level A) to the semantic problem of meaning preservation (Level B). This mismatch imposes significant overhead. In visual pipelines, screenshot upload accounts for over 60% of end-to-end action latency on constrained uplinks, and in voice pipelines, conventional transport carries massive redundancy, sending 43-64x more data than needed to maintain task accuracy. We present Sema, a semantic transport system that combines discrete audio tokenizers with a hybrid screen representation (lossless accessibility-tree or OCR text, plus compact visual tokens) and bursty token delivery that eliminates jitter buffers. In simulations under emulated WAN conditions, Sema reduces uplink bandwidth by 64x for audio and 130-210x for screenshots while preserving task accuracy within 0.7 percentage points of the raw baseline.

Multimodal Entity Linking (MEL) is a fundamental task in data management that maps ambiguous mentions with diverse modalities to the multimodal entities in a knowledge base. However, most existing MEL approaches primarily focus on optimizing instance-centric features and evidence, leaving broader forms of evidence and their intricate interdependencies insufficiently explored. Motivated by the observation that human expert decision-making process relies on multi-perspective judgment, in this work, we propose MSR-MEL, a Multi-perspective Evidence Synthesis and Reasoning framework with Large Language Models (LLMs) for unsupervised MEL. Specifically, we adopt a two-stage framework: (1) Offline Multi-Perspective Evidence Synthesis constructs a comprehensive set of evidence. This includes instance-centric evidence capturing the instance-centric multimodal information of mentions and entities, group-level evidence that aggregates neighborhood information, lexical evidence based on string overlap ratio, and statistical evidence based on simple summary statistics. A core contribution of our framework is the synthesis of group-level evidence, which effectively aggregates vital neighborhood information by graph. We first construct LLM-enhanced contextualized graphs. Subsequently, different modalities are jointly aligned through an asymmetric teacher-student graph neural network. (2) Online Multi-Perspective Evidence Reasoning leverages the power of LLM as a reasoning module to analyze the correlation and semantics of the multi-perspective evidence to induce an effective ranking strategy for accurate entity linking without supervision. Extensive experiments on widely used MEL benchmarks demonstrate that MSR-MEL consistently outperforms state-of-the-art unsupervised methods. The source code of this paper was available at: https://anonymous.4open.science/r/MSR-MEL-C21E/.

With the popularity of the large language models (LLMs), text steganography has achieved remarkable performance. However, existing methods still have some issues: (1) For the white-box paradigm, this steganography behavior is prone to exposure due to sharing the off-the-shelf language model between Alice and Bob.(2) For the black-box paradigm, these methods lack flexibility and practicality since Alice and Bob should share the fixed codebook while sharing a specific extracting prompt for each steganographic sentence. In order to improve the security and practicality, we introduce a black-box text steganography with a dynamic codebook and multimodal large language model. Specifically, we first construct a dynamic codebook via some shared session configuration and a multimodal large language model. Then an encrypted steganographic mapping is designed to embed secret messages during the steganographic caption generation. Furthermore, we introduce a feedback optimization mechanism based on reject sampling to ensure accurate extraction of secret messages. Experimental results show that the proposed method outperforms existing white-box text steganography methods in terms of embedding capacity and text quality. Meanwhile, the proposed method has achieved better practicality and flexibility than the existing black-box paradigm in some popular online social networks.

Audio carries richer information than text, including emotion, speaker traits, and environmental context, while also enabling lower-latency processing compared to speech-to-text pipelines. However, recent multimodal information retrieval research has predominantly focused on images, largely overlooking audio, especially in the setting of interleaved audio-text contextual retrieval. In this work, we introduce the Audio-Text Interleaved contextual Retrieval (ATIR) task, where queries can alternate between audio and text modalities. We construct an ATIR benchmark by integrating several Automatic Speech Recognition (ASR), QA, and retrieval datasets, ultimately unifying four types of contextual retrieval tasks. This benchmark substantially addresses the limitations of existing audio retrieval datasets in semantic retrieval. To study this task, we evaluate several off-the-shelf retrievers and train our ATIR model based on a Multimodal Large Language Model (MLLM). We further introduce a novel token compression mechanism that is orthogonal to existing compression methods, thereby alleviating the issue of excessive audio tokens in MLLM-based ATIR models. Experimental results demonstrate that our ATIR model achieves substantial improvements over strong baselines.

Virtual cell modeling predicts molecular state changes under genetic perturbations in silico, which is essential for biological mechanism studies. However, existing approaches suffer from unconstrained reasoning, uninterpretable predictions, and retrieval signals that are weakly aligned with regulatory topology. To address these limitations, we propose AROMA, an Augmented Reasoning Over a Multimodal Architecture for virtual cell genetic perturbation modeling. AROMA integrates textual evidence, graph-topology information, and protein sequence features to model perturbation-target dependencies, and is trained with a two-stage optimization strategy to yield predictions that are both accurate and interpretable. We also construct two knowledge graphs and a perturbation reasoning dataset, PerturbReason, containing more than 498k samples, as reusable resources for the virtual cell domain. Experiments show that AROMA outperforms existing methods across multiple cell lines, and remains robust under zero-shot evaluation on an unseen cell line, as well as in knowledge-sparse, long-tail scenarios. Overall, AROMA demonstrates that combining knowledge-driven multimodal modeling with evidence retrieval provides a promising pathway toward more reliable and interpretable virtual cell perturbation prediction. Model weights are available at https://huggingface.co/blazerye/AROMA. Code is available at https://github.com/blazerye/AROMA.

Multimodal Large Language Models (MLLMs) effectively integrate text and audio to interpret context in complex interactive dialogues. However, the internal mechanisms by which heterogeneous modalities influence model behavior remain opaque. While Shapley Values (SV) provide a robust, model-agnostic framework for local explainability in text-based NLP, their extension to multimodal data is hindered by cross-channel dependencies, intricate dialogue structures, and the prohibitive computational complexity of dense audio representations. In this work, we formalize a multimodal extension of the Shapley Value framework, treating discrete text tokens and aligned audio segments as cooperative features. To ensure computational feasibility, we deploy a suite of efficient estimation strategies: exact SV computation for low-dimensional inputs and sampling-based approximations - including Monte Carlo permutations and stratified sampling with Neyman-optimal allocation - to minimize variance under constrained computational budgets. To resolve the granularity mismatch between modalities, we propose Spectrogram-Guided Phonetic Alignment (SGPA), a novel preprocessing method that maps high-frequency audio streams to interpretable, word-aligned segments. Our contribution is twofold: first, we provide an open-source, model-agnostic Python package and a companion GUI for the computation and interactive visualization of multimodal attributions. Second, we evaluate our framework using curated subsets of the VoiceBench and Infinity Instruct datasets across diverse multilingual scenarios. Our experimental results reveal that input modality is a primary driver of attribution volatility and demonstrate that standard syntactic importance proxies often fail to predict model attention in multimodal, cross-lingual contexts.

Goal-conditioned navigation models for ground robots trained using supervised learning show promising zero-shot transfer, but their collision-avoidance capability nevertheless degrades under distribution shift, i.e. environmental, robot or sensor configuration changes. We propose ViLiNT a multimodal, attention-based policy for goal navigation, trained on heterogeneous data from multiple platforms and environments, which improves robustness with two key features. First, we fuse RGB images, 3D LiDAR point clouds, a goal embedding and a robot's embodiment descriptor with a transformer architecture to capture complementary geometry and appearance cues. The transformer's output is used to condition a diffusion model that generates navigable trajectories. Second, using automatically generated offline labels, we train a path clearance prediction head for scoring and ranking trajectories produced by the diffusion model. The diffusion conditioning as well as the trajectory ranking head depend on a robot's embodiment token that allows our model to generate and select trajectories with respect to the robot's dimensions. Across three simulated environments, ViLiNT improves Success Rate on average by 166% over equivalent state-of-the-art vision-only baseline (NoMaD). This increase in performance is confirmed through real-world deployments of a rover navigating in obstacle fields. These results highlight that combining multimodal fusion with our collision prediction mechanism leads to improved off-road navigation robustness.

Agentic multimodal models have garnered significant attention for their ability to leverage external tools to tackle complex tasks. However, it is observed that such agents often meet premature interaction collapse, caused by two primary reasons: 1) the terminal reward often appending on the last token prevents the advantage from distinguishing trajectories with exploratory behavior; 2) excessively redundant context hinders the agent from absorbing useful feedback. To address these issues, we propose the Deepening Reasoning MMSearchAgent, the framework leverages the structural proximity to derive advantage signals from the whole rollout trajectories in an entire batch, such that trajectories of different lengths are further encouraged to be generated, even when containing the same correct answer. Additionally, differentiated gaussian rewards are employed to dynamically calibrate interaction tolerance, thereby ensuring information reliability and reduce redundancy. To support multi-turn interaction training, we have constructed a multi-step deep-reasoning dataset including 3602 high-quality QA pair with at least 3 reasonning steps. Extensive experiments demonstrate that our method achieves state-of-the-art performance, outperforming the MMSearch-R1 by 8.4$\%$ on FVQA-test.

Despite remarkable progress toward general-purpose video models, a critical question remains unanswered: how far are these models from achieving true multimodal reasoning? Existing benchmarks fail to address this question rigorously, as they remain constrained by straightforward task designs and fragmented evaluation metrics that neglect complex multimodal reasoning. To bridge this gap, we introduce CLVG-Bench, an evaluation framework designed to probe video models' zero-shot reasoning capabilities via Context Learning in Video Generation. CLVG-Bench comprises more than 1,000 high-quality, manually annotated metadata across 6 categories and 47 subcategories, covering complex scenarios including physical simulation, logical reasoning, and interactive contexts. To enable rigorous and scalable assessment, we further propose an Adaptive Video Evaluator (AVE) that aligns with human expert perception using minimal annotations, delivering interpretable textual feedback across diverse video context tasks. Extensive experiments reveal a striking answer to our central question: while state-of-the-art (SOTA) video models, such as Seedance 2.0, demonstrate competence on certain understanding and reasoning subtasks, they fall substantially short with logically grounded and interactive generation tasks (achieving success rates <25% and ~0%, respectively), exposing multimodal reasoning and physical grounding as critical bottlenecks. By systematically quantifying these limitations, the proposed method provides actionable feedbacks and a clear roadmap toward truly robust, general-purpose video models. CLVG-Bench and code are released here.

This paper presents the first exploration of text-to-image diffusion models for zero-shot sketch-based 3D shape retrieval (ZS-SBSR). Existing sketch-based 3D shape retrieval methods struggle in zero-shot settings due to the absence of category supervision and the extreme sparsity of sketch inputs. Our key insight is that large-scale pretrained diffusion models inherently exhibit open-vocabulary capability and strong shape bias, making them well suited for zero-shot visual retrieval. We leverage a frozen Stable Diffusion backbone to extract and aggregate discriminative representations from intermediate U-Net layers for both sketches and rendered 3D views. Diffusion models struggle with sketches due to their extreme abstraction and sparsity, compounded by a significant domain gap from natural images. To address this limitation without costly retraining, we introduce a multimodal feature-enhanced strategy that conditions the frozen diffusion backbone with complementary visual and textual cues from CLIP, explicitly enhancing the ability of semantic context capture and concentrating on sketch contours. Specifically, we inject global and local visual features derived from a pretrained CLIP visual encoder, and incorporate enriched textual guidance by combining learnable soft prompts with hard textual descriptions generated by BLIP. Furthermore, we employ the Circle-T loss to dynamically strengthen positive-pair attraction once negative samples are sufficiently separated, thereby adapting to sketch noise and enabling more effective sketch-3D alignment. Extensive experiments on two public benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches in ZS-SBSR.

Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the feasibility of backdoors in MLLMs via fine-tuning data poisoning to manipulate inference, the underlying mechanisms of backdoor attacks remain opaque, complicating the understanding and mitigation. To bridge this gap, we propose ProjLens, an interpretability framework designed to demystify MLLMs backdoors. We first establish that normal downstream task alignment--even when restricted to projector fine--tuning--introduces vulnerability to backdoor injection, whose activation mechanism is different from that observed in text-only LLMs. Through extensive experiments across four backdoor variants, we uncover:(1) Low-Rank Structure: Backdoor injection updates appear overall full-rank and lack dedicated ``trigger neurons'', but the backdoor-critical parameters are encoded within a low-rank subspace of the projector;(2) Activation Mechanism: Both clean and poisoned embedding undergoes a semantic shift toward a shared direction aligned with the backdoor target, but the shifting magnitude scales linearly with the input norm, resulting in the distinct backdoor activation on poisoned samples. Our code is available at: https://anonymous.4open.science/r/ProjLens-8FD7

Multimodal large language models (MLLMs) have achieved impressive performance on visual perception and reasoning tasks with RGB imagery, yet they remain fragile under common degradations, such as fog, blur, or low-light conditions. Infrared (IR) imaging, a well-established complement to RGB, offers inherent robustness in these conditions, but its integration into MLLMs remains underexplored. To bridge this gap, we propose DUALVISION, a lightweight fusion module that efficiently incorporates IR-RGB information into MLLMs via patch-level localized cross-attention. To support training and evaluation and to facilitate future research, we also introduce DV-204K, a dataset of ~25K publicly available aligned IR-RGB image pairs with 204K modality-specific QA annotations, and DV-500, a benchmark of 500 IR-RGB image pairs with 500 QA pairs designed for evaluating cross-modal reasoning. Leveraging these datasets, we benchmark both open- and closed-source MLLMs and demonstrate that DUALVISION delivers strong empirical performance under a wide range of visual degradations. Our code and dataset are available at https://abrarmajeedi.github.io/dualvision.

Mathematical problem solving remains a challenging test of reasoning for large language and multimodal models, yet existing benchmarks are limited in size, language coverage, and task diversity. We introduce MathNet, a high-quality, large-scale, multimodal, and multilingual dataset of Olympiad-level math problems together with a benchmark for evaluating mathematical reasoning in generative models and mathematical retrieval in embedding-based systems. MathNet spans 47 countries, 17 languages, and two decades of competitions, comprising 30,676 expert-authored problems with solutions across diverse domains. In addition to the core dataset, we construct a retrieval benchmark consisting of mathematically equivalent and structurally similar problem pairs curated by human experts. MathNet supports three tasks: (i) Problem Solving, (ii) Math-Aware Retrieval, and (iii) Retrieval-Augmented Problem Solving. Experimental results show that even state-of-the-art reasoning models (78.4% for Gemini-3.1-Pro and 69.3% for GPT-5) remain challenged, while embedding models struggle to retrieve equivalent problems. We further show that retrieval-augmented generation performance is highly sensitive to retrieval quality; for example, DeepSeek-V3.2-Speciale achieves gains of up to 12%, obtaining the highest scores on the benchmark. MathNet provides the largest high-quality Olympiad dataset together with the first benchmark for evaluating mathematical problem retrieval, and we publicly release both the dataset and benchmark at https://mathnet.mit.edu.

Multimodal affective computing aims to predict humans' sentiment, emotion, intention, and opinion using language, acoustic, and visual modalities. However, current models often learn spurious correlations that harm generalization under distribution shifts or noisy modalities. To address this, we propose a causal modality-invariant representation (CmIR) learning framework for robust multimodal learning. At its core, we introduce a theoretically grounded disentanglement method that separates each modality into causal invariant representation' and environment-specific spurious representation' from a causal inference perspective. CmIR ensures that the learned invariant representations retain stable predictive relationships with labels across different environments while preserving sufficient information from the raw inputs via invariance constraint, mutual information constraint, and reconstruction constraint. Experiments across multiple multimodal benchmarks demonstrate that CmIR achieves state-of-the-art performance. CmIR particularly excels on out-of-distribution data and noisy data, confirming its robustness and generalizability.

Change visual question answering (Change VQA) addresses the problem of answering natural-language questions about semantic changes between bi-temporal remote sensing (RS) images. Although vision-language models (VLMs) have recently been studied for temporal RS image understanding, Change VQA remains underexplored in the context of modern multimodal models. In this letter, we revisit the CDVQA benchmark using recent Qwen models under a unified low-rank adaptation (LoRA) setting. We compare Qwen3-VL, which follows a structured vision-language pipeline with multi-depth visual conditioning and a full-attention decoder, with Qwen3.5, a native multimodal model that combines a single-stage alignment with a hybrid decoder backbone. Experimental results on the official CDVQA test splits show that recent VLMs improve over earlier specialized baselines. They further show that performance does not scale monotonically with model size, and that native multimodal models are more effective than structured vision-language pipelines for this task. These findings indicate that tightly integrated multimodal backbones contribute more to performance than scale or explicit multi-depth visual conditioning for language-driven semantic change reasoning in RS imagery.

Audio-text retrieval systems based on Contrastive Language-Audio Pretraining (CLAP) achieve strong performance on traditional benchmarks; however, these benchmarks rely on caption-style queries that differ substantially from real-world search behavior, limiting their assessment of practical retrieval robustness. We present Omni-Embed-Audio (OEA), a retrieval-oriented encoder leveraging multimodal LLMs with native audio understanding. To systematically evaluate robustness beyond caption-style queries, we introduce User-Intent Queries (UIQs) - five formulations reflecting natural search behaviors: questions, commands, keyword tags, paraphrases, and exclusion-based negative queries. For negative queries, we develop a hard negative mining pipeline and propose discrimination metrics (HNSR, TFR) assessing models' ability to suppress acoustically similar distractors. Experiments on AudioCaps, Clotho, and MECAT show that OEA achieves comparable text-to-audio retrieval performance to state-of-the-art M2D-CLAP, while demonstrating clear advantages in two critical areas: (1) dominant text-to-text retrieval (+22% relative improvement), and (2) substantially superior hard negative discrimination (+4.3%p HNSR@10, +34.7% relative TFR@10), revealing that LLM backbones provide superior semantic understanding of complex queries.

Mixture-of-Experts Multimodal Large Language Models (MoE MLLMs) suffer from a significant efficiency bottleneck during Expert Parallelism (EP) inference due to the straggler effect. This issue is worsened in the multimodal context, as existing token-count-based load balancing methods fail to address two unique challenges: (1) Information Heterogeneity, where numerous redundant visual tokens are treated equally to semantically critical ones, and (2) Modality Dynamics, where varying visual to text ratios across tasks lead to resource misallocation. To address these challenges, we propose MACS (Modality-Aware Capacity Scaling), a training-free inference framework. Specifically, MACS introduces an Entropy-Weighted Load mechanism to quantify the semantic value of visual tokens, addressing information heterogeneity. Additionally, the Dynamic Modality-Adaptive Capacity mechanism allocates expert resources based on the real-time modal composition of the input. Extensive experiments demonstrate that MACS significantly outperforms existing methods on various multimodal benchmarks, providing a novel and robust solution for the efficient deployment of MoE MLLMs in EP inference.

Multimodal Retrieval-Augmented Generation (RAG) has emerged as an effective paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing multimodal RAG systems predominantly rely on coarse-grained page-level retrieval, which fails to capture fine-grained semantic and layout structures in visually rich documents, thereby compromising retrieval accuracy and leading to redundant context in downstream tasks. To address these issues, we propose Layout-oriented Fine-grained Retrieval-Augmented Generation (LFRAG), a novel framework that advances multimodal RAG from page-level to block-level retrieval. We perform layout segmentation to construct semantically coherent fine-grained retrieval units and design a semantic-layout fusion encoder that integrates local semantics with global context via cross-attention. With block-level late interaction retrieval, LFRAG enables precise query-content alignment and reduces irrelevant content for downstream generation. To enable rigorous evaluation, we construct LFDocQA, a large-scale benchmark with block-level annotations spanning diverse document types, designed to assess both multimodal document retrieval and question answering with greater granularity than existing datasets. Extensive experiments on LFDocQA demonstrate that LFRAG achieves state-of-the-art performance on retrieval tasks, outperforms the best baseline by 7.20% in answer accuracy, and reduces token consumption by 73.07% in generation tasks, confirming LFRAG as an accurate and efficient framework for multimodal RAG over visually rich documents. Our code and datasets will be released soon.

Large pre-trained language models are increasingly adapted to downstream tasks using parameter-efficient fine-tuning (PEFT), but existing PEFT methods are typically deterministic and unimodal, making them poorly suited for low-resource multimodal settings where predictive uncertainty and cross-modal reliability both matter. We introduce CALIBER (Context-Aware Low-rank Inference with Bayesian Embedding Regularization), a multimodal uncertainty-aware PEFT framework for audio-text learning. CALIBER extends Bayesian low-rank adaptation by conditioning the variational posterior in the adapter space on per-layer, token-level text-audio cross-attention. Specifically, text-derived low-rank features attend to frame-level audio embeddings to produce localized acoustic context, which then modulates the mean and variance of a compact stochastic latent matrix within the rank-$r$ adapter space. This design treats audio not only as an additional feature source, but as a contextual reliability signal that shapes both adaptation and confidence. By confining stochasticity to a low-dimensional latent component, CALIBER retains the computational efficiency and scalability of PEFT while enabling heteroscedastic multimodal uncertainty estimation. Experimental results across diverse text and audio backbones show that CALIBER consistently matches or improves upon text-only Bayesian PEFT and conventional multimodal transfer-learning baselines, with token-level cross-attention yielding the most consistent gains. Our findings demonstrate that localized cross-modal conditioning is an effective and lightweight mechanism for uncertainty-aware multimodal adaptation.

We introduce CoCo-LoRA, a multimodal, uncertainty-aware parameter-efficient fine-tuning method for text prediction tasks accompanied by audio context. Existing PEFT approaches such as LoRA are efficient but typically deterministic, while recent Bayesian low-rank adapters model uncertainty in a lightweight way yet remain largely unimodal and condition uncertainty primarily on internal text features. This leaves them poorly equipped to reflect uncertainty driven by external acoustic factors such as background noise, channel variability, or speaking style, which can materially affect reliability in speech-centered applications. CoCo-LoRA addresses this gap by conditioning a contextual variational posterior in the low-rank space on both local text-derived adapter features and an audio-derived context signal. A pooled audio embedding is projected once into a shared context space and then adapted through lightweight layer-wise heads, enabling global-to-local, depth-specific modulation of the adapter uncertainty and update without high-dimensional multimodal fusion. Stochasticity is confined to a compact latent component in the rank space, preserving PEFT scalability while producing audio-sensitive, heteroscedastic uncertainty. Based on our evaluations across diverse tasks and backbone combinations, CoCo-LoRA consistently matches or outperforms text-only PEFT and conventional feature-fusion transfer baselines, particularly on high-coverage labels where reliable adaptation is critical. The results indicate that using audio as a contextual uncertainty signal, rather than as a fused feature stream, provides a robust and parameter-efficient alternative for multimodal low-resource prediction.

UAV vision-language navigation (VLN) requires an agent to navigate complex 3D environments from an egocentric perspective while following ambiguous multi-step instructions over long horizons. Existing zero-shot methods remain limited, as they often rely on large base models, generic prompts, and loosely coordinated modules. In this work, we propose FineCog-Nav, a top-down framework inspired by human cognition that organizes navigation into fine-grained modules for language processing, perception, attention, memory, imagination, reasoning, and decision-making. Each module is driven by a moderate-sized foundation model with role-specific prompts and structured input-output protocols, enabling effective collaboration and improved interpretability. To support fine-grained evaluation, we construct AerialVLN-Fine, a curated benchmark of 300 trajectories derived from AerialVLN, with sentence-level instruction-trajectory alignment and refined instructions containing explicit visual endpoints and landmark references. Experiments show that FineCog-Nav consistently outperforms zero-shot baselines in instruction adherence, long-horizon planning, and generalization to unseen environments. These results suggest the effectiveness of fine-grained cognitive modularization for zero-shot aerial navigation. Project page: https://smartdianlab.github.io/projects-FineCogNav.

Autonomous robots operating in natural karstic caves face perception and navigation challenges that are qualitatively distinct from those encountered in mines or tunnels: irregular geometry, reflective wet surfaces, near-zero ambient light, and complex branching passages. Yet publicly available datasets targeting this environment remain scarce and offer limited sensing modalities and environmental diversity. We present CAVERS, a multimodal dataset acquired in two structurally distinct rooms of Cueva de la Victoria, Málaga, Spain, comprising 24 sequences totaling approximately 335 GB of recorded data. The sensor suite combines an Intel RealSense D435i RGB-D-I camera, an Optris PI640i near-IR thermal camera, and a Velodyne VLP-16 LiDAR, operated both handheld and mounted on a wheeled rover under full darkness and artificial illumination. For most of the sequences, mm-accurate 6-DoF ground truth pose and velocity at 120 Hz are provided by an Optirack motion capture system installed directly inside the cave. We benchmark seven state-of-the-art SLAM and odometry algorithms spanning visual, visual-inertial, thermal-inertial, and LiDAR-based pipelines, as well as a 3D reconstruction pipeline, demonstrating the dataset's usability. %The dataset and all supplementary material are publicly available at: https://github.com/spaceuma/cavers.

Tool learning with foundation models aims to endow AI systems with the ability to invoke external resources -- such as APIs, computational utilities, and specialized models -- to solve complex tasks beyond the reach of standalone language generation. While recent advances in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have expanded their reasoning and perception capabilities, existing tool-use methods are predominantly limited to text-only inputs and closed-world settings. Consequently, they struggle to interpret multimodal user instructions and cannot generalize to tools unseen during training. In this work, we introduce RaTA-Tool, a novel framework for open-world multimodal tool selection. Rather than learning direct mappings from user queries to fixed tool identifiers, our approach enables an MLLM to convert a multimodal query into a structured task description and subsequently retrieve the most appropriate tool by matching this representation against semantically rich, machine-readable tool descriptions. This retrieval-based formulation naturally supports extensibility to new tools without retraining. To further improve alignment between task descriptions and tool selection, we incorporate a preference-based optimization stage using Direct Preference Optimization (DPO). To support research in this setting, we also introduce the first dataset for open-world multimodal tool use, featuring standardized tool descriptions derived from Hugging Face model cards. Extensive experiments demonstrate that our approach significantly improves tool-selection performance, particularly in open-world, multimodal scenarios.

Composed Image Retrieval (CIR) aims to retrieve target images by integrating a reference image with a corresponding modification text. CIR requires jointly considering the explicit semantics specified in the query and the implicit semantics embedded within its bi-modal composition. Recent training-free Zero-Shot CIR (ZS-CIR) methods leverage Multimodal Large Language Models (MLLMs) to generate detailed target descriptions, converting the implicit information into explicit textual expressions. However, these methods rely heavily on the textual modality and fail to capture the fuzzy retrieval nature that requires considering diverse combinations of candidates. This leads to reduced diversity and accuracy in retrieval results. To address this limitation, we propose a novel training-free method, Geodesic Mixup-based Implicit semantic eXpansion and Explicit semantic Re-ranking for ZS-CIR (G-MIXER). G-MIXER constructs composed query features that reflect the implicit semantics of reference image-text pairs through geodesic mixup over a range of mixup ratios, and builds a diverse candidate set. The generated candidates are then re-ranked using explicit semantics derived from MLLMs, improving both retrieval diversity and accuracy. Our proposed G-MIXER achieves state-of-the-art performance across multiple ZS-CIR benchmarks, effectively handling both implicit and explicit semantics without additional training. Our code will be available at https://github.com/maya0395/gmixer.

Training multimodal large language models (MLLMs) for video understanding requires large-scale annotated data spanning diverse tasks such as object counting, question answering, and segmentation. However, collecting and annotating multimodal video data in real-world is costly, slow, and inherently limited in diversity and coverage. To address this challenge, we propose~\textbf{SynMulti} dataset, along with a unified synthetic data generation pipeline capable of automatically producing unlimited multimodal video data with rich and diverse supervision. Our framework supports multiple task formats within a single pipeline, enabling scalable and consistent data creation across tasks. To further enhance reasoning ability, we introduce a VQA-based fine-tuning strategy that trains models to answer structured questions about visual content rather than relying solely on captions or simple instructions. This formulation encourages deeper visual grounding and reasoning. We evaluate our approach in three challenging tasks: video object counting, video-based visual question answering, and video object segmentation. Experimental results demonstrate that models trained predominantly on synthetic data generalize effectively to real-world datasets, often outperforming traditionally trained counterparts. Our findings highlight the potential of unified synthetic data pipelines as a scalable alternative to expensive real-world annotation for multimodal video understanding.

Multi-robot systems hold significant promise for social environments such as homes and hospitals, yet existing multi-robot systems often treat robots as functionally interchangeable, overlooking how distinct agent identities shape user perception and how such individuality changes the coordination requirements of multi-robot interaction. To address this, we introduce M2HRI, a multimodal multi-agent framework that models each robot as an identity-bearing agent through personality and long-term memory, together with a contextualized coordination mechanism that regulates agent participation. In a controlled user study (n = 105) in a multi-agent human-robot interaction (HRI) scenario, we found that most personality contrasts were distinguishable and consistently expressed. Long-term memory improved preference awareness and interaction naturalness, while contextualized coordination improved conversational flow, response appropriateness, and overlap avoidance. Together, these findings show that agent individuality and contextualized participation coordination play complementary roles in supporting coherent and socially appropriate multi-agent HRI. Project website available at https://project-m2hri.github.io/.