Modality-Specific Encoders

Follow this topic Ask about this topic

Momentum

0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 32

Sep 29, 2026cs.CV

OmniRoute: Mapping Temporal Semantic Evidence to Audio-Visual Token Budgets for Efficient Omnimodal Large Language Models

Omnimodal large language models (Omni-LLMs) encode audio and visual streams into temporally interleaved token sequences for multimodal reasoning. However, processing long audio-visual token sequences incurs substantial prefill costs. Existing compression methods have made progress, but often overlook temporal changes in audio-visual semantic relevance. Motivated by temporal variation and local continuity, we propose OmniRoute, a training-free, two-stage compression framework. First, Temporal Evidence-Guided Budgeting (TEGB) derives chunk-wise modality preferences and initial leading-modality budgets from semantic relevance and local content variation. Second, Budget-Constrained Semantic Compression (BCSC) compresses the leading modality and then calibrates the follower's retention target using the actual retained fraction. For video, it combines spatiotemporal grouping with query-guided selection; for audio, it selects tokens based on encoder attention and query relevance, then merges residual tokens into context anchors under visual guidance. Experiments on four representative benchmarks demonstrate a better trade-off between inference efficiency and performance than competitive baselines. The code and interface will be released to facilitate further research.

Yuchen Deng, Zidang Cai, Feidiao Yang +4

Shenzhen International Graduate School, Tsinghua University, China · Pengcheng Laboratory, China

Omni-Modal Audio-Visual Reasoning Modality-Specific Encoders Multimodal Large Language Models Modalities Semantic Mapping

Aug 11, 2026cs.CV

Towards Unified Dynamic Face Landmark Detection

Although advancements in face landmark detection (FLD) methods continue to push performance boundaries, they overlook two major functional limitations: (1) different network parameters need to be trained independently for each $N$-point'' benchmark dataset, and (2) a model trained on an

N

-point'' dataset reliably outputs only the

N

landmarks. In our work, we first conceptualize Face Part-Anchored Landmark Positions (FPALPs), wherein each landmark is treated as a progression value between zero (start) and one (end) along a face part's contour. Every landmark can be expressed in the FPALP format, irrespective of its source dataset, hence unlocking the ability to unify all

$N$-point'' datasets into a single dataset. Secondly, we represent each landmark with an FPALP-based query, refine it progressively with a cross-modality decoder, and predict its coordinates based on the final representation. Our approach, called Unified Dynamic FLD, embodies these two design choices and streamlines the landmark detection pipeline by enabling (1) a single model to learn on any number of

N

-point'' datasets, and (2) yield any number of specific landmark predictions by loading the designated landmark queries at runtime. Extensive experiments on multiple benchmark datasets show that our method delivers these benefits while remaining competitive with, and in several cases outperforming existing state-of-the-art methods.

Sebastian Regalado, Varshanth R. Rao, Ruowei Jiang +2

University of Toronto · 2ModiFace · †Work completed while employed at ModiFace +1

One-Shot Medical Landmark Detection Modality-Specific Encoders Benchmark Datasets Queries

Jul 28, 2026cs.CV

MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities

Any-to-any models predict any modality from any combination of others within a single network, a formulation used in multimodal vision and vision-language models, and increasingly in scientific domains such as ecology and astronomy. Existing any-to-any models are typically trained from scratch using encoder-decoder or diffusion architectures, impacting their performance and preventing them from using strong pre-trained decoder-only models as a prior. In this work, we investigate decoder-only any-to-any multimodal modeling, which treats all modalities symmetrically and supports arbitrary modalities as inputs and outputs without modality-specific heads, losses, or task pipelines. Because every modality is both an input and an output of the same model, the resulting model, named Modus, can support a range of applications, such as chained generation through intermediate modalities or cross-modal self-verification by scoring the model's own outputs with another generated modality. Modus demonstrates strong out-of-the-box performance and is competitive with specialist and multitask baselines using a single model across various benchmarks. All materials are open-sourced at https://modus-multimodal.epfl.ch/.

Mingqiao Ye, Zhaochong An, Zhitong Gao +11

1EPFL · University of Copenhagen · 4CUHK +3

Modality-Specific Encoders Complementary Modalities Modalities Reference-Guided Multimodal In-Context Verification

Jul 25, 2026cs.CV

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models

Existing token compression methods for omnimodal large language models typically rely on one modality to determine what to retain in the other. We show that this assumption often breaks down: for the same query, audio and video relevance often peaks at different moments. This cross-modal salience mismatch makes unidirectional guidance prone to discarding answer-critical cues under aggressive compression. We propose OmniScope, a training-free token compression framework that uses the query as a shared semantic anchor while estimating relevance separately for audio and video. OmniScope allocates modality-specific token budgets, prunes visual tokens with an anchor-delta strategy that preserves both global context and temporal changes, and merges audio tokens within each second to reduce redundancy while maintaining temporal continuity. Across four audio-video benchmarks and two Qwen2.5-Omni model scales, OmniScope achieves the best average accuracy across all compression settings. At 25% overall token retention, it delivers up to 3.53x prefill speedup and more than 15% GPU memory reduction, with only a 0.35-point drop in average accuracy. These results suggest a simple design principle for OmniLLM inference: share the query across modalities, but not the salience estimates. The code is available at https://github.com/MAC-AutoML/OmniScope.

Jinsen Su, Yongdong Luo, Yuexiao Ma +3

Media Analytics and Computing Lab, Xiamen University, Xiamen, China · Institute of Artificial Intelligence, Xiamen University, Xiamen, China · School of Informatics, Xiamen University, Xiamen, China +1

Token Compression Omni-Modal Modality-Specific Encoders Multimodal Large Language Models Cross-Modal Conflicts Relevance

Jul 23, 2026cs.CV

Advancing All-Weather Building Damage Mapping to the Instance Level: Outcomes and Insights from the 2026 Bright Challenge

Rapid post-disaster response requires timely, building-level information on whether structures remain intact, are damaged, or are destroyed. Post-event optical imagery, however, may be unavailable because of cloud, smoke, or darkness. The Bright Challenge evaluated all-weather building damage mapping from a submeter-resolution pre-event optical image and a post-event SAR image. Participants were required to detect and delineate each building and assign exactly one of three mutually exclusive damage labels. The challenge extended the globally distributed \textsc{Bright} dataset with instance-level annotations for about 291,000 buildings across 16 disaster events spanning seven disaster types. The final phase was evaluated exclusively on two 2025 events absent from training: a wildfire event in California and a hurricane in Jamaica. A total of 157 participants made 1,289 submissions, and 46 teams entered the final phase. The two winning solutions achieved test mAPs of 0.182 and 0.181, approximately 8.7 times the public baseline of 0.021, but remained far below the best in-domain holdout score of 0.513. Across teams ranked in both phases, performance declined sharply and the rank order changed substantially. The two leading solutions independently favored modality-specific encoding, staged or late optical--SAR fusion, and an optical-dominant separation of building localization from damage recognition. The winning method additionally used scene-aware threshold adjustment and pseudo-label adaptation. These results identify cross-event generalization and stable severity discrimination as the principal remaining challenges. All data, annotations, baseline code, and winning solutions are publicly available at https://github.com/ChenHongruixuan/BRIGHT.

Hongruixuan Chen, He Huang, Haifeng Wang +19

Post-Disaster Damage Assessment Synthetic Aperture Radar Modality-Specific Encoders Insights

Jul 9, 2026cs.CV

Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing

Multimodal Large Language Models (MLLMs) are typically designed under the assumption that all modalities available during training will also be accessible at inference. However, many real-world settings violate this assumption, requiring models to operate under a privileged modality setting, where auxiliary modalities are available only during training. While these modalities contain valuable information, existing MLLMs largely fail to leverage them effectively, as they treat modalities as interchangeable inputs rather than sources of complementary supervision. We propose Mixture of Probes (MoP), a novel framework that disentangles modality-specific and modality-general signals within the MLLM, allowing the model to preserve modality-dependent structure while learning transferable representations across modalities. At its core, MoP achieves this through a structured probing mechanism that extracts and organizes information from intermediate representations of a shared modality encoder, rather than relying only on final-layer alignment as done in existing MLLMs. To support this disentanglement, we further introduce MoP Cross-modal Training (MoP-X), a training strategy for MoP centered around a probe disentanglement loss that prevents probe collapse and encourages cross-modal learning. We evaluate MoP across two domains spanning eight tasks and four modalities under a comprehensive evaluation protocol tailored to the privileged modality setting, where each modality is independently treated as the sole input at inference time. MoP consistently outperforms strong MLLM baselines, achieving up to 65% relative improvement, demonstrating that auxiliary modalities, even when unavailable at inference, can provide substantial gains when effectively leveraged during training. Code, model checkpoints, and evaluation protocols will be made available at https://github.com/Sony/MoP.

Dominick Reilly, Qiyu Wu, Hiromi Wakaki +2

Sony Group Corporation · University of North Carolina at Charlotte · Sony AI

Multimodal Large Language Models Modality-Specific Encoders Cross-Modal Complementary Modalities Mixtures

Jul 6, 2026stat.ML

Integrating Neural Encoders in Bayesian Generalized Linear Mixed Models for Multimodal Data

Scalable Bayesian inference for generalized linear mixed models (GLMMs) provides uncertainty-aware analysis of correlated longitudinal data, but existing scalable approaches largely assume low-dimensional tabular predictors and do not directly accommodate high-dimensional modalities such as images and text. We address this limitation by learning one or more modality-specific neural encoders jointly with a GLMM objective, then performing variance-corrected stochasticgradient MCMC for the GLMM parameters conditional on the learned representation. This conditional-Bayes design combines supervised representation learning with posterior uncertainty quantification for population-level effects, subjectspecific heterogeneity, and modality-level random slopes. The resulting model preserves interpretable fixed and random effects for structured covariates and learned modalities while scaling gracefully to large longitudinal datasets. In simulation studies, our method recovers posterior means and variance estimates from full-data MCMC benchmarks after covariance correction. We further evaluate uncertainty through parameter-level interval coverage in simulations and predictive calibration on held-out data. Applications to glaucoma progression and adolescent mental health demonstrate that the framework allows nuanced assessment of the relative importance of each modality on both individual and population levels without sacrificing predictive performance.

Yuankang Zhao, Youngsoo Baek, Felipe A. Medeiros +2

Department of Biostatistics & Bioinformatics, Duke University · Department of Ophthalmology, University of Miami

Generalized Linear Model Multimodal Learning Modality-Specific Encoders Covariates Longitudinal Data

Jul 3, 2026cs.LG

OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models

Omni modal large language models (OmniLLMs) have attracted wide attention for their ability to jointly process audio and video, but they generate large token sequences under audio-visual inputs, leading to substantial inference cost. Existing audio-visual token compression methods often rely on unimodal guidance, overlooking the temporal locality of query-relevant evidence in audio-visual inputs and implicitly assuming that the two modalities share a temporally aligned information density distribution. We propose \textbf{OmniFocus}, a training-free query-guided token compression method for OmniLLMs that performs independent importance estimation for video and audio, enabling a modality-symmetric compression design that preserves modality-specific salient evidence while maintaining audio-visual alignment, thereby mitigating the modality bias issue that can arise from unimodal-guided compression. Experiments on the Qwen2.5-Omni model family across four audio-visual benchmarks show that OmniFocus maintains strong compressed performance at low token retention ratios and outperforms existing baselines on several major benchmark scores at 25% token retention. On DailyOmni with Qwen2.5-Omni-7B at 25% token retention, OmniFocus maintains 59.40 accuracy while delivering up to 1.38

\times

prefill speedup relative to the full-token baseline, highlighting a favorable practical accuracy-efficiency trade-off.

Shijie Cao, Qingyu Zhang, Boxi Yu +6

School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences · University of Limerick +1

Token Compression Audio-Visual Reasoning Omni-Modal Modality-Specific Encoders Task-Aware Compression Large Audio Language Models+1

Jun 30, 2026cs.RO

TactX: Learning Shared Tactile Representations Across Diverse Sensors

Tactile sensors provide critical information for contact-rich manipulation, yet tactile representations and policies remain tightly coupled to each specific sensor, limiting transferability across robots and hardware platforms. We propose TactX, a framework for learning a transferable tactile representation across sensors spanning three fundamentally different transduction modalities: resistive, magnetic, and vision-based. TactX maps heterogeneous tactile observations into a shared latent space through modality-specific encoders trained on paired contact data. Such paired interactions provide a natural alignment signal across modalities, and the encoders are jointly trained across all sensor pairs, inducing a consistent latent space for all sensor types. Our experiments show that TactX aligns tactile representations across sensors while preserving object-level contact information, as evidenced by sensor-identity prediction and object classification in the learned latent space. We evaluate TactX on four contact-rich manipulation tasks: pick-and-place, plug insertion, board wiping, and object reorientation, and show that policies trained with one sensor transfer zero-shot to physically distinct sensors through the shared latent. This improves the average success rate from 27.5% for vision-only policy to 45.9%, providing a step toward sensor-agnostic tactile manipulation.

Junsung Park, Sachin Bhadang, Carmelo Sferrazza +2

UC San Diego · Seoul National University · Amazon FAR

Tactile Tac Contact-Rich Dexterous Manipulation Contact-Rich Manipulation Modality-Specific Encoders

Jun 26, 2026cs.SD

LoRA-Tuned Large Language Models for Dementia Detection via Multi-View Speech-Derived Features

Early detection of dementia enables timely intervention, and reflecting cognitive impairment, spontaneous speech offers a non-invasive screening modality. Conventional approaches often focus on a single representational dimension -- such as acoustic descriptors, pause modeling, automatic speech recognition (ASR) transcripts, or multimodal fusion -- limiting integrative reasoning across heterogeneous cognitive symptoms. We propose a low-rank adaptation (LoRA)-tuned large language model (LLM) that performs structured multi-view reasoning over four complementary speech-derived signals: ASR transcripts with pause markers, discourse-level topic cues, temporal fluency statistics, and phonological sequences. These cues are encoded within a unified prompt, enabling a single LLM to learn a coherent decision function without modality-specific encoders or late-stage fusion. On ADReSSo, our best model achieves an F1-score of 90.14%, and ablation confirms the complementary contribution of each view.

Jonghyeon Park, Olivier Jiyoun Jung, Myungwoo Oh

NAVER Cloud, South Korea · Division of Communication and Media, Ewha Womans University, South Korea

Alzheimer Speaker Transcript Modality-Specific Encoders Multi-View

Jun 23, 2026cs.CV

MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning

Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning. Since audio and visual streams naturally co-occur in video data, extending this success to jointly learn from both modalities is a natural next step, yet it remains challenging. Existing audio-visual self-supervised methods rely on modality-specific encoders and complex combinations of contrastive or reconstruction objectives, limiting cross-modal synergy and scalability. Joint Embedding Predictive Architectures (JEPAs) offer a simple, modality-agnostic alternative, but have to date been applied primarily to individual modalities. We introduce MJEPA, a joint-embedding predictive architecture for audio-visual learning that uses a single, unified encoder for both modalities. Our approach uses only a single predictive objective, applied both within and across modalities. We show that cross-modal prediction is critical: without it, a shared encoder degrades below unimodal baselines; with it, each modality's representation benefits from the other. Our frozen ViT-g model outperforms the best prior frozen baseline by over 6.8 mAP on AudioSet-20K, surpasses fully finetuned models on ESC-50 and FSD50K, and is competitive on video benchmarks despite using 10x less video data.

Revant Teotia, Adrien Bardes, Michael Rabbat +3

1FAIR at Meta · 2New York University

Video Joint Embedding Predictive Architecture Audio-Visual Reasoning Joint-Embedding Predictive Architectures Modality-Specific Encoders Self-Supervised Learning Cross-Modal

Jun 23, 2026cs.CL

AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression

Multimodal Large Language Models have achieved remarkable progress in short-form audio-video understanding, yet long-form audio-video comprehension remains challenged by limited context windows and severe information redundancy. To address these bottlenecks, we propose AVOC, a framework for long-form audio-video understanding in Omni-modal Large Language Models. AVOC introduces a learnable token compression module between the modality encoders and the LLM backbone. We reframe multimodal token compression as a top-

K

retrieval problem: given a fixed context budget, the module must retrieve a compact subset of tokens that best supports answering the user query. We draw inspiration from three classical Information Retrieval criteria for selecting informative units from a large candidate pool: relevance, importance, and diversity. AVOC instantiates each criterion as a tailored mechanism for audio-video understanding, and integrates them into a unified retrieval-style compression pipeline. Experiments show that AVOC achieves state-of-the-art performance on long-form audio-video benchmarks, surpassing the second-best model by 4.9 and 5.5 points in average accuracy on OmniVideoBench and LVOmniBench, respectively. Moreover, AVOC maintains robust performance on Audio-Video Needle-in-a-Haystack task at durations up to one hour.

Yijing Chen, Wenhui Tan, Xiaoyi Yu +7

1Gaoling School of Artificial Intelligence, Renmin University of China · 2Huawei Inc.

Audio-Visual Reasoning Large Audio Language Models Modality-Specific Encoders Token Compression Data Compression Methods

Jun 17, 2026cs.RO

TactSpace: Learning a Physics-enriched Shared Latent Space for Tactile Sim-to-Real Transfer

Tactile sensing provides direct measurements of contact interactions that are essential for robotic manipulation. However, current simulators lack the fidelity to faithfully model the complex deformation and transduction mechanics of tactile sensors, severely hindering sim-to-real transfer in robot learning pipelines. To address this challenge, we propose a multi-modal representation learning framework that aligns heterogeneous tactile modalities within a shared latent space, eliminating the need for accurate raw-signal simulation while preserving relevant contact information. Our approach employs modality-specific encoders to project diverse tactile observations, such as simulated penetration depth and real-world capacitance, into a common embedding space. The model is trained using self- and cross-reconstruction objectives alongside contrastive alignment, encouraging modality-invariant yet information-rich representations. We evaluate the learned embeddings on indenter shape identification, force prediction, and geometric reconstruction tasks, training exclusively in simulation and testing directly on real sensor measurements. Our results demonstrate zero-shot sim-to-real transfer across physically dissimilar representations. Furthermore, incorporating multi-physics simulation modalities yields more informative embeddings that transfer across diverse downstream tasks, demonstrating a 16.7% reduction in force prediction error and a 45.8% reduction in shape reconstruction error. Finally, we release an efficient Warp-based implementation of a penalty-based tactile simulation model for Isaac Lab, enabling scalable tactile data generation.

Arunim Joarder, Arjun Bhardwaj, René Zurbrügg +6

Robotic Systems Lab, ETH Zürich · ETH AI Center · NVIDIA +1

Tactile Sim-To-Real Reinforcement Learning Tac Latent Space Modality-Specific Encoders

Jun 15, 2026cs.CV

VinQA: Visual Elements Interleaved Long-form Answer Generation for Real-World Multimodal Document QA

Real-world documents combine text with tables, charts, photographs, and diagrams arranged in diverse layouts, yet existing research on multimodal large language models (MLLMs) for document QA predominantly produces text-only responses, underutilizing these visual elements. We introduce VinQA, a dataset for long-form answer generation where cited visual elements are explicitly interleaved with their supporting text and grounded in relevant document pages. To support this task, we study two encoding methods for feeding raw document page images into an MLLM, along with their visual-element citation mechanisms: (1) Page Encoding, which directly encodes full-page images with bounding boxes of visual elements and treats these boxed regions as citable units; and (2) Modality Encoding, which parses each page to extract text and crop visual elements, encodes them separately, and uses these cropped elements as citable units. In our experiments, we propose M-GroSE, a multimodal evaluation framework extending GroUSE to assess answers along four dimensions: completeness, answer relevancy, faithfulness, and unanswerability. We additionally report Visual Source F1 to directly measure visual citation accuracy. Although proprietary frontier models still achieve the best overall scores on the VinQA test split, fine-tuning open Qwen2.5-VL models on the training split substantially improves their performance and narrows this gap. Modality Encoding is initially more robust for complex documents with long text, many visual elements, and diverse citation requirements. After training on VinQA, however, Page Encoding reaches a comparable level, competing effectively even without the explicit parsing used in Modality Encoding. Finally, Visual G-Eval, an MLLM-based judge, confirms that fine-tuned models insert visual elements at semantically appropriate positions with faithful supporting text.

Young Rok Jang, Hyesoo Kong, Kyunghwan An +3

LG AI Research

Modality-Specific Encoders Long-Form Generation Citations

Jun 11, 2026cs.CV

Modality Forcing for Scalable Spatial Generation

Text-to-image (T2I) models contain rich spatial priors. Synthesizing photorealistic, cluttered scenes requires an understanding of geometry, including perspective and relative scale. Prior works adapt T2I models to leverage this prior for depth prediction, but they require dense depth data and involve complex recipes. We propose Modality Forcing, a simple, scalable post-training recipe for joint image-depth generation using a single DiT trained on sparse depth data. Modality Forcing enables conditional and joint generation of image and depth in any permutation by assigning separate noise levels per modality. Per-modality decoders let us train on sparse, real-world depth and achieve strong, generalizable depth prediction. We further show that Modality Forcing inherits the scalability of T2I pre-training: by training a set of T2I models from scratch (370M to 3.3B parameters), we find that larger models trained on more image data produce more accurate depth. Our strongest model is competitive with state-of-the-art monocular depth estimators and reduces AbsRel by 57% relative to existing joint image-depth generative models. These results provide strong evidence that image generation is a scalable pre-training objective for spatial perception. https://modality-forcing.github.io/

Bardienus Pieter Duisterhof, Deva Ramanan, Jeffrey Ichnowski +2

Carnegie Mellon University · World Labs

Multi-Reference Image Generation Dense Prediction Spatial Priors Modality-Specific Encoders Modalities Post-Training

Jun 8, 2026cs.CL

Explicit Representation Alignment for Multimodal Sentiment Analysis

Multimodal affective analysis aims to understand human sentiment and emotion by jointly modeling heterogeneous modalities such as text and images. However, multimodal models often fail to consistently outperform strong text-only baselines, with performance varying significantly across fusion strategies. In this work, we identify representation misalignment between independently pretrained modality encoders as a key bottleneck for effective multimodal learning, and show through controlled experiments that alignment prior to fusion is often more important than fusion complexity. To address this issue, we propose a unified multimodal affective analysis framework that leverages vision-language models (VLMs) to convert visual content into structured textual descriptions, projecting heterogeneous modalities into a shared linguistic space and enabling interpretable text-centric reasoning. To further improve robustness, we introduce a hybrid learning strategy that combines semantic token selection with a batch-level uniformity regularization objective, encouraging a more dispersed and stable global feature space while mitigating noise introduced by VLM-generated descriptions. Experiments on multiple multimodal sentiment and emotion benchmarks show that our method consistently outperforms strong unimodal and multimodal baselines, achieving state-of-the-art performance. Our analysis further highlights the critical role of representation alignment in multimodal affective learning.

Baode Wang, Ziming Wang, Huacan Wang +2

AgentAlpha

Multimodal Sentiment Analysis Modality-Specific Encoders Value Alignment

May 30, 2026cs.CV

V-LynX: Token Interface Alignment for Video+X LLMs

This study introduces an intriguing phenomenon in Video LLMs: rather than merely translating frames into textual embeddings, Video LLMs establish a continuous manifold, token interface, allowing visual tokens to operate as standalone entities within the architecture. Exploiting this discovery, we propose V-LynX, a scalable framework that integrates novel modalities into Video LLMs by repurposing the internalized interface. Departing from conventional paradigms that necessitate heavy modality-specific encoders or paired supervision, V-LynX employs a lightweight auxiliary pathway in parallel with the frozen vision encoder. Our method integrates new sensory inputs with intrinsic video priors by aligning both attention responses and statistical distributions using unpaired unimodal data sets. This ensures manifold compatibility while preserving the integrity of the Video LLMs. Extensive benchmarks demonstrate that V-LynX achieves SOTA and efficiency across audio-visual QA, 3D reasoning, high-frame-rate, and multi-view video understanding. The code is available at https://github.com/park-jungin/lynx.

Jungin Park, Jiyoung Lee, Kwanghoon Sohn

Yonsei University, Seoul, South Korea · Ewha Womans University, Seoul, South Korea

Modality-Specific Encoders Robotwin

May 21, 2026cs.CV

Two-Stage Multimodal Framework for Emotion Mimicry Intensity Prediction

We present our submission to the Hume-ABAW10 Emotional Mimicry Intensity (EMI) Challenge, which aims to predict six continuous emotion intensity dimensions: Admiration, Amusement, Determination, Empathic Pain, Excitement, and Joy, from in-the-wild multimodal video clips. We propose a staged multimodal framework that combines textual, acoustic, and visual representations, with an optional motion branch. Our approach first trains modality-specific encoders independently and then fuses their learned representations through a lightweight regressor with modality dropout and controlled encoder adaptation. Across our submitted systems, the best validation performance is obtained by the text--audio--vision--motion fusion model under the expanded 4:1 split, achieving an average Pearson correlation of 0.4722. Although the motion branch yields only very slight gains, its behavior can be interesting to study. Our team was placed third in the EMI challenge, achieving an average Pearson correlation of 0.57 for the test set. Overall, we provide a practical and reproducible baseline for EMI prediction.

Dinithi Dissanayake, Shaveen Silva, Ovindu Atukorala +2

Augmented Human Lab, National University of Singapore, Singapore · University of Moratuwa, Sri Lanka

Emotion Recognition Modality-Specific Encoders In-The-Wild Videos

May 18, 2026cs.CV

Speech-Guided Multimodal Learning for Vocal Tract Segmentation in Real-Time MRI

Segmenting vocal tract articulators in real-time MRI (rtMRI) is a challenging dynamic image segmentation problem characterized by low contrast, rapid motion, and limited spatial resolution. However, while rtMRI acquisitions may provide synchronized acoustic signals, existing methods discard this information, and the few multimodal approaches that incorporate audio cannot be deployed when audio is unavailable. We propose a three-stage framework that leverages acoustic and phonological supervision during training while requiring only the rtMRI image at inference: phonological representations are converted into spatial bounding-box priors for articulator localization, visual and acoustic encoders are aligned via dual-level cross-modal contrastive pretraining, and the learned representations are fused through a cross-attention decoder, effectively transferring multimodal knowledge into a single-modality inference pipeline. Evaluated on 75-Speaker~Annot-16 and USC-TIMIT datasets, our method outperforms existing unimodal and multimodal methods, demonstrating that multimodal supervision provides transferable benefits for precise and clinically deployable vocal tract segmentation.

Daiqi Liu, Lukas Mulzer, Md Hasan +11

Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany · Smart Imaging Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany · Harvard Medical School / Massachusetts General Hospital, Boston, USA +3

Vocal Tract Shape Magnetic Resonance Imaging Modality-Specific Encoders Multimodal Contrastive Learning Grapheme-To-Phoneme

May 18, 2026cs.CV

OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models

Omnimodal large language models (OmniLLMs) have recently gained increasing attention for unified audio-video understanding. However, processing long multimodal token sequences introduces substantial computational overhead, making efficient token compression crucial. Existing methods typically rely on fixed, modality-specific guidance, which fails to account for the varying importance of modalities across different queries. To address this limitation, we propose

\textbf{OmniSelect}

, a training-free, modality-adaptive token pruning framework that dynamically selects appropriate compression strategies for multimodal inputs. Specifically, we leverage a lightweight AudioCLIP model to estimate cross-modal relevance and categorize each input into three pruning regimes: Audio-Centric, Video-Centric, and Uniform pruning. Based on these relevance scores, OmniSelect further performs fine-grained token pruning within each temporal group, adaptively allocating pruning ratios to preserve informative tokens across modalities. By explicitly modeling modality preference and enabling dynamic strategy selection, OmniSelect effectively avoids the pitfalls of one-size-fits-all compression. Extensive experiments demonstrate that our method achieves efficient multimodal token reduction while maintaining strong performance, without requiring any additional training.

Morunliu Yang, Ruotao Xu, Le Li +6

1Soochow University · Peking University

Visual Token Pruning Modality-Specific Encoders Omni-Modal Cross-Modal Audio-Visual Reasoning Data Compression Methods

May 8, 2026cs.CL

jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers

In this work, we introduce GELATO (Geometry-preserving Embeddings via Locked Aligned TOwers), a novel approach to multimodal embedding models. We build on the VLM-style architecture, in which non-text encoders are adapted to produce input for a language model, which in turn generates embeddings for all varieties of input. We present the result: the jina-embeddings-v5-omni suite, a pair of models that encode text, image, audio, and video input into a single semantic embedding space. GELATO extends the two Jina Embeddings v5 Text models to support additional modality by adding encoders for images and audio. The backbone text embedding models and the added non-text modality encoders remain frozen. We only trained the connecting components, representing 0.35% of the total weights of the joint model. Training is therefore much more efficient than full-parameter retraining. Additionally, the language model remains effectively unaltered, producing exactly the same embeddings for text inputs as the Jina Embeddings v5 Text models. Our evaluations show that GELATO produces results that are competitive with the state-of-the-art, yielding nearly equal performance to larger multimodal embedding models.

Florian Hönicke, Michael Günther, Andreas Koukounas +4

Jina by Elastic

Multimodal Embeddings Modality-Specific Encoders Text Embeddings Retraining

May 8, 2026cs.CV

PRIMED: Adaptive Modality Suppression for Referring Audio-Visual Segmentation via Biased Competition

Referring Audio-Visual Segmentation (Ref-AVS) seeks to localize and segment target objects in video frames based on visual, auditory, and textual referring cues. The task is challenging because the relevance of different modalities varies across referring expressions and scenes, while existing methods typically treat multimodal cues as homogeneous inputs for fusion, prompting, or reasoning, making them vulnerable to irrelevant or misleading modalities. To address this problem, we propose PRIMED, inspired by the biased competition theory in cognitive neuroscience, which explicitly models both visual perception and language-driven prior modulation, and enables more accurate Ref-AVS by adaptive modality suppression. Specifically, a Modality Prior Decoder first estimates whether the referring expression relies primarily on audio, vision, or their joint interaction, generating a modality prior to adaptively guide high-level attention. A Token Distiller further extracts compact global visual tokens from high-level features and shares them across Competition-aware Cross-modal Fusion modules to provide hierarchical global context. Additionally, we introduce a Spatial-Aware Semantic Alignment loss to further enhance foreground-background discrimination through contrastive learning. Extensive experiments on the Ref-AVS benchmark demonstrate that PRIMED achieves state-of-the-art overall performance.

Yuchen He, Jing Zhang

School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China

Video Object Segmentation Modality-Specific Encoders Modalities Priming

May 2, 2026cs.CV

OmniEncoder: See, Hear, and Feel Continuous Motion Like Humans With One Encoder

Recent advances in omni-modal large language models have enabled remarkable progress in joint vision-audio understanding. However, prevailing architectures rely on modality-specific encoders with a \emph{video-coarse, audio-dense} design -- sampling visual frames at 1--2 fps while processing audio waveforms at 25 fps -- resulting in systems that perceive video \emph{frame by frame, modality by modality} rather than holistically as humans do. Such a discrepancy leaves models with impoverished cross-modal interaction during encoding and an inability to capture fine-grained visual motion. To bridge this gap, we present \textbf{Omni-Encoder, a unified Transformer backbone designed to co-embed visual and audio signals at a symmetrical 25 fps} within a shared latent space. This architecture leverages three core innovations -- the Omni-Encoder Token Template, Omni-RoPE, and Temporal Window Shifting -- to effectively reconcile the dual challenges of modality disentanglement and computational efficiency. Experiments demonstrate that, compared to the modality-specific baseline Qwen2.5-Omni under the same input token budget to the LLM decoder, Omni-Encoder delivers substantial gains on visual continuous understanding tasks -- such as sign language recognition and fine-grained sports action analysis -- while maintaining competitive performance on established audio-visual benchmarks such as AVQA and Speaker Identification and Localization. These results suggest that unified omnivorous encoding offers a promising direction for building omni-modal models that more closely reflect the integrated nature of human perception.

Detao Bai, Shimin Yao, Weixuan Chen +4

1Tongyi Lab Alibaba Group · Shenzhen University of Advanced Technology

Audio-Visual Reasoning Omni-Modal Modality-Specific Encoders Encoders Motion

May 1, 2026cs.LG

Group Cognition Learning: Making Everything Better Through Governed Two-Stage Agents Collaboration

Centralized multimodal learning commonly compresses language, acoustic, and visual signals into a single fused representation for prediction. While effective, this paradigm suffers from two limitations: modality dominance, where optimization gravitates towards the path of least resistance, ignoring weaker but informative modalities, and spurious modality coupling, where models overfit to incidental cross-modal correlations. To address these, we propose Group Cognition Learning (GCL), a governed collaboration paradigm that applies a two-stage protocol after modality-specific encoding. In Stage 1 (Selective Interaction), a Routing Agent proposes directed interaction routes, and an Auditing Agent assigns sample-wise gates to emphasize exchanges that yield positive marginal predictive gain while suppressing redundant coupling. In Stage 2 (Consensus Formation), a Public-Factor Agent maintains an explicit shared factor, and an Aggregation Agent produces the final prediction through contribution-aware weighting while keeping each modality representation as a specialization channel. Extensive experiments on CMU-MOSI, CMU-MOSEI, and MIntRec demonstrate that GCL mitigates dominance and coupling, establishing state-of-the-art results across both regression and classification benchmarks. Analysis experiments further demonstrate the effectiveness of the design.

Chunlei Meng, Pengbin Feng, Rong Fu +7

The College of Intelligent Robotics and Advanced Manufacturing, Fudan University · University of Southern California · University of Macau +5

Multimodal Learning Cross-Modal Modality-Specific Encoders Modalities Collaboration

Apr 26, 2026cs.CV

Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling

Joint audio-video generation models have shown that unified generation yields stronger cross-modal coherence than cascaded approaches. However, existing models couple modalities throughout denoising via pervasive attention, treating high-level semantics and low-level details in a fully entangled manner. This is suboptimal for talking head synthesis: while audio and facial motion are semantically correlated, their low-level realizations (acoustic signals and visual textures) follow distinct rendering processes. Enforcing joint modeling across all levels causes unnecessary entanglement and reduces efficiency. We propose Talker-T2AV, an autoregressive diffusion framework where high-level cross-modal modeling occurs in a shared backbone, while low-level refinement uses modality-specific decoders. A shared autoregressive language model jointly reasons over audio and video in a unified patch-level token space. Two lightweight diffusion transformer heads decode the hidden states into frame-level audio and video latents. Experiments on talking portrait benchmarks show Talker-T2AV outperforms dual-branch baselines in lip-sync accuracy, video quality, and audio quality, achieving stronger cross-modal consistency than cascaded pipelines.

Zhen Ye, Xu Tan, Aoxiong Yin +8

Hong Kong University of Science and Technology · Independent Researcher · Zhejiang University +3

Audio-Video Generation Autoregressive Diffusion Talk Diffusion Transformers Modality-Specific Encoders Cross-Modal

Apr 24, 2026cs.CV

Uni-Encoder Meets Multi-Encoders: Representation Before Fusion for Brain Tumor Segmentation with Missing Modalities

Multimodal MRI offers complementary information for brain tumor segmentation, but clinical scans often lack one or more modalities, which degrades segmentation performance. In this paper, we propose UniME (Uni-Encoder Meets Multi-Encoders), a two-stage heterogeneous method for brain tumor segmentation with missing modalities that reconciles the trade-offs among fine-grained structure capture, cross-modal complementarity modeling, and exploitation of available modalities. The idea is to decouple representation learning from segmentation via a two-stage heterogeneous architecture. Stage 1 pretrains a single ViT Uni-Encoder with masked image modeling to establish a unified representation robust to missing modalities. Stage 2 adds modality-specific CNN Multi-Encoders to extract high-resolution, multi-scale, fine-grained features. We fuse these features with the global representation to produce precise segmentations. Experiments on BraTS 2023 and BraTS 2024 show that UniME outperforms previous methods under incomplete multi-modal scenarios. The code is available at https://github.com/Hooorace-S/UniME

Peibo Song, Xiaotian Xue, Jinshuo Zhang +5

School of Mathematics, Shandong University · 2GSFS, The University of Tokyo · 3MedVisAI Lab +2

Brain Tumor Segmentation Magnetic Resonance Imaging Missing Modalities Multimodal Fusion Modality-Specific Encoders Unified Representation

Apr 22, 2026cs.LG

Breaking the Illusion: When Positive Meets Negative in Multimodal Decoding

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.

Yubo Jiang, Yitong An, Xin Yang +7

School of Astronautics, Beihang University, Beijing 102206, China · Longcat Interaction Team, Meituan, Beijing 100102, China · Tianmushan Laboratory, Beihang University, Hangzhou 311115, China

Modality-Specific Encoders Object Hallucination Illusions Negative Results Dual-Path Network Positive+1

Apr 16, 2026cs.CV

OmniGCD: Abstracting Generalized Category Discovery for Modality Agnosticism

Generalized Category Discovery (GCD) challenges methods to identify known and novel classes using partially labeled data, mirroring human category learning. Unlike prior GCD methods, which operate within a single modality and require dataset-specific fine-tuning, we propose a modality-agnostic GCD approach inspired by the human brain's abstract category formation. Our

\textbf{OmniGCD}

leverages modality-specific encoders (e.g., vision, audio, text, remote sensing) to process inputs, followed by dimension reduction to construct a

\textbf{GCD latent space}

, which is transformed at test-time into a representation better suited for clustering using a novel synthetically trained Transformer-based model. To evaluate OmniGCD, we introduce a

\textbf{zero-shot GCD setting}

where no dataset-specific fine-tuning is allowed, enabling modality-agnostic category discovery.

\textbf{Trained once on synthetic data}

, OmniGCD performs zero-shot GCD across 16 datasets spanning four modalities, improving classification accuracy for known and novel classes over baselines (average percentage point improvement of

\textbf{+6.2}

,

\textbf{+17.9}

,

\textbf{+1.5}

and

\textbf{+12.7}

for vision, text, audio and remote sensing). This highlights the importance of strong encoders while decoupling representation learning from category discovery. Improving modality-agnostic methods will propagate across modalities, enabling encoder development independent of GCD. Our work serves as a benchmark for future modality-agnostic GCD works, paving the way for scalable, human-inspired category discovery. All code is available

\href{https://github.com/Jordan-HS/OmniGCD}{here}

Jordan Shipard, Arnold Wiliem, Kien Nguyen Thanh +2

SAIVT, QUT, Australia · Shield AI, Australia · La Trobe University, Australia

Generalized Category Discovery Modality-Specific Encoders Modalities Omnichem

Mar 15, 2026cs.MM

DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression

Omnimodal large language models (OmniLLMs) jointly process audio and visual streams, but the resulting long multimodal token sequences make inference prohibitively expensive. Existing compression methods typically rely on fixed window partitioning and attention-based pruning, which overlook the piecewise semantic structure of audio-visual signals and become fragile under aggressive token reduction. We propose Dynamic Audio-driven Semantic cHunking (DASH), a training-free framework that aligns token compression with semantic structure. DASH treats audio embeddings as a semantic anchor and detects boundary candidates via cosine-similarity discontinuities, inducing dynamic, variable-length segments that approximate the underlying piecewise-coherent organization of the sequence. These boundaries are projected onto video tokens as a soft temporally co-registered segmentation prior. Within each segment, token retention is determined by a tri-signal importance estimator that fuses structural boundary cues, representational distinctiveness, and attention-based salience, mitigating the sparsity bias of attention-only selection. This structure-aware allocation preserves transition-critical tokens while reducing redundant regions. Extensive experiments on AVUT, VideoMME, and WorldSense demonstrate that DASH maintains competitive or superior accuracy while achieving higher compression ratios compared to prior methods. Code is available at: https://github.com/laychou666/DASH.

Bingzhou Li, Tao Huang

Shanghai Jiao Tong University, Shanghai, China · Tongji University, Shanghai, China

Token Compression Audio-Visual Reasoning Modality-Specific Encoders Chunk Object-Centric Cues

Jul 21, 2025cs.CL

Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey

The rapid advancement of large language models (LLMs) has intensified the need for effective mechanisms to transform continuous multimodal data into discrete representations suitable for language-based processing. Discrete tokenization, with vector quantization (VQ) as a central approach, offers both computational efficiency and compatibility with LLM architectures. Despite its growing importance, there is a lack of a comprehensive survey that systematically examines VQ techniques in the context of LLM-based systems. This work fills this gap by presenting the first structured taxonomy and analysis of discrete tokenization methods designed for LLMs. We categorize 8 representative VQ variants that span classical and modern paradigms and analyze their algorithmic principles, training dynamics, and integration challenges with LLM pipelines. Beyond algorithm-level investigation, we discuss existing research in terms of classical applications without LLMs, LLM-based single-modality systems, and LLM-based multimodal systems, highlighting how quantization strategies influence alignment, reasoning, and generation performance. In addition, we identify key challenges including codebook collapse, unstable gradient estimation, and modality-specific encoding constraints. Finally, we discuss emerging research directions such as dynamic and task-adaptive quantization, unified tokenization frameworks, and biologically inspired codebook learning. This survey bridges the gap between traditional vector quantization and modern LLM applications, serving as a foundational reference for the development of efficient and generalizable multimodal systems. A continuously updated version is available at: https://github.com/jindongli-Ai/LLM-Discrete-Tokenization-Survey.

Jindong Li, Yali Fu, Jiahong Liu +5

Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Jilin University, Changchun, China · The Chinese University of Hong Kong, Hong Kong, China +2

Large Language Model Quantization Multimodal Large Language Models Modality-Specific Encoders Large Language Model Pipelines Systematic Study Survey

Mar 20, 2025cs.LG

Structured-Noise Masked Modeling for Video, Audio and Beyond

Masked modeling has emerged as a robust self-supervised learning framework. However, most methods rely on random masking, which disregards the structural properties of different data modalities. To align with the spatiotemporal and spectral characteristics of video and audio data, we introduce a structured noise-based masking approach. By filtering white noise into different color noise distributions, we generate structured masks that capture modality-specific patterns without requiring handcrafted heuristics or access to the data. Our approach enhances masked video and audio modeling frameworks without any additional computational cost. Experiments show that structured noise masking consistently outperforms random masking, underscoring the value of modality-aware masking strategies for representation learning.

Aritra Bhowmik, Carlos Hinojosa, Fida Mohammad Thoker +2

University of Amsterdam · King Abdullah University of Science and Technology

Noise-Aware Neural Audio Modality-Specific Encoders Modalities Audio Understanding

Date pendingcs.AI

MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) suffer from cross-modal hallucinations, where one modality inappropriately influences generation about another, leading to fabricated output. This exposes a more fundamental deficiency in modality-interaction control. To address this, we propose Modality-Adaptive Decoding (MAD), a training-free method that adaptively weights modality-specific decoding branches based on task requirements. MAD leverages the model's inherent ability to self-assess modality relevance by querying which modalities are needed for each task. The extracted modality probabilities are then used to adaptively weight contrastive decoding branches, enabling the model to focus on relevant information while suppressing cross-modal interference. Extensive experiments on CMM and AVHBench demonstrate that MAD significantly reduces cross-modal hallucinations across multiple audio-visual language models (7.8% and 2.0% improvements for VideoLLaMA2-AV, 8.7% and 4.7% improvements for Qwen2.5-Omni). Our approach demonstrates that explicit modality awareness through self-assessment is crucial for robust multimodal reasoning, offering a principled extension to existing contrastive decoding methods. Our code is available at \href{https://github.com/top-yun/MAD}{https://github.com/top-yun/MAD}

Sangyun Chung, Se Yeon Kim, Youngchae Chee +1

Integrated Vision Language Lab, KAIST, South Korea

Multimodal Large Language Models Modality-Specific Encoders Contrastive Decoding Large Language Model Hallucination Modalities Large Audio Language Models