Multimodal Generation

Ask about this topic

Overview

Multimodal generation studies models that create outputs such as images, video, speech, motion, or scientific signals from text, media, or combinations of them. Common approaches include diffusion and flow-matching decoders, autoregressive or discrete-token models, shared latent spaces, and systems that connect vision-language models to modality-specific generators; planning and reinforcement learning can add control for complex or interleaved outputs. A major direction is building models that both understand and generate, with benchmarks measuring prompt adherence, fidelity, temporal and cross-modal coherence, and task-specific validity. An open challenge is enabling shared models to turn understanding into faithful, controllable generation without modality imbalance or loss of specialized quality, especially over long sequences and varied real-world inputs.

Latest papers

CardsList

243 papers29 papers in the last four weeks, up 38% on the four weeks before. 0.2% of all new papers.

May 12, 2026

AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward

In this paper, we propose AlphaGRPO, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models (UMMs) to enhance multimodal generation capabilities without an additional cold-start stage. Our approach unlocks the model's intrinsic potential to perform advanced reasoning tasks: Reasoning Text-to-Image Generation, where the model actively infers implicit user intents, and Self-Reflective Refinement, where it autonomously diagnoses and corrects misalignments in generated outputs. To address the challenge of providing stable supervision for real-world multimodal generation, we introduce the Decompositional Verifiable Reward (DVReward). Unlike holistic scalar rewards, DVReward utilizes an LLM to decompose complex user requests into atomic, verifiable semantic and quality questions, which are then evaluated by a general MLLM to provide reliable and interpretable feedback. Extensive experiments demonstrate that AlphaGRPO yields robust improvements across multimodal generation benchmarks, including GenEval, TIIF-Bench, DPG-Bench and WISE, while also achieving significant gains in editing tasks on GEdit without training on editing tasks. These results validate that our self-reflective reinforcement approach effectively leverages inherent understanding to guide high-fidelity generation. Project page: https://huangrh99.github.io/AlphaGRPO/

Runhui Huang, Jie Wu, Rui Yang +2

The University of Hong Kong · Bytedance Seed

Unified Multimodal ModelsMultimodal GenerationReinforcement Learning with Verifiable RewardsRL for Generative Models
AskPDF
May 12, 2026

Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation

While recent advancements in multimodal language models have enabled image generation from expressive multi-image instructions, existing methods struggle to maintain performance under complex interleaved instructions. This limitation stems from the structural separation of images and text in current paradigms, which forces models to bridge difficult long-range dependencies to match descriptions with visual targets. To address these challenges, we propose Images iN SEnTences (a.k.a, INSET), a unified generation model that seamlessly embeds images as native vocabulary within textual instructions. By positioning visual features directly at their corresponding semantic slots, INSET leverages the contextual locality of transformers for precise object binding, effectively treating images as dense, expressive language tokens. Furthermore, we introduce a scalable data engine that synthesizes 15M high-quality interleaved samples from standard image and video datasets, utilizing VLMs and LLMs to construct rich, long-horizon sequences. Evaluation results on InterleaveBench demonstrate that INSET significantly outperforms state-of-the-art methods in multi-image consistency and text alignment, with performance gaps widening as input complexity increases. Beyond standard generation, our approach inherently extends to multimodal image editing, integrating visual content as part of the instruction to facilitate highly expressive and creative visual manipulations.

Yabo Zhang, Kunchang Li, Dewei Zhou +2

ByteDance Seed

Unified Multimodal ModelsCompositional Image GenerationMultimodal Generation
AskPDF
May 12, 2026

Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models

Generating realistic and user-preferred advertisements is a key challenge in e-commerce. Existing approaches utilize multiple independent models driven by click-through-rate (CTR) to controllably create attractive image or text advertisements. However, their pipelines lack cross-modal perception and rely on CTR that only reflects average preferences. Therefore, we explore jointly generating personalized image-text advertisements from historical click behaviors. We first design a Unified Advertisement Generative model (Uni-AdGen) that employs a single autoregressive framework to produce both advertising images and texts. By incorporating a foreground perception module and instruction tuning, Uni-AdGen enhances the realism of the generated content. To further personalize advertisements, we equip Uni-AdGen with a coarse-to-fine preference understanding module that effectively captures user interests from noisy multimodal historical behaviors to drive personalized generation. Additionally, we construct the first large-scale Personalized Advertising image-text dataset (PAd1M) and introduce a Product Background Similarity (PBS) metric to facilitate training and evaluation. Extensive experiments show that our method outperforms baselines in general and personalized advertisement generation. Our project is available at https://github.com/JD-GenX/Uni-AdGen.

Yexing Xu, Wei Feng, Shen Zhang +15

Sun Yat-Sen University · Northeastern University

Online AdvertisingMultimodal GenerationAutoregressive Image GenerationE-Commerce
AskPDF
May 12, 2026

Towards Visually Grounded Multimodal Summarization via Cross-Modal Transformer and Gated Attention

Multimodal summarization requires models to jointly understand textual and visual inputs to generate concise, semantically coherent summaries. Existing methods often inject shallow visual features into deep language models, leading to representational mismatches and weak cross-modal grounding. We propose a unified framework that jointly performs text summarization and representative image selection. Our system, SPeCTrA-Sum (Sampler Perceiver with Cross-modal Transformer and gated Attention for Summarization), introduces two key innovations. First, a Deep Visual Processor (DVP) aligns the visual encoder with the language model at corresponding depths, enabling hierarchical, layer-wise fusion that preserves semantic consistency. Second, a lightweight Visual Relevance Predictor (VRP) selects salient and diverse images by distilling soft labels from a Determinantal Point Processes (DPP) teacher. SPeCTrA-Sum is trained using a multi-objective loss that combines autoregressive summarization, cross-modal alignment, and DPP-based distillation. Experiments show that our system produces more accurate, visually grounded summaries and selects more representative images, demonstrating the benefits of depth-aware fusion and principled image selection for multimodal summarization.

Abid Ali, Diego Molla-Aliod, Usman Naseem

School of Computing, Macquarie University, Sydney, Australia

Cross-Modal AlignmentDeterminantal Point ProcessMultimodal GenerationMultimodal Fusion
AskPDF
May 12, 2026

Measuring What Matters Beyond Text: Evaluating Multimodal Summaries by Quality, Alignment, and Diversity

Multimodal Large Language Models (MLLMs) have facilitated Multimodal Summarization with Multimodal Output (MSMO), wherein systems generate concise textual summaries accompanied by salient visuals from multimodal sources. However, current MSMO evaluation remains fragmented: text quality, image-text alignment, and visual diversity are typically assessed in isolation using unimodal metrics, making it difficult to capture whether the modalities jointly support a faithful and useful summary. To address this gap, we introduce MM-Eval, a unified evaluation framework that integrates assessments of textual quality, cross-modal alignment, and visual diversity. MM-Eval comprises three components: (1) text quality, measured using OpenFActScore for factual consistency and G-Eval for coherence, fluency, and relevance; (2) image-text relevance, evaluated via an MLLM-as-a-judge approach; and (3) image-set diversity, quantified using Truncated CLIP Entropy. We calibrate MM-Eval through a learned aggregation model trained on the mLLM-EVAL news benchmark, aligning component contributions with human preferences. Our analysis reveals a text-dominant hierarchy in this setting, where factual consistency acts as a critical determinant of perceived overall quality, while visual relevance and diversity provide complementary signals. MM-Eval improves over heuristic aggregation baselines and provides an interpretable, reference-weak framework for comparative evaluation of multimodal summaries.

Abid Ali, Diego Molla-Aliod, Usman Naseem

School of Computing, Macquarie University, Sydney, Australia

LLM EvaluationMultimodal Large Language ModelsMultimodal GenerationSummarization EvaluationMultimodal Model Evaluation
AskPDF
May 11, 2026

Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning

Unified Multimodal Models (UMMs) excel in general tasks but struggle to bridge the gap between personalized understanding and generation. Prior works largely rely on implicit token-level alignment via supervised fine-tuning, which fails to fully capture the potential synergy between comprehension and creation. In this work, we propose Sync-R1, an end-to-end reinforcement learning framework that jointly optimizes personalized understanding and generation within a single, explicit reasoning loop. Through this unified feedback process, Sync-R1 enables personalized comprehension to guide content creation, while the resulting generation quality reciprocally refines understanding within an integrated reward landscape. To efficiently orchestrate this dual-task synergy, we introduce Sync-GRPO, a reinforcement learning method utilizing an ensemble reward system. Furthermore, we propose Dynamic Group Scaling (DGS), which adaptively filters low-potential trajectories to reduce gradient variance and accelerate convergence. To better reflect real-world complexity, we introduce UnifyBench++, featuring denser textual descriptions and richer user contexts. Experimental results demonstrate that Sync-R1 achieves state-of-the-art performance, showcasing superior cross-task reasoning and robust personalization without requiring complex cold-start procedures. The code and the UnifyBench++ dataset will be released at: https://github.com/arctanxarc/UniCTokens.

Zijun Shen, Sihan Yang, Ruichuan An +5

1Peking University · 3CUHK · 4Zhongguancun Academy

Unified Multimodal ModelsMultimodal ReasoningMultimodal GenerationRL for VLMs
AskPDF
May 11, 2026

Yeti: A compact protein structure tokenizer for reconstruction and multi-modal generation

Multimodal models that jointly reason over protein sequences, structures, and function annotations within a unified representation hold immense potential for integrating multimodal data and generating new proteins with designed functional properties. To utilize transformer architectures, such models require a tokenizer that converts protein structure from continuous atomic coordinates into discrete representations suitable for scalable multimodal training. The quality of such models are fundamentally upper bounded by the fidelity and expressiveness of the underlying tokenized structure. However, existing tokenizers prioritize reconstruction over generative abilities. To address these gaps, we introduce Yeti, a simple and compact protein structure tokenizer based on lookup free quantization and trained end to end with a flow matching objective for multimodal learning. Compared to existing models, Yeti generally achieves the best codebook utilization and token diversity, and second best reconstruction accuracy (with 10x fewer parameters than ESM3) on diverse datasets. To validate Yeti's generative capability, we trained a compact multimodal model jointly over its structure tokens and amino acid sequence entirely from scratch, with no pretrained initialization. The resulting multimodal model generates plausible structures under unconditional cogeneration of protein sequence and structures, achieving comparable results to 10x larger models. Together, these results demonstrate that Yeti is a compact and expressive protein structure tokenizer suitable for training multimodal models that cogenerates highly plausible sequences and structures.

Nabin Giri, Steven Farrell, Kristofer E. Bouchard

Lawrence Berkeley National Laboratory

Protein Structure GenerationGenerative ModelingMultimodal Generation
AskPDF
May 9, 2026

SynerMedGen: Synergizing Medical Multimodal Understanding with Generation via Task Alignment

Unifying multimodal understanding and generation is a compelling frontier that is beginning to emerge in the medical field. However, the limited existing unified medical models typically treat understanding and generation as disjoint objectives, lacking a meaningful functional synergy. In this work, we identify and address a critical question in unified medical modeling: what form of understanding truly benefits generation. We present SynerMedGen, a unified framework built on the proposed principle of generation-aligned understanding, which synergizes understanding objectives with generation tasks via task alignment. SynerMedGen introduces three generation-aligned understanding tasks and a two-stage training strategy that transfers generation-beneficial representations learned during understanding training to medical image synthesis. Remarkably, even with understanding training alone, our SynerMedGen achieves strong zero-shot performance across 22 medical image synthesis tasks and demonstrates robust generalization to unseen datasets. When combined with generation training, SynerMedGen consistently outperforms state-of-the-art specialized medical image synthesis models as well as recent unified medical models. We also release a large-scale dataset named SynerMed consisting of 1M paired synthesis samples and 2M generation-derived understanding instances to support further research on understanding-generation synergy. Our project can be accessed at https://github.com/piooip/SynerMedGen.

Weiren Zhao, Yi Dong, Cheng Chen

The University of Hong Kong, Hong Kong, China.

HealthcareUnified Multimodal ModelsMultimodal GenerationMedical Image SynthesisMultimodal Understanding
AskPDF
May 8, 2026

Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria

Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human judgment. Prevailing RLHF approaches reduce this structure to scalar or pairwise labels, collapsing nuanced preferences into opaque parametric proxies and exposing vulnerabilities to reward hacking. While recent Rubrics-as-Reward (RaR) methods attempt to recover this structure through explicit criteria, generating rubrics that are simultaneously reliable, scalable, and data-efficient remains an open problem. We introduce Auto-Rubric as Reward (ARR), a framework that reframes reward modeling from implicit weight optimization to explicit, criteria-based decomposition. Before any pairwise comparison, ARR externalizes a VLM's internalized preference knowledge as prompt-specific rubrics, translating holistic intent into independently verifiable quality dimensions. This conversion of implicit preference structure into inspectable, interpretable constraints substantially suppresses evaluation biases including positional bias, enabling both zero-shot deployment and few-shot conditioning on minimal supervision. To extend these gains into generative training, we propose Rubric Policy Optimization (RPO), which distills ARR's structured multi-dimensional evaluation into a robust binary reward, replacing opaque scalar regression with rubric-conditioned preference decisions that stabilize policy gradients. On text-to-image generation and image editing benchmarks, ARR-RPO outperforms pairwise reward models and VLM judges, demonstrating that explicitly externalizing implicit preference knowledge into structured rubrics achieves more reliable, data-efficient multimodal alignment, revealing that the bottleneck is the absence of a factorized interface, not a deficit of knowledge.

Juanxi Tian, Fengyuan Liu, Jiaming Han +6

1Nanyang Technological University · 2Ant Group · 3MMLab, The Chinese University of Hong Kong +1

Policy OptimizationMultimodal Reward ModelingRubric-Based RLMultimodal GenerationRL for Image GenerationRubric-Based Evaluation
AskPDF
May 8, 2026

STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation

Deep generative models have advanced rapidly across text and vision, motivating unified multimodal systems that can understand, reason over, and generate interleaved text-image sequences. Most existing approaches combine autoregressive language modeling with diffusion-based image generators, inheriting a structural mismatch between causal text generation and iterative visual denoising. We observe that autoregressive normalizing flows are autoregressive Transformers--sharing the same causal mask, KV-cache mechanism, and left-to-right structure as LLMs--making them the most natural paradigm for true unified multimodal generation. We present STARFlow2, built on the Pretzel architecture that vertically interleaves a pretrained VLM stream with a TarFlow stream via residual skip connections, both operating under the same causal mask. Combined with a deep-shallow flow design and a unified FAE latent space, STARFlow2 enables cache-friendly interleaved generation where both text and visual outputs directly enter the KV-cache without re-encoding. Experiments demonstrate strong performance across image generation and multimodal understanding benchmarks, validating autoregressive flows as a viable foundation for unified multimodal modeling.

Ying Shen, Tianrong Chen, Yuan Gao +6

UIUC · Apple

Unified Multimodal ModelsMultimodal GenerationAutoregressive Image GenerationFlow-Based Generative ModelingMultimodal Foundation Models
AskPDF
May 7, 2026

Steering Visual Generation in Unified Multimodal Models with Understanding Supervision

Unified multimodal models are envisioned to bridge the gap between understanding and generation. Yet, to achieve competitive performance, state-of-the-art models adopt largely decoupled understanding and generation components. This design, while effective for individual tasks, weakens the connection required for mutual enhancement, leaving the potential synergy empirically uncertain. We propose to explicitly restore this synergy by introducing Understanding-Oriented Post-Training (UNO), a lightweight framework that treats understanding not only as a distinct task, but also a direct supervisory signal to steer generative representations. By incorporating objectives that encode semantic abstraction (captioning) and structural details (visual regression), we enable effective gradient flow from understanding to generation. Extensive experiments on image generation and editing demonstrate that understanding can serve as an effective catalyst for generation.

Zeyu Liu, Zanlin Ni, Yang Yue +5

1Tsinghua University · 2Kolors Team, Kuaishou Technology

Unified Multimodal ModelsImage GenerationMultimodal GenerationMultimodal Foundation ModelsMultimodal Understanding
AskPDF
May 5, 2026

Multimodal synthesis of MRI and tabular data with diffusion in a joint latent space via cross-attention

We propose a multimodal latent diffusion model that jointly synthesizes volumetric magnetic resonance imaging (MRI) and tabular clinical data within a shared latent space via cross-attention. This approach enables coherent joint representation learning of MRI and tabular modalities for generative modeling. Our model utilizes a variational autoencoder to fuse the two modalities before diffusion-based synthesis, allowing modality-appropriate reconstruction with separate decoders for MRI and tabular data. We evaluated the framework on data from the German National Cohort (NAKO Gesundheitsstudie), comprising over 10,000 participants with MRI scans and clinical tabular features such as age, sex, body measurements, and ethnicity. The generated MRI volumes exhibited anatomical plausibility and body composition consistent with the synthesized tabular attributes. Quantitative evaluation using Fréchet distance and precision-recall metrics confirmed high-fidelity image generation. In the tabular modality, our model outperformed CTGAN across standard evaluation metrics and achieved results comparable to TVAE, demonstrating competitive performance relative to established unimodal baselines. This work is, to our knowledge, the first to demonstrate the feasibility of jointly modeling MRI and mixed-type tabular data in a single latent diffusion framework, offering a proof-of-concept for generating coherent synthetic multimodal patient data and aligning with the broader goal of developing digital twins in healthcare.

Daniel Mensing, Jan Kapar, Jochen G. Hirsch +3

Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany · Leibniz Institute for Prevention Research and Epidemiology – BIPS, Bremen, Germany · Faculty of Mathematics and Computer Science, University of Bremen, Bremen, Germany +1

Synthetic Tabular Data GenerationMultimodal GenerationMedical Image SynthesisMultimodal Diffusion Models
AskPDF
May 4, 2026

FEAT: Fashion Editing and Try-On from Any Design

Fashion design aims to express a designer's creative intent and to depict how garments interact with the human body. Recent methods condition on multimodal inputs to support garment editing and virtual try-on. However, existing methods still (i) confine design to garment-related images, excluding creative design sources such as artwork, abstract imagery, and natural photographs, and (ii) cannot support complete outfits, including accessories. We present FEAT (Fashion Editing And Try-On from Any Design), a method that enables editing and try-on across garments and accessories using diverse design sources. To achieve this, we introduce Disentangled Dual Injection (DDI). It takes both apparel and non-apparel design sources and selectively injects design cues via content and style disentanglement. Furthermore, we propose Orthogonal-Guided Noise Fusion (OGNF), a training-free mechanism that removes residual garments via orthogonal projection and applies region-specific noise strategies to enable virtual try-on for both garments and accessories. Extensive experiments demonstrate that FEAT achieves state-of-the-art performance in design flexibility, prompt consistency, and visual realism.

Soye Kwon, Keonyoung Lee, Dahuin Jung +1

Department of Computer Science, Kookmin University · School of Software, Soongsil University · Department of Artificial Intelligence, Chung-Ang University

Virtual Try-OnMultimodal GenerationImage Editing
AskPDF
May 3, 2026

Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models

Emerging multi-modal world models attempt to jointly generate videos across diverse modalities (e.g., RGB, depth, and mask), yet they fail to fully exploit the rich priors of existing foundation models. We propose M2M^2-REPA, the first representation alignment method tailored for multi-modal video generation. Our key insight is that foundation models trained on different modality spaces naturally capture distinct domain-specific priors, acting as complementary "experts." Specifically, we first decouple modality-specific features from the diffusion model's intermediate representations, then align each with its corresponding expert foundation model. To this end, we design two synergistic objectives: a multi-modal representation alignment loss that enforces feature-to-expert matching, and a modality-specific decoupling regularization that encourages complementarity across different modalities. This design enables joint optimization, fully exploiting priors from multiple foundation models. Extensive experiments demonstrate that our method significantly outperforms baselines in visual quality and long-term consistency.

Junyuan Xiao, Dingkang Liang, Xin Zhou +9

Tsinghua University, China · Huazhong University of Science and Technology, China · CSU, China +4

World ModelsCross-Modal AlignmentMultimodal GenerationMultimodal Video GenerationMultimodal Foundation ModelsMultimodal Diffusion Models
AskPDF
May 3, 2026

TMD-Bench: A Multi-Level Evaluation Paradigm for Music-Dance Co-Generation

Unified audio-visual generation is rapidly gaining industrial and creative relevance, enabling applications in virtual production and interactive media. However, when moving from general audio-video synthesis to music-dance co-generation, the task becomes substantially harder: musical rhythm, phrasing, and accents must drive choreographic motion at fine temporal resolution, and such rhythmic coupling is not captured by unimodal metrics or generic audiovisual consistency scores used in current evaluation practice. We introduce TMD-Bench, a benchmark for text-driven music-dance co-generation that assesses systems across unimodal generation quality, instruction adherence, and cross-modal rhythmic alignment. The benchmark integrates computable physical metrics with perceptual multimodal judgments, and is supported by a curated rhythm-aligned music-dance dataset and a fine-grained Music Captioner for structured music semantics. TMD-Bench further reveals that (i) modern commercial audio-visual models, such as Veo 3 and Sora 2, produce high-quality music and video, while rhythmic coupling remains less consistently optimized and leaves room for improvement, and (ii) our unified baseline RhyJAM trained on rhythm-aligned data achieves competitive beat-level synchronization while maintaining competitive unimodal fidelity. This presents prospects for building next-generation music-dance models that explicitly optimize rhythmic and kinetic coherence.

Xiaoda Yang, Majun Zhang, Changhao Pan +10

Department of Zhejiang, University of China · Tecent, China · School of National University of Singapore.

Human Motion GenerationAudio-Visual SynchronizationMultimodal GenerationMultimodal Model Evaluation
AskPDF
May 1, 2026

Learning Multimodal Energy-Based Model with Multimodal Variational Auto-Encoder via MCMC Revision

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.

Jiali Cui, Zhiqiang Lao, Heather Yu

Basking Ridge, New Jersey, USA Futurewei Technologies Inc · Basking Ridge, New Jersey, USA2026 Futurewei Technologies Inc

Variational AutoencodersMarkov Chain Monte CarloEnergy-Based ModelsMultimodal Generation
AskPDF
May 1, 2026

Towards Customized Multimodal Role-Play

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.

Chao Tang, Jianzong Wu, Qingyu Shi +5

1Peking University · 2Alibaba Group · 3Zhejiang University

Cross-Modal LearningCross-Modal AlignmentMultimodal GenerationMultimodal Instruction Tuning
AskPDF
Apr 27, 2026

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creating misalignment between the two tasks and preventing fully end-to-end optimization from raw pixels. We introduce Tuna-2, a native unified multimodal model that performs visual understanding and generation directly based on pixel embeddings. Tuna-2 drastically simplifies the model architecture by employing simple patch embedding layers to encode visual input, completely discarding the modular vision encoder designs such as the VAE or the representation encoder. Experiments show that Tuna-2 achieves state-of-the-art performance in multimodal benchmarks, demonstrating that unified pixel-space modelling can fully compete with latent-space approaches for high-quality image generation. Moreover, while the encoder-based variant converges faster in early pretraining, Tuna-2's encoder-free design achieves stronger multimodal understanding at scale, particularly on tasks requiring fine-grained visual perception. These results show that pretrained vision encoders are not necessary for multimodal modelling, and end-to-end pixel-space learning offers a scalable path toward stronger visual representations for both generation and perception.

Zhiheng Liu, Weiming Ren, Xiaoke Huang +12

Meta AI · University of Waterloo · The University of Hong Kong

Unified Multimodal ModelsMultimodal PretrainingMultimodal GenerationMultimodal Foundation ModelsMultimodal LearningMultimodal Understanding
AskPDF
Apr 26, 2026

Multimodal QUD: Inquisitive Questions from Scientific Figures

Asking inquisitive questions while reading, and looking for their answers, is an important part in human discourse comprehension, curiosity, and creative ideation, and prior work has investigated this in text-only scenarios. However, in scientific or research papers, many of the critical takeaways are conveyed through both figures and the text that analyzes them. While scientific visualizations have been used to evaluate Vision-Language Models (VLMs) capabilities, current benchmarks are limited to questions that focus simply on extracting information from them. Such questions only require lower-level reasoning, do not take into account the context in which a figure appears, and do not reflect the communicative goals the authors wish to achieve. We generate inquisitive questions that reach the depth of questions humans generate when engaging with scientific papers, conditioned on both the figure and the paper's context, and require reasoning across both modalities. To do so, we extend the linguistic theory of Questions Under Discussion (QUD) from being text-only to multimodal, where implicit questions are raised and resolved as discourse progresses. We present MQUD, a dataset of research papers in which such questions are made explicit and annotated by the original authors. We show that fine-tuning a VLM on MQUD shifts the model from generating generic low-level visual questions to content-specific grounding that requires a high-level of multimodal reasoning, yielding higher-quality, more visually grounded multimodal QUD generation.

Yating Wu, William Rudman, Venkata S Govindarajan +2

The University of Texas at Austin · Ithaca College · UC Berkeley, BespokeLabs.ai

Multimodal GroundingScientific QAMultimodal ReasoningMultimodal GenerationMultimodal Understanding
AskPDF
Apr 23, 2026

Context Unrolling in Omni Models

We present Omni, a unified multimodal model natively trained on diverse modalities, including text, images, videos, 3D geometry, and hidden representations. We find that such training enables Context Unrolling, where the model explicitly reasons across multiple modal representations before producing predictions. This process enables the model to aggregate complementary information across heterogeneous modalities, facilitating a more faithful approximation of the shared multimodal knowledge manifold and improving downstream reasoning fidelity. As a result, Omni achieves strong performance on both multimodal generation and understanding benchmarks, while demonstrating advanced multimodal reasoning capabilities, including in-context generation of text, image, video, and 3D geometry.

Ceyuan Yang, Zhijie Lin, Yang Zhao +16

Cross-Modal LearningUnified Multimodal ModelsMultimodal PretrainingMultimodal ReasoningMultimodal GenerationMultimodal Foundation Models+1
AskPDF
Apr 22, 2026

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

We present LLaDA2.0-Uni, a unified discrete diffusion large language model (dLLM) that supports multimodal understanding and generation within a natively integrated framework. Its architecture combines a fully semantic discrete tokenizer, a MoE-based dLLM backbone, and a diffusion decoder. By discretizing continuous visual inputs via SigLIP-VQ, the model enables block-level masked diffusion for both text and vision inputs within the backbone, while the decoder reconstructs visual tokens into high-fidelity images. Inference efficiency is enhanced beyond parallel decoding through prefix-aware optimizations in the backbone and few-step distillation in the decoder. Supported by carefully curated large-scale data and a tailored multi-stage training pipeline, LLaDA2.0-Uni matches specialized VLMs in multimodal understanding while delivering strong performance in image generation and editing. Its native support for interleaved generation and reasoning establishes a promising and scalable paradigm for next-generation unified foundation models. Codes and models are available at https://github.com/inclusionAI/LLaDA2.0-Uni.

Inclusion AI, Tiwei Bie, Haoxing Chen +15

AGI Research Center, Inclusion AI

Unified Multimodal ModelsMultimodal GenerationDiffusion-Based Image GenerationMultimodal Foundation ModelsDiffusion Language ModelsImage Editing+1
AskPDF
Apr 22, 2026

Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback

Multimodal Large Language Models (MLLMs) have shown promising capabilities in generating Scalable Vector Graphics (SVG) via direct code synthesis. However, existing paradigms typically adopt an open-loop "blind drawing" approach, where models generate symbolic code sequences without perceiving intermediate visual outcomes. This methodology severely underutilizes the powerful visual priors embedded in MLLMs vision encoders, treating SVG generation as a disjointed textual sequence modeling task rather than an integrated visuo-spatial one. Consequently, models struggle to reason about partial canvas states and implicit occlusion relationships, which are visually explicit but textually ambiguous. To bridge this gap, we propose Render-in-the-Loop, a novel generation paradigm that reformulates SVG synthesis as a step-wise, visual-context-aware process. By rendering intermediate code states into a cumulative canvas, the model explicitly observes the evolving visual context at each step, leveraging on-the-fly feedback to guide subsequent generation. However, we demonstrate that applying this visual loop naively to off-the-shelf models is suboptimal due to their inability to leverage incremental visual-code mappings. To address this, we first utilize fine-grained path decomposition to construct dense multi-step visual trajectories, and then introduce a Visual Self-Feedback (VSF) training strategy to condition the next primitive generation on intermediate visual states. Furthermore, a Render-and-Verify (RaV) inference mechanism is proposed to effectively filter degenerate and redundant primitives. Our framework, instantiated on a multimodal foundation model, outperforms strong open-weight baselines on the standard MMSVGBench. This result highlights the remarkable data efficiency and generalization capability of our Render-in-the-Loop paradigm for both Text-to-SVG and Image-to-SVG tasks.

Guotao Liang, Zhangcheng Wang, Juncheng Hu +5

School of Software, Beihang University, China · 3 4Paradigm, China · Department of Computer Science, The University of Hong Kong, China

Vector Graphics GenerationText-to-SVG GenerationMultimodal Large Language ModelsMultimodal Generation
AskPDF
Apr 21, 2026

MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings

We present MMCORE, a unified framework designed for multimodal image generation and editing. MMCORE leverages a pre-trained Vision-Language Model (VLM) to predict semantic visual embeddings via learnable query tokens, which subsequently serve as conditioning signals for a diffusion model. This streamlined design effectively transfers the rich understanding and reasoning capabilities of VLMs into the visual generation process. By obviating the need for deep fusion between autoregressive and diffusion models or training from scratch, MMCORE significantly reduces computational overhead while maintaining high-fidelity synthesis. MMCORE seamlessly integrates text-to-image synthesis with interleaved image generation, demonstrating robust multimodal comprehension in complex scenarios such as spatial reasoning and visual grounding. Comprehensive evaluations indicate that MMCORE consistently outperforms state-of-the-art baselines across a broad spectrum of text-to-image and single/multi-image editing benchmarks.

Zijie Li, Yichun Shi, Jingxiang Sun +8

ByteDance Seed

Unified Multimodal ModelsConditional Image GenerationMultimodal GenerationDiffusion-Based Image Editing
AskPDF
Apr 20, 2026

Culture-Aware Humorous Captioning: Multimodal Humor Generation across Cultural Contexts

Recent multimodal large language models have shown promising ability in generating humorous captions for images, yet they still lack stable control over explicit cultural context, making it difficult to jointly maintain image relevance, contextual appropriateness, and humor quality under a specified cultural background. To address this limitation, we introduce a new multimodal generation task, culture-aware humorous captioning, which requires a model to generate a humorous caption conditioned on both an input image and a target cultural context. Captions generated under different cultural contexts are not expected to share the same surface form, but should remain grounded in similar visual situations or humorous rationales.To support this task, we establish a six-dimensional evaluation framework covering image relevance, contextual fit, semantic richness, reasonableness, humor, and creativity. We further propose a staged alignment framework that first initializes the model with high-resource supervision under the Western cultural context, then performs multi-dimensional preference alignment via judge-based GRPO with a Degradation-aware Prototype Repulsion Constraint to mitigate reward hacking in open-ended generation, and finally adapts the model to the Eastern cultural context with a small amount of supervision. Experimental results show that our method achieves stronger overall performance under the proposed evaluation framework, with particularly large gains in contextual fit and a better balance between image relevance and humor under cultural constraints.

Run Xu, Lu Li, Rongzhao Zhang +1

Nanyang Technological University · Tongji University · Shanghai Artificial Intelligence Laboratory

Image CaptioningMultimodal GenerationMultimodal Model Evaluation
AskPDF
Apr 18, 2026

CogGen: A Cognitively Inspired Recursive Framework for Deep Research Report Generation

The autonomous synthesis of deep research reports represents a critical frontier for Large Language Models (LLMs), demanding sophisticated information orchestration and non-linear narrative logic. Current approaches rely on rigid predefined linear workflows, which cause error accumulation, preclude global restructuring from subsequent insights, and ultimately limit in-depth multimodal fusion and report quality. We propose CogGen, a Cognitively inspired recursive framework for deep research report Generation. Leveraging a Hierarchical Recursive Architecture to simulate cognitive writing, CogGen enables flexible planning and global restructuring. To extend this recursivity to multimodal content, we introduce Abstract Visual Representation (AVR): a concise intent-driven language that iteratively refines visual-text layouts without pixel-level regeneration overhead. We further present CLEF, a Cognitive Load Evaluation Framework, and curate a new benchmark from Our World in Data (OWID). Extensive experiments show CogGen achieves state-of-the-art results among open-source systems, generating reports comparable to professional analysts' outputs and surpassing Gemini Deep Research. Our code and dataset are available at https://github.com/NJUNLP/CogGen.

Kuo Tian, Pengfei Sun, Zhen Wu +2

National Key Laboratory for Novel Software Technology, Nanjing University, China · Nanjing Haodun Technology Development Co., Ltd. · School of Artificial Intelligence, Nanjing University, China

Multimodal GenerationAutonomous Research Agents
AskPDF
Apr 17, 2026

Cross-Modal Generation: From Commodity WiFi to High-Fidelity mmWave and RFID Sensing

AIGC has shown remarkable success in CV and NLP, and has recently demonstrated promising potential in the wireless domain. However, significant data imbalance exists across RF modalities, with abundant WiFi data but scarce mmWave and RFID data due to high acquisition cost. This makes it difficult to train high-quality generative models for these data-scarce modalities. In this work, we propose RF-CMG, a diffusion-based cross-modal generative method that leverages data-rich WiFi signals to synthesize high-fidelity RF data for scarce modalities including mmWave and RFID. The key insight of RF-CMG is to decouple cross-modal generation into high-frequency guidance and low-frequency constraint, which respectively learn high-frequency distribution from limited target modality data and preserve the underlying physical structure via low-frequency constraints during generation. On this basis, we introduce a Modality-Guided Embedding (MGE) module to steer the reverse diffusion trajectory toward the target high-frequency distribution, and a Low-Frequency Modality Consistency (LFMC) module to progressively enforce low-frequency constraints to suppress the accumulation of source-modality structural biases during inference, enabling high-quality target-modality generation. Performance comparison with several prevalent generative models demonstrates that RF-CMG achieves superior performance in synthesizing RFID and mmWave signals. We further showcase the effectiveness of the data generated by RF-CMG in gesture recognition tasks, and analyze the impact of the proportion of synthetic data on downstream performance.

Zhixiong Yang, Long Jing, Yao Li +3

Tsinghua University Beijing, China

Synthetic Data GenerationWireless CommunicationsMultimodal GenerationMultimodal Diffusion Models
AskPDF
Apr 17, 2026

BOOKAGENT: Orchestrating Safety-Aware Visual Narratives via Multi-Agent Cognitive Calibration

Recent advancements in Large Generative Models (LGMs) have revolutionized multi-modal generation. However, generating illustrated storybooks remains an open challenge, where prior works mainly decompose this task into separate stages, and thus, holistic multi-modal grounding remains limited. Besides, while safety alignment is studied for text- or image-only generation, existing works rarely integrate child-specific safety constraints into narrative planning and sequence-level multi-modal verification. To address these limitations, we propose BookAgent, a safety-aware multi-agent collaboration framework designed for high-quality, safety-aware visual narratives. Different from prior story visualization models that assume a fixed storyline sequence, BookAgent targets end-to-end storybook synthesis from a user draft by jointly planning, scripting, illustrating, and globally repairing inconsistencies. To ensure precise multi-modal grounding, BookAgent dynamically calibrates page-level alignment between textual scripts and visual layouts. Furthermore, BookAgent calibrates holistic consistency from the temporal dimension, by verifying-then-rectifying global inconsistencies in character identity and storytelling logic. Extensive experiments demonstrate that BookAgent significantly outperforms current methods in narrative coherence, visual consistency, and safety compliance, offering a robust paradigm for reliable agents in complex multi-modal creation. The implementation will be publicly released at https://github.com/bogao-code/BookAgent/tree/main.

Bo Gao, Chang Liu, Yuyang Miao +2

Carnegie Mellon University · University of Science and Technology of China · Imperial College London +2

Multimodal GroundingMulti-Agent CollaborationMultimodal Generation
AskPDF
Apr 16, 2026

MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation

The rapid progress of Artificial Intelligence Generated Content (AIGC) tools enables images, videos, and visualizations to be created on demand for webpage design, offering a flexible and increasingly adopted paradigm for modern UI/UX. However, directly integrating such tools into automated webpage generation often leads to style inconsistency and poor global coherence, as elements are generated in isolation. We propose MM-WebAgent, a hierarchical agentic framework for multimodal webpage generation that coordinates AIGC-based element generation through hierarchical planning and iterative self-reflection. MM-WebAgent jointly optimizes global layout, local multimodal content, and their integration, producing coherent and visually consistent webpages. We further introduce a benchmark for multimodal webpage generation and a multi-level evaluation protocol for systematic assessment. Experiments demonstrate that MM-WebAgent outperforms code-generation and agent-based baselines, especially on multimodal element generation and integration. Code & Data: https://aka.ms/mm-webagent.

Yan Li, Zezi Zeng, Yifan Yang +12

Shanghai Jiao Tong University · Xi’an Jiaotong University · Microsoft Corporation +1

Web Application GenerationWeb Agent BenchmarksMultimodal GenerationMultimodal AgentsWeb Agents
AskPDF
Apr 16, 2026

ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling

Recent advances in video-to-audio (V2A) generation enable high-quality audio synthesis from visual content, yet achieving robust and fine-grained controllability remains challenging. Existing methods suffer from weak textual controllability under visual-text conflict and imprecise stylistic control due to entangled temporal and timbre information in reference audio. Moreover, the lack of standardized benchmarks limits systematic evaluation. We propose ControlFoley, a unified multimodal V2A framework that enables precise control over video, text, and reference audio. We introduce a joint visual encoding paradigm that integrates CLIP with a spatio-temporal audio-visual encoder to improve alignment and textual controllability. We further propose temporal-timbre decoupling to suppress redundant temporal cues while preserving discriminative timbre features. In addition, we design a modality-robust training scheme with unified multimodal representation alignment (REPA) and random modality dropout. We also present VGGSound-TVC, a benchmark for evaluating textual controllability under varying degrees of visual-text conflict. Extensive experiments demonstrate state-of-the-art performance across multiple V2A tasks, including text-guided, text-controlled, and audio-controlled generation. ControlFoley achieves superior controllability under cross-modal conflict while maintaining strong synchronization and audio quality, and shows competitive or better performance compared to an industrial V2A system. Code, models, datasets, and demos are available at: https://github.com/xiaomi-research/controlfoley.

Jianxuan Yang, Xinyue Guo, Zhi Cheng +10

MiLM Plus, Xiaomi Inc. · Wuhan University

Audio-Video GenerationMultimodal GenerationAudio-Visual Alignment
AskPDF
Apr 15, 2026

Seedance 2.0: Advancing Video Generation for World Complexity

Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro, Seedance 2.0 adopts a unified, highly efficient, and large-scale architecture for multi-modal audio-video joint generation. This allows it to support four input modalities: text, image, audio, and video, by integrating one of the most comprehensive suites of multi-modal content reference and editing capabilities available in the industry to date. It delivers substantial, well-rounded improvements across all key sub-dimensions of video and audio generation. In both expert evaluations and public user tests, the model has demonstrated performance on par with the leading levels in the field. Seedance 2.0 supports direct generation of audio-video content with durations ranging from 4 to 15 seconds, with native output resolutions of 480p and 720p. For multi-modal inputs as reference, its current open platform supports up to 3 video clips, 9 images, and 3 audio clips. In addition, we provide Seedance 2.0 Fast version, an accelerated variant of Seedance 2.0 designed to boost generation speed for low-latency scenarios. Seedance 2.0 has delivered significant improvements to its foundational generation capabilities and multi-modal generation performance, bringing an enhanced creative experience for end users.

Team Seedance, De Chen, Liyang Chen +168

Audio-Video GenerationMultimodal Video GenerationMultimodal GenerationT2V GenerationImage-to-Video GenerationVideo-Reference Video Generation
AskPDF