Audio-Visual Generation

We present **Captain Cinema**, a generation framework for short movie generation. Given a detailed textual description of a movie storyline, our approach firstly generates a sequence of keyframes that outline the entire narrative, which ensures long-range coherence in both the storyline and visual appearance (e.g., scenes and characters). We refer to this step as top-down keyframe planning. These keyframes then serve as conditioning signals for a video synthesis model, which supports long context learning, to produce the spatio-temporal dynamics between them. This step is referred to as bottom-up video synthesis. To support stable and efficient generation of multi-scene long narrative cinematic works, we introduce an interleaved training strategy for Multimodal Diffusion Transformers (MM-DiT), specifically adapted for long-context video data. Our model is trained on a curated cinematic dataset consisting of interleaved samples for video generation. Our experiments demonstrate that Captain Cinema performs favorably in the automated creation of visually coherent and narratively consistent short films.

The use of latent diffusion models (LDMs) such as Stable Diffusion has significantly improved the perceptual quality of All-in-One image Restoration (AiOR) methods, while also enhancing their generalization capabilities. However, these LDM-based frameworks suffer from slow inference due to their iterative denoising process, rendering them impractical for time-sensitive applications. Visual autoregressive modeling (VAR), a recently introduced approach for image generation, performs scale-space autoregression and achieves comparable performance to that of state-of-the-art diffusion transformers with drastically reduced computational costs. Moreover, our analysis reveals that coarse scales in VAR primarily capture degradations while finer scales encode scene detail, simplifying the restoration process. Motivated by this, we propose RestoreVAR, a novel VAR-based generative approach for AiOR that significantly outperforms LDM-based models in restoration performance while achieving over $\mathbf{10\times}$ faster inference. To optimally exploit the advantages of VAR for AiOR, we propose architectural modifications and improvements, including intricately designed cross-attention mechanisms and a latent-space refinement module, tailored for the AiOR task. Extensive experiments show that RestoreVAR achieves state-of-the-art performance among generative AiOR methods, while also exhibiting strong generalization capabilities. The code will be made publicly available after the review process.

We present \textsc{GenRep}, a unified image understanding and synthesis model that jointly conducts discriminative learning and generative modeling in one training session. By leveraging Monte Carlo approximation, \textsc{GenRep} distills distributional knowledge embedded in diffusion models to guide the discriminative learning for visual perception tasks. Simultaneously, a semantic-driven image generation process is established, where high-level semantics learned from perception tasks can be used to inform image synthesis, creating a positive feedback loop for mutual boosts. Moreover, to reconcile the learning process for both tasks, a gradient alignment strategy is proposed to symmetrically modify the optimization directions of perception and generation losses. These designs empower \textsc{GenRep} to be a versatile and powerful model that achieves top-leading performance on both image understanding and generation benchmarks. Code will be released after acceptance.

This paper introduces JavisDiT, a novel Joint Audio-Video Diffusion Trans- former designed for synchronized audio-video generation (JAVG). Based on the powerful Diffusion Transformer (DiT) architecture, JavisDiT simultaneously generates high-quality audio and video content from open-ended user prompts in a unified framework. To ensure audio-video synchronization, we introduce a fine-grained spatio-temporal alignment mechanism through a Hierarchical Spatial-Temporal Synchronized Prior (HiST-Sypo) Estimator. This module extracts both global and fine-grained spatio-temporal priors, guiding the synchronization between the visual and auditory components. Furthermore, we propose a new benchmark, JavisBench, which consists of 10,140 high-quality text-captioned sounding videos and focuses on synchronization evaluation in diverse and complex real-world scenarios. Further, we specifically devise a robust metric for measuring the synchrony between generated audio-video pairs in real-world content. Experimental results demonstrate that JavisDiT significantly outperforms existing methods by ensuring both high-quality generation and precise synchronization, setting a new standard for JAVG tasks. Our code, model, and data are available at https://javisverse.github.io/JavisDiT-page/.

While preference optimization is crucial for improving visual generative models, how to effectively scale this paradigm for visual generation remains largely unexplored. Current open-source preference datasets typically contain substantial conflicting preference patterns, where winners excel in some dimensions but underperform in others. Naively optimizing on such noisy datasets fails to learn meaningful preferences, fundamentally hindering effective scaling. To enhance the robustness of preference algorithms against noise, we propose Poly-DPO, which extends the DPO objective with an additional polynomial term that dynamically adjusts model confidence during training based on dataset characteristics, enabling effective learning across diverse data distributions from noisy to trivially simple patterns. Beyond biased patterns, existing datasets suffer from low resolution, limited prompt diversity, and imbalanced distributions. To facilitate large-scale visual preference optimization by tackling key data bottlenecks, we construct ViPO, a massive-scale preference dataset with 1M image pairs (1024px) across five categories and 300K video pairs (720p+) across three categories. Leveraging state-of-the-art generative models and diverse prompts ensures consistent, reliable preference signals with balanced distributions. Remarkably, when applying Poly-DPO to our high-quality dataset, the optimal configuration converges to standard DPO. This convergence validates both our dataset quality and Poly-DPO's adaptive nature: sophisticated optimization becomes unnecessary with sufficient data quality, yet remains valuable for imperfect datasets. We comprehensively validate our approach across various visual generation models. On noisy datasets like Pick-a-Pic V2, Poly-DPO achieves 6.87\% and 2.32\% gains over Diffusion-DPO on GenEval for SD1.5 and SDXL, respectively. For our high-quality VIPO dataset, models achieve performance far exceeding those trained on existing open-source preference datasets. These results confirm that addressing both algorithmic adaptability and data quality is essential for scaling visual preference optimization. All models and datasets will be released.

Audiovisual video captioning aims to generate semantically rich descriptions with temporal alignment between visual and auditory events, thereby benefiting both video understanding and generation. In this paper, we present **AVoCaDO**, a powerful audiovisual video captioner driven by the temporal orchestration between audio and visual modalities. We propose a two-stage post-training pipeline: (1) **AVoCaDO SFT**, which fine-tunes the model on a newly curated dataset of 107K high-quality, temporally-aligned audiovisual captions; and (2) **AVoCaDO GRPO**, which leverages tailored reward functions to further enhance temporal coherence and dialogue accuracy while regularizing caption length and reducing collapse. Experimental results demonstrate that AVoCaDO significantly outperforms existing open-source models across four audiovisual video captioning benchmarks, and also achieves competitive performance on the VDC benchmark under visual-only settings. The model will be made publicly available to facilitate future research in audiovisual video understanding and generation.

The advancement of Large Language Model (LLM)-powered agents has enabled automated task processing through reasoning and tool invocation capabilities. However, existing frameworks often operate under the idealized assumption that tool executions are invariably successful, relying solely on textual descriptions that fail to distinguish precise performance boundaries and cannot adapt to iterative tool updates. This gap introduces uncertainty in planning and execution, particularly in domains like visual content generation (AIGC), where nuanced tool performance significantly impacts outcomes. To address this, we propose PerfGuard, a performance-aware agent framework for visual content generation that systematically models tool performance boundaries and integrates them into task planning and scheduling. Our framework introduces three core mechanisms: (1) Performance-Aware Selection Modeling (PASM), which replaces generic tool descriptions with a multi-dimensional scoring system based on fine-grained performance evaluations; (2) Adaptive Preference Update (APU), which dynamically optimizes tool selection by comparing theoretical rankings with actual execution rankings; and (3) Capability-Aligned Planning Optimization (CAPO), which guides the planner to generate subtasks aligned with performance-aware strategies. Experimental comparisons against state-of-the-art methods demonstrate PerfGuard’s advantages in tool selection accuracy, execution reliability, and alignment with user intent, validating its robustness and practical utility for complex AIGC tasks.

Massive Activations (MAs) are a well-documented phenomenon across Transformer architectures, and prior studies in both LLMs and ViTs have shown that they play a substantial role in shaping model behavior. However, the nature and function of MAs within Diffusion Transformers (DiTs) remain largely unexplored. In this work, we systematically investigate these activations to elucidate their role in visual generation. We found that these massive activations occur across all spatial tokens, and their distribution is modulated by the input timestep embeddings. Importantly, our investigations further demonstrate that these massive activations play a key role in local detail synthesis, while having minimal impact on the overall semantic content of output. Building on these insights, we propose Detail Guidance (DG), a MAs-driven, training-free self-guidance strategy to explicitly enhance local detail fidelity for DiTs. Specifically, DG constructs a degraded ``detail-deficient'' model by disrupting MAs and leverages it to guide the original network toward higher-quality detail synthesis. Our DG can seamlessly integrate with Classifier-Free Guidance (CFG), enabling joint enhancement of detail fidelity and prompt alignment. Extensive experiments demonstrate that our DG consistently improves local detail quality across various pre-trained DiTs (\eg, SD3, SD3.5, and Flux).

Text-to-video and image-to-video generation have made rapid progress in visual quality, but they remain limited in controlling the precise timing of motion. In contrast, audio provides temporal cues aligned with video motion, making it a promising condition for temporally controlled video generation. However, existing audio-to-video (A2V) models struggle with fine-grained synchronization due to indirect conditioning mechanisms or limited temporal modeling capacity. We present Syncphony, which generates 380×640 resolution, 24fps videos synchronized with diverse audio inputs. Our approach builds upon a pre-trained video backbone and incorporates two key components to improve synchronization: (1) Motion-aware Loss, which emphasizes learning at high-motion regions; (2) Audio Sync Guidance, which guides the full model using a visually aligned off-sync model without audio layers to better exploit audio cues at inference while maintaining visual quality. To evaluate synchronization, we propose CycleSync, a video-to-audio-based metric that measures the amount of motion cues in the generated video to reconstruct the original audio. Experiments on AVSync15 and The Greatest Hits datasets demonstrate that Syncphony outperforms existing methods in both synchronization accuracy and visual quality.

Creating novel images by fusing visual cues from multiple sources is a fundamental yet underexplored problem in image-to-image generation, with broad applications in artistic creation, virtual reality and visual media. Existing methods often face two key challenges: coexistent generation, where multiple objects are simply juxtaposed without true integration, and bias generation, where one object dominates the output due to semantic imbalance. To address these issues, we propose **Visual Mixing Diffusion (VMDiff)**, a simple yet effective diffusion-based framework that synthesizes a single, coherent object by integrating two input images at both noise and latent levels. Our approach comprises: (1) a **hybrid sampling process** that combines guided denoising, inversion, and spherical interpolation with adjustable parameters to achieve structure-aware fusion, mitigating coexistent generation; and (2) an **efficient adaptive adjustment module**, which introduces a novel similarity-based score to automatically and adaptively search for optimal parameters, countering semantic bias. Experiments on a curated benchmark of 780 concept pairs demonstrate that our method outperforms strong baselines in visual quality, semantic consistency, and human-rated creativity.

The rapid development of visual generative models raises the need for more scalable and human-aligned evaluation methods. While the crowdsourced Arena platforms offer human preference assessments by collecting human votes, they are costly and time-consuming, inherently limiting their scalability. Leveraging vision-language model (VLMs) as substitutes for manual judgments presents a promising solution. However, the inherent hallucinations and biases of VLMs hinder alignment with human preferences, thus compromising evaluation reliability. Additionally, the static evaluation approach lead to low efficiency. In this paper, we propose K-Sort Eval, a reliable and efficient VLM-based evaluation framework that integrates posterior correction and dynamic matching. Specifically, we curate a high-quality dataset from thousands of human votes in K-Sort Arena, with each instance containing the outputs and rankings of K models. When evaluating a new model, it undergoes (K+1)-wise free-for-all comparisons with existing models, and the VLM provide the rankings. To enhance alignment and reliability, we propose a posterior correction method, which adaptively corrects the posterior probability in Bayesian updating based on the consistency between the VLM prediction and human supervision. Moreover, we propose a dynamic matching strategy, which balances uncertainty and diversity to maximize the expected benefit of each comparison, thus ensuring more efficient evaluation. Extensive experiments show that K-Sort Eval delivers evaluation results consistent with K-Sort Arena, typically requiring fewer than 90 model runs, demonstrating both its efficiency and reliability. The dataset and code are publicly available.

End-to-end human animation with rich multi-modal conditions, e.g., text, image and audio has achieved remarkable advancements in recent years. However, most existing methods could only animate a single subject and inject conditions in a global manner, ignoring scenarios that multiple concepts could appears in the same video with rich human-human interactions and human-object interactions. Such global assumption prevents precise and per-identity control of multiple concepts including humans and objects, therefore hinders applications. In this work, we discard the single-entity assumption and introduce a novel framework that enforces strong, region‑specific binding of conditions from modalities to each identity's spatiotemporal footprint. Given reference images of multiple concepts, our method could automatically infer layout information by leveraging a mask predictor to match appearance cues between the denoised video and each reference appearance. Furthermore, we inject local audio condition into its corresponding region to ensure layout-aligned modality matching in a iterative manner. This design enables the high-quality generation of human dialogue videos between two to three people or video customization from multiple reference images. Empirical results and ablation studies validate the effectiveness of our explicit layout control for multi-modal conditions compared to implicit counterparts and other existing methods.

We introduce ARPG, a novel visual Autoregressive model that enables Randomized Parallel Generation, addressing the inherent limitations of conventional raster-order approaches, which hinder inference efficiency and zero-shot generalization due to their sequential, predefined token generation order. Our key insight is that effective random-order modeling necessitates explicit guidance for determining the position of the next predicted token. To this end, we propose a novel decoupled decoding framework that decouples positional guidance from content representation, encoding them separately as queries and key-value pairs. By directly incorporating this guidance into the causal attention mechanism, our approach enables fully random-order training and generation, eliminating the need for bidirectional attention. Consequently, ARPG readily generalizes to zero-shot tasks such as image in-painting, out-painting, and resolution expansion. Furthermore, it supports parallel inference by concurrently processing multiple queries using a shared KV cache. On the ImageNet-1K 256 benchmark, our approach attains an FID of 1.83 with only 32 sampling steps, achieving over a 30 times speedup in inference and and a 75 percent reduction in memory consumption compared to representative recent autoregressive models at a similar scale.

Audio and music generation based on flexible multimodal control signals is a widely applicable topic, with the following key challenges: 1) a unified multimodal modeling framework, and 2) large-scale, high-quality training data. As such, we propose AudioX, a unified framework for anything-to-audio generation that integrates varied multimodal conditions (i.e., text, video, image, and audio signals) in this work. The core design in this framework is a Multimodal Adaptive Fusion module, which enables the effective fusion of diverse multimodal inputs, enhancing cross-modal alignment and improving overall generation quality. To train this unified model, we construct a large-scale, high-quality dataset, IF-caps, comprising over 7 million samples curated through a structured data annotation pipeline. This dataset provides comprehensive supervision for multimodal-conditioned audio generation. We benchmark AudioX against state-of-the-art methods across a wide range of tasks, finding that our model achieves superior performance, especially in text-to-audio and text-to-music generation. These results demonstrate our method is capable of audio generation under multimodal control signals, showing powerful instruction-following potential. We will release the code, model, and dataset.

Masked Autoregressive (MAR) models promise better efficiency in visual generation than continuous autoregressive (AR) models for the ability of parallel generation, yet their acceleration potential remains constrained by the modeling complexity of spatially correlated visual tokens in a single step. To address this limitation, we introduce Generation then Reconstruction (GtR), a training-free hierarchical sampling strategy that decomposes generation into two stages: structure generation establishing global semantic scaffolding, followed by detail reconstruction efficiently completing remaining tokens. Assuming that it is more difficult to create an image from scratch than to complement images based on a basic image framework, GtR is designed to achieve acceleration by computing the reconstruction stage quickly while maintaining the generation quality by computing the generation stage slowly. Moreover, observing that tokens on the details of an image often carry more semantic information than tokens in the salient regions, we further propose Frequency-Weighted Token Selection (FTS) to offer more computation budget to tokens on image details, which are localized based on the energy of high frequency information. Extensive experiments on ImageNet class-conditional and text-to-image generation demonstrate 3.72$\times$ speedup on MAR-H while maintaining comparable quality (e.g., FID: 1.59, IS: 304.4 vs. original 1.59, 299.1), substantially outperforming existing acceleration methods across various model scales and generation tasks. Our codes have been released in supplementary materials and will be released on Github.

Large Language Models (LLMs), despite being trained on text alone, surprisingly develop rich visual priors. These priors allow latent visual capabilities to be unlocked for vision tasks with a relatively small amount of multimodal data, and to perform symbolic visual generation tasks without ever having seen an image. Through systematic analysis, we reveal that visual priors—the implicit, emergent knowledge about the visual world acquired during language pre-training—are composed of separable perception and reasoning priors with unique scaling trends and origins. We show that an LLM's latent visual reasoning ability is predominantly developed by pre-training on reasoning-centric data (\eg, code, math, academia) and scales progressively. This reasoning prior acquired from language pre-training is transferable and universally applicable to visual reasoning. In contrast, the perception prior emerges more diffusely from broad corpora, and perception ability is more sensitive to the vision encoder and visual instruction tuning data. In parallel, text describing the visual world proves crucial, though its performance impact saturates rapidly. Leveraging these insights, we propose a data-centric recipe for pre-training vision-aware LLMs and verify it in 1T token scale pre-training. Our findings are grounded in over 100 controlled experiments consuming 500,000 GPU-hours, spanning the full MLLM construction pipeline—from LLM pre-training to visual alignment and supervised multimodal fine-tuning—across five model scales, a wide range of data categories and mixtures, and multiple adaptation setups. Along with our main findings, we also propose and investigate several hypotheses, and introduce a Multi-Level Existence Bench (MLE-Bench) to facilitate future research. Together, this work provides a new way of deliberately cultivating visual priors from language pre-training, paving the way for the next generation of multimodal LLMs. We recommend a visit to our anonymous project page (https://anonymouspaperweb.github.io/lsbs/) for an interactive reading.

We present LongLive, a frame-level autoregressive (AR) framework for real-time and interactive long video generation. Long video generation presents challenges in both efficiency and quality. Diffusion and Diffusion-Forcing models can produce high-quality videos but suffer from low efficiency due to bidirectional attention. Causal attention AR models support KV caching for faster inference but often degrade in quality on long videos due to memory challenges during long-video training. In addition, beyond static prompt-based generation, interactive capabilities, such as streaming prompt inputs, are critical for dynamic content creation, enabling users to guide narratives in real time. This interactive requirement significantly increases the complexity, especially in ensuring visual consistency and semantic coherence during prompt transitions. To address these challenges, LongLive adopts a causal, frame-level AR design that integrates a KV-recache mechanism that refreshes cached states with the new prompt for smooth, adherent switches streaming long tuning to enable long video training and to align training and inference (train-long–test-long); and short window attention paired with a frame-level attention sink, preserving long-range consistency while enabling faster generation. With these key designs, LongLive fine-tunes a 1.3B-parameter short-clip model to minute-long generation in just 32 GPU-days. At inference, LongLive sustains 20.7 FPS on a single NVIDIA H100, achieves strong performance on VBench in both short- and long-video settings. LongLive supports up to 240-second videos on a single H100 GPU. With FP8 quantization, LongLive boosts inference to 24.8 FPS with marginal quality loss.

Essential to visual generation is efficient modeling of visual data priors. Conventional next-token prediction methods define the process as learning the conditional probability distribution of successive tokens. Recently, next-scale prediction methods redefine the process to learn the distribution over multi-scale representations, significantly reducing generation latency. However, these methods condition each scale on all previous scales and require each token to consider all preceding tokens, exhibiting scale and spatial redundancy. To better model the distribution by mitigating redundancy, we propose Markovian Visual AutoRegressive modeling (MVAR), a novel autoregressive framework that introduces scale and spatial Markov assumptions to reduce the complexity of conditional probability modeling. Specifically, we introduce a scale-Markov trajectory that only takes as input the features of adjacent preceding scale for next-scale prediction, enabling the adoption of a parallel training strategy that significantly reduces GPU memory consumption. Furthermore, we propose spatial-Markov attention, which restricts the attention of each token to a localized neighborhood of size (k) at corresponding positions on adjacent scales, rather than attending to every token across these scales, for the pursuit of reduced modeling complexity. Building on these improvements, we reduce the computational complexity of attention calculation from (\mathcal{O}(N^{2})) to (\mathcal{O}(N k)), enabling training with just eight NVIDIA RTX 4090 GPUs and eliminating the need for KV cache during inference. Extensive experiments on ImageNet demonstrate that MVAR achieves comparable or superior performance with both small model trained from scratch and large fine-tuned models, while reducing the average GPU memory footprint by 3.0x.

AutoRegressive Visual Generation (ARVG) models retain an architecture compatible with language models, while achieving performance comparable to diffusion-based models. Quantization is commonly employed in neural networks to reduce model size and computational latency. However, applying quantization to ARVG remains largely underexplored, and existing quantization methods fail to generalize effectively to ARVG models. In this paper, we explore this issue and identify three key challenges: (1) severe outliers at channel-wise level, (2) highly dynamic activations at token-wise level, and (3) mismatched distribution information at sample-wise level. To these ends, we propose PTQ4ARVG, a training-free post-training quantization (PTQ) framework consisting of: (1) Gain-Projected Scaling (GPS) mitigates the channel-wise outliers, which expands the quantization loss via a Taylor series to quantify the gain of scaling for activation-weight quantization, and derives the optimal scaling factor through differentiation. (2) Static Token-Wise Quantization (STWQ) leverages the inherent properties of ARVG, fixed token length and position-invariant distribution across samples, to address token-wise variance without incurring dynamic calibration overhead. (3) Distribution-Guided Calibration (DGC) selects samples that contribute most to distributional entropy, eliminating the sample-wise distribution mismatch. Extensive experiments show that PTQ4ARVG can effectively quantize the ARVG family models to 8-bit and 6-bit while maintaining competitive performance.

Diffusion Transformers (DiTs) typically use the same patch size for $\operatorname{Patchify}$ across timesteps, enforcing a constant token budget across timesteps. In this paper, we introduce Pyramidal Patchification Flow (PPFlow), which reduces the number of tokens for high-noise timesteps to improve the sampling efficiency. The idea is simple: use larger patches at higher-noise timesteps and smaller patches at lower-noise timesteps. The implementation is easy: share the DiT's transformer blocks across timesteps, and learn separate linear projections for different patch sizes in $\operatorname{Patchify}$ and $\operatorname{Unpatchify}$. Unlike Pyramidal Flow that operates on pyramid representations,, our approach operates over full latent representations, eliminating trajectory ``jump points'', and thus avoiding re-noising tricks for sampling. Training from pretrained SiT-XL/2 requires only $+8.9\%$ additional training FLOPs and delivers $2.02\times$ denoising speedups with image generation quality kept; training from scratch achieves comparable sampling speedup, e.g., $2.04\times$ speedup in SiT-B. Training from text-to-image model FLUX.1, PPFlow can achieve $1.61 - 1.86 \times$ speedup from 512 to 2048 resolution with comparable quality.