Hu Yu

Man Zhou, Hu Yu, Jie Huang et al.

Existing convolutional neural networks widely adopt spatial down-/up-sampling for multi-scale modeling. However, spatial up-sampling operators (\emph{e.g.}, interpolation, transposed convolution, and un-pooling) heavily depend on local pixel attention, incapably exploring the global dependency. In contrast, the Fourier domain obeys the nature of global modeling according to the spectral convolution theorem. Unlike the spatial domain that performs up-sampling with the property of local similarity, up-sampling in the Fourier domain is more challenging as it does not follow such a local property. In this study, we propose a theoretically sound Deep Fourier Up-Sampling (FourierUp) to solve these issues. We revisit the relationships between spatial and Fourier domains and reveal the transform rules on the features of different resolutions in the Fourier domain, which provide key insights for FourierUp's designs. FourierUp as a generic operator consists of three key components: 2D discrete Fourier transform, Fourier dimension increase rules, and 2D inverse Fourier transform, which can be directly integrated with existing networks. Extensive experiments across multiple computer vision tasks, including object detection, image segmentation, image de-raining, image dehazing, and guided image super-resolution, demonstrate the consistent performance gains obtained by introducing our FourierUp.

Hu Yu, Li Shen, Jie Huang et al.

Denoising diffusion models have emerged as a dominant approach for image generation, however they still suffer from slow convergence in training and color shift issues in sampling. In this paper, we identify that these obstacles can be largely attributed to bias and suboptimality inherent in the default training paradigm of diffusion models. Specifically, we offer theoretical insights that the prevailing constant loss weight strategy in $ε$-prediction of diffusion models leads to biased estimation during the training phase, hindering accurate estimations of original images. To address the issue, we propose a simple but effective weighting strategy derived from the unlocked biased part. Furthermore, we conduct a comprehensive and systematic exploration, unraveling the inherent bias problem in terms of its existence, impact and underlying reasons. These analyses contribute to advancing the understanding of diffusion models. Empirical results demonstrate that our method remarkably elevates sample quality and displays improved efficiency in both training and sampling processes, by only adjusting loss weighting strategy. The code is released publicly at \url{https://github.com/yuhuUSTC/Debias}

Hu Yu, Jie Huang, Kaiwen Zheng et al.

Image dehazing is quite challenging in dense-haze scenarios, where quite less original information remains in the hazy image. Though previous methods have made marvelous progress, they still suffer from information loss in content and color in dense-haze scenarios. The recently emerged Denoising Diffusion Probabilistic Model (DDPM) exhibits strong generation ability, showing potential for solving this problem. However, DDPM fails to consider the physics property of dehazing task, limiting its information completion capacity. In this work, we propose DehazeDDPM: A DDPM-based and physics-aware image dehazing framework that applies to complex hazy scenarios. Specifically, DehazeDDPM works in two stages. The former stage physically models the dehazing task with the Atmospheric Scattering Model (ASM), pulling the distribution closer to the clear data and endowing DehazeDDPM with fog-aware ability. The latter stage exploits the strong generation ability of DDPM to compensate for the haze-induced huge information loss, by working in conjunction with the physical modelling. Extensive experiments demonstrate that our method attains state-of-the-art performance on both synthetic and real-world hazy datasets.

Hu Yu, Jie Huang, Yajing Liu et al.

Deep learning-based source dehazing methods trained on synthetic datasets have achieved remarkable performance but suffer from dramatic performance degradation on real hazy images due to domain shift. Although certain Domain Adaptation (DA) dehazing methods have been presented, they inevitably require access to the source dataset to reduce the gap between the source synthetic and target real domains. To address these issues, we present a novel Source-Free Unsupervised Domain Adaptation (SFUDA) image dehazing paradigm, in which only a well-trained source model and an unlabeled target real hazy dataset are available. Specifically, we devise the Domain Representation Normalization (DRN) module to make the representation of real hazy domain features match that of the synthetic domain to bridge the gaps. With our plug-and-play DRN module, unlabeled real hazy images can adapt existing well-trained source networks. Besides, the unsupervised losses are applied to guide the learning of the DRN module, which consists of frequency losses and physical prior losses. Frequency losses provide structure and style constraints, while the prior loss explores the inherent statistic property of haze-free images. Equipped with our DRN module and unsupervised loss, existing source dehazing models are able to dehaze unlabeled real hazy images. Extensive experiments on multiple baselines demonstrate the validity and superiority of our method visually and quantitatively.

Inclusion AI, Biao Gong, Cheng Zou et al.

We introduce Ming-Lite-Uni, an open-source multimodal framework featuring a newly designed unified visual generator and a native multimodal autoregressive model tailored for unifying vision and language. Specifically, this project provides an open-source implementation of the integrated MetaQueries and M2-omni framework, while introducing the novel multi-scale learnable tokens and multi-scale representation alignment strategy. By leveraging a fixed MLLM and a learnable diffusion model, Ming-Lite-Uni enables native multimodal AR models to perform both text-to-image generation and instruction based image editing tasks, expanding their capabilities beyond pure visual understanding. Our experimental results demonstrate the strong performance of Ming-Lite-Uni and illustrate the impressive fluid nature of its interactive process. All code and model weights are open-sourced to foster further exploration within the community. Notably, this work aligns with concurrent multimodal AI milestones - such as ChatGPT-4o with native image generation updated in March 25, 2025 - underscoring the broader significance of unified models like Ming-Lite-Uni on the path toward AGI. Ming-Lite-Uni is in alpha stage and will soon be further refined.

Zizheng Yang, Hu Yu, Bing Li et al.

Diffusion models have recently been investigated as powerful generative solvers for image dehazing, owing to their remarkable capability to model the data distribution. However, the massive computational burden imposed by the retraining of diffusion models, coupled with the extensive sampling steps during the inference, limit the broader application of diffusion models in image dehazing. To address these issues, we explore the properties of hazy images in the semantic latent space of frozen pre-trained diffusion models, and propose a Diffusion Latent Inspired network for Image Dehazing, dubbed DiffLI$^2$D. Specifically, we first reveal that the semantic latent space of pre-trained diffusion models can represent the content and haze characteristics of hazy images, as the diffusion time-step changes. Building upon this insight, we integrate the diffusion latent representations at different time-steps into a delicately designed dehazing network to provide instructions for image dehazing. Our DiffLI$^2$D avoids re-training diffusion models and iterative sampling process by effectively utilizing the informative representations derived from the pre-trained diffusion models, which also offers a novel perspective for introducing diffusion models to image dehazing. Extensive experiments on multiple datasets demonstrate that the proposed method achieves superior performance to existing image dehazing methods. Code is available at https://github.com/aaaasan111/difflid.

Hangjie Yuan, Weihua Chen, Jun Cen et al.

Autoregressive large language models (LLMs) have unified a vast range of language tasks, inspiring preliminary efforts in autoregressive video generation. Existing autoregressive video generators either diverge from standard LLM architectures, depend on bulky external text encoders, or incur prohibitive latency due to next-token decoding. In this paper, we introduce Lumos-1, an autoregressive video generator that retains the LLM architecture with minimal architectural modifications. To inject spatiotemporal correlations in LLMs, we identify the efficacy of incorporating 3D RoPE and diagnose its imbalanced frequency spectrum ranges. Therefore, we propose MM-RoPE, a RoPE scheme that preserves the original textual RoPE while providing comprehensive frequency spectra and scaled 3D positions for modeling multimodal spatiotemporal data. Moreover, Lumos-1 resorts to a token dependency strategy that obeys intra-frame bidirectionality and inter-frame temporal causality. Based on this dependency strategy, we identify the issue of frame-wise loss imbalance caused by spatial information redundancy and solve it by proposing Autoregressive Discrete Diffusion Forcing (AR-DF). AR-DF introduces temporal tube masking during training with a compatible inference-time masking policy to avoid quality degradation. By using memory-efficient training techniques, we pre-train Lumos-1 on only 48 GPUs, achieving performance comparable to EMU3 on GenEval, COSMOS-Video2World on VBench-I2V, and OpenSoraPlan on VBench-T2V. Code and models are available at https://github.com/alibaba-damo-academy/Lumos.

Jiangtong Tan, Hu Yu, Jie Huang et al.

Long video generation involves generating extended videos using models trained on short videos, suffering from distribution shifts due to varying frame counts. It necessitates the use of local information from the original short frames to enhance visual and motion quality, and global information from the entire long frames to ensure appearance consistency. Existing training-free methods struggle to effectively integrate the benefits of both, as appearance and motion in videos are closely coupled, leading to motion inconsistency and visual quality. In this paper, we reveal that global and local information can be precisely decoupled into consistent appearance and motion intensity information by applying Principal Component Analysis (PCA), allowing for refined complementary integration of global consistency and local quality. With this insight, we propose FreePCA, a training-free long video generation paradigm based on PCA that simultaneously achieves high consistency and quality. Concretely, we decouple consistent appearance and motion intensity features by measuring cosine similarity in the principal component space. Critically, we progressively integrate these features to preserve original quality and ensure smooth transitions, while further enhancing consistency by reusing the mean statistics of the initial noise. Experiments demonstrate that FreePCA can be applied to various video diffusion models without requiring training, leading to substantial improvements. Code is available at https://github.com/JosephTiTan/FreePCA.

Guohui Zhang, XiaoXiao Ma, Jie Huang et al.

Recent advances in joint audio-video generation have been remarkable, yet real-world applications demand strong per-modality fidelity, cross-modal alignment, and fine-grained synchronization. Reinforcement Learning (RL) offers a promising paradigm, but its extension to multi-objective and multi-modal joint audio-video generation remains unexplored. Notably, our in-depth analysis first reveals that the primary obstacles to applying RL in this stem from: (i) multi-objective advantages inconsistency, where the advantages of multimodal outputs are not always consistent within a group; (ii) multi-modal gradients imbalance, where video-branch gradients leak into shallow audio layers responsible for intra-modal generation; (iii) uniform credit assignment, where fine-grained cross-modal alignment regions fail to get efficient exploration. These shortcomings suggest that vanilla RL fine-tuning strategy with a single global advantage often leads to suboptimal results. To address these challenges, we propose OmniNFT, a novel modality-aware online diffusion RL framework with three key innovations: (1) Modality-wise advantage routing, which routes independent per-reward advantages to their respective modality generation branches. (2) Layer-wise gradient surgery, which selectively detaches video-branch gradients on shallow audio layers while retaining those for cross-modal interaction layers. (3) Region-wise loss reweighting, which modulates policy optimization toward critical regions related to audio-video synchronization and fine-grained alignment. Extensive experiments on JavisBench and VBench with the LTX-2 backbone demonstrate that OmniNFT achieves comprehensive improvements in audio and video perceptual quality, cross-modal alignment, and audio-video synchronization.

Hu Yu, Hang Xu, Jie Huang et al.

The latent space of generative modeling is long dominated by the VAE encoder. The latents from the pretrained representation encoders (e.g., DINO, SigLIP, MAE) are previously considered inappropriate for generative modeling. Recently, RAE method lights the hope and reveals that the representation autoencoder can also achieve competitive performance as the VAE encoder. However, the integration of representation autoencoder into continuous autoregressive (AR) models, remains largely unexplored. In this work, we investigate the challenges of employing high-dimensional representation autoencoders within the AR paradigm, denoted as \textit{RAE-AR}. We focus on the unique properties of AR models and identify two primary hurdles: complex token-wise distribution modeling and the high-dimensionality amplified training-inference gap (exposure bias). To address these, we introduce token simplification via distribution normalization to ease modeling difficulty and improve convergence. Furthermore, we enhance prediction robustness by incorporating Gaussian noise injection during training to mitigate exposure bias. Our empirical results demonstrate that these modifications substantially bridge the performance gap, enabling representation autoencoder to achieve results comparable to traditional VAEs on AR models. This work paves the way for a more unified architecture across visual understanding and generative modeling.

Guohui Zhang, Hu Yu, Xiaoxiao Ma et al.

Reinforcement learning (RL) has demonstrated significant potential for post-training language models and autoregressive visual generative models, but adapting RL to masked generative models remains challenging. The core factor is that policy optimization requires accounting for the probability likelihood of each step due to its multi-step and iterative refinement process. This reliance on entire sampling trajectories introduces high computational cost, whereas natively optimizing random steps often yields suboptimal results. In this paper, we present MaskFocus, a novel RL framework that achieves effective policy optimization for masked generative models by focusing on critical steps. Specifically, we determine the step-level information gain by measuring the similarity between the intermediate images at each sampling step and the final generated image. Crucially, we leverage this to identify the most critical and valuable steps and execute focused policy optimization on them. Furthermore, we design a dynamic routing sampling mechanism based on entropy to encourage the model to explore more valuable masking strategies for samples with low entropy. Extensive experiments on multiple Text-to-Image benchmarks validate the effectiveness of our method.

Hu Yu, Hao Luo, Hangjie Yuan et al.

Autoregressive (AR) models for image generation typically adopt a two-stage paradigm of vector quantization and raster-scan ``next-token prediction", inspired by its great success in language modeling. However, due to the huge modality gap, image autoregressive models may require a systematic reevaluation from two perspectives: tokenizer format and regression direction. In this paper, we introduce the frequency progressive autoregressive (\textbf{FAR}) paradigm and instantiate FAR with the continuous tokenizer. Specifically, we identify spectral dependency as the desirable regression direction for FAR, wherein higher-frequency components build upon the lower one to progressively construct a complete image. This design seamlessly fits the causality requirement for autoregressive models and preserves the unique spatial locality of image data. Besides, we delve into the integration of FAR and the continuous tokenizer, introducing a series of techniques to address optimization challenges and improve the efficiency of training and inference processes. We demonstrate the efficacy of FAR through comprehensive experiments on the ImageNet dataset and verify its potential on text-to-image generation.

Hu Yu, Hao Luo, Fan Wang et al.

The correspondence between input text and the generated image exhibits opacity, wherein minor textual modifications can induce substantial deviations in the generated image. While, text embedding, as the pivotal intermediary between text and images, remains relatively underexplored. In this paper, we address this research gap by delving into the text embedding space, unleashing its capacity for controllable image editing and explicable semantic direction attributes within a learning-free framework. Specifically, we identify two critical insights regarding the importance of per-word embedding and their contextual correlations within text embedding, providing instructive principles for learning-free image editing. Additionally, we find that text embedding inherently possesses diverse semantic potentials, and further reveal this property through the lens of singular value decomposition (SVD). These uncovered properties offer practical utility for image editing and semantic discovery. More importantly, we expect the in-depth analyses and findings of the text embedding can enhance the understanding of text-to-image diffusion models.

Hu Yu, Biao Gong, Hangjie Yuan et al.

Masked-based autoregressive models have demonstrated promising image generation capability in continuous space. However, their potential for video generation remains under-explored. In this paper, we propose \textbf{VideoMAR}, a concise and efficient decoder-only autoregressive image-to-video model with continuous tokens, composing temporal frame-by-frame and spatial masked generation. We first identify temporal causality and spatial bi-directionality as the first principle of video AR models, and propose the next-frame diffusion loss for the integration of mask and video generation. Besides, the huge cost and difficulty of long sequence autoregressive modeling is a basic but crucial issue. To this end, we propose the temporal short-to-long curriculum learning and spatial progressive resolution training, and employ progressive temperature strategy at inference time to mitigate the accumulation error. Furthermore, VideoMAR replicates several unique capacities of language models to video generation. It inherently bears high efficiency due to simultaneous temporal-wise KV cache and spatial-wise parallel generation, and presents the capacity of spatial and temporal extrapolation via 3D rotary embeddings. On the VBench-I2V benchmark, VideoMAR surpasses the previous state-of-the-art (Cosmos I2V) while requiring significantly fewer parameters ($9.3\%$), training data ($0.5\%$), and GPU resources ($0.2\%$).

Xiaoxiao Ma, Feng Zhao, Pengyang Ling et al.

In this work, we first revisit the sampling issues in current autoregressive (AR) image generation models and identify that image tokens, unlike text tokens, exhibit lower information density and non-uniform spatial distribution. Accordingly, we present an entropy-informed decoding strategy that facilitates higher autoregressive generation quality with faster synthesis speed. Specifically, the proposed method introduces two main innovations: 1) dynamic temperature control guided by spatial entropy of token distributions, enhancing the balance between content diversity, alignment accuracy, and structural coherence in both mask-based and scale-wise models, without extra computational overhead, and 2) entropy-aware acceptance rules in speculative decoding, achieving near-lossless generation at about 85\% of the inference cost of conventional acceleration methods. Extensive experiments across multiple benchmarks using diverse AR image generation models demonstrate the effectiveness and generalizability of our approach in enhancing both generation quality and sampling speed.

Guohui Zhang, Hu Yu, Xiaoxiao Ma et al.

Recent studies have extended Reinforcement Learning with Verifiable Rewards (RLVR) to autoregressive (AR) visual generation and achieved promising progress. However, existing methods typically apply uniform optimization across all image tokens, while the varying contributions of different image tokens for RLVR's training remain unexplored. In fact, the key obstacle lies in how to identify more critical image tokens during AR generation and implement effective token-wise optimization for them. To tackle this challenge, we propose $\textbf{G}$roup $\textbf{C}$ritical-token $\textbf{P}$olicy $\textbf{O}$ptimization ($\textbf{GCPO}$), which facilitates effective policy optimization on critical tokens. We identify the critical tokens in RLVR-based AR generation from three perspectives, specifically: $\textbf{(1)}$ Causal dependency: early tokens fundamentally determine the later tokens and final image effect due to unidirectional dependency; $\textbf{(2)}$ Entropy-induced spatial structure: tokens with high entropy gradients correspond to image structure and bridges distinct visual regions; $\textbf{(3)}$ RLVR-focused token diversity: tokens with low visual similarity across a group of sampled images contribute to richer token-level diversity. For these identified critical tokens, we further introduce a dynamic token-wise advantage weight to encourage exploration, based on confidence divergence between the policy model and reference model. By leveraging 30\% of the image tokens, GCPO achieves better performance than GRPO with full tokens. Extensive experiments on multiple text-to-image benchmarks for both AR models and unified multimodal models demonstrate the effectiveness of GCPO for AR visual generation.

Hu Yu, Hao Luo, Fan Wang et al.

Diffusion probabilistic models (DPMs) have achieved impressive success in visual generation. While, they suffer from slow inference speed due to iterative sampling. Employing fewer sampling steps is an intuitive solution, but this will also introduces discretization error. Existing fast samplers make inspiring efforts to reduce discretization error through the adoption of high-order solvers, potentially reaching a plateau in terms of optimization. This raises the question: can the sampling process be accelerated further? In this paper, we re-examine the nature of sampling errors, discerning that they comprise two distinct elements: the widely recognized discretization error and the less explored approximation error. Our research elucidates the dynamics between these errors and the step by implementing a dual-error disentanglement strategy. Building on these foundations, we introduce an unified and training-free acceleration framework, DualFast, designed to enhance the speed of DPM sampling by concurrently accounting for both error types, thereby minimizing the total sampling error. DualFast is seamlessly compatible with existing samplers and significantly boost their sampling quality and speed, particularly in extremely few sampling steps. We substantiate the effectiveness of our framework through comprehensive experiments, spanning both unconditional and conditional sampling domains, across both pixel-space and latent-space DPMs.